{"id":"src_-khuqUkENPl1hYY6-1dXV","slug":"diffusers-releases","name":"Diffusers","type":"github","url":"https://github.com/huggingface/diffusers","orgId":"org_GDdYeYynEgCEBNBwy-m6s","productId":"prod_EHQ0crDRAcblP5NVrhyBu","productSlug":"diffusers","org":{"id":"org_GDdYeYynEgCEBNBwy-m6s","slug":"hugging-face","name":"Hugging Face"},"isPrimary":false,"isHidden":false,"discovery":"curated","metadata":"{\"evaluatedMethod\":\"github\",\"evaluatedAt\":\"2026-04-07T17:19:13.586Z\",\"changelogDetectedAt\":\"2026-04-07T17:27:26.845Z\",\"wellKnownSweptAt\":\"2026-10-01T06:01:26.362Z\",\"sourceActor\":{\"nextAlarmAt\":\"2026-10-09T08:42:13.034Z\",\"lastAlarmAt\":\"2026-10-08T08:42:14.477Z\",\"managed\":true}}","notice":null,"kind":"sdk","stars":34689,"starsFetchedAt":"2026-10-08T08:46:52.850Z","releaseCount":94,"releasesLast30Days":1,"avgReleasesPerWeek":0.2,"latestVersion":"v0.41.0","latestDate":"2026-10-06T06:43:25.000Z","changelogUrl":null,"hasChangelogFile":false,"lastFetchedAt":"2026-10-08T08:46:52.850Z","lastPolledAt":"2026-10-08T08:46:46.610Z","changeDetectedAt":null,"trackingSince":"2022-07-21T14:52:31.000Z","releases":[{"id":"rel_IDkNJbwyJ2YUTTP_3CIg6","version":"v0.41.0","type":"feature","title":"Diffusers 0.41.0: QwenImage 2.1 pipeline and more","summary":"Qwen-Image 2.1 unifies image generation and editing in one model with 7B visual generation parameters, multiple reference images, native RGBA transparency output, and LoRA training. ONNX support is deprecated in favor of Optimum, and previously deprecated LuminaText2ImgPipeline and Lumina2Text2ImgPipeline aliases were removed in favor of LuminaPipeline and Lumina2Pipeline.","titleGenerated":"Diffusers 0.41.0 adds Qwen-Image 2.1 pipeline, deprecates ONNX support","titleShort":"Qwen-Image 2.1 lands; ONNX support deprecated","breaking":"major","importance":4,"content":"> [!TIP]\r\n> This release brings Qwen-Image 2.1 to Diffusers, with text-to-image generation, image editing, native transparency, and LoRA training.\r\n>\r\n> Starting with this release, we’re adopting the Transformers release philosophy: coordinating minor releases around new model integrations, while including the other changes merged since the previous release. Patch releases remain focused on fixes. See our [release policy](https://huggingface.co/docs/diffusers/main/en/conceptual/contribution#when-new-model-or-pipeline-support-is-released).\r\n\r\n## **Qwen-Image 2.1**\r\n\r\n[Qwen-Image 2.1](https://huggingface.co/Qwen/Qwen-Image-2.1) unifies image generation and editing in one model. Its visual generation component has 7B parameters, and it supports multiple reference images and native RGBA output for transparent images. Check out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwenimage21) for more details.\r\n\r\nThanks to [@naykun](https://github.com/naykun) for the model integration ([#14804](https://github.com/huggingface/diffusers/pull/14804)).\r\n\r\n**Other highlights**\r\n\r\n- **Tensor-parallel checkpoint loading:** each rank reads its own slice of sharded weights directly, reducing the memory needed during loading. ([#14544](https://github.com/huggingface/diffusers/pull/14544))\r\n- **LTX-2.5 DFR:** new pipelines support generation with keyframe slots and composable spatial and temporal refinement. ([#14567](https://github.com/huggingface/diffusers/pull/14567))\r\n- **Cosmos 3:** SeaCache support and mixed W8A8/W8A16 denoising for ModelOpt FP8 checkpoints. ([#14663](https://github.com/huggingface/diffusers/pull/14663), [#14664](https://github.com/huggingface/diffusers/pull/14664))\r\n- **Modular Diffusers:** Wan 2.2 VACE gains modular blocks, and loading from existing local paths avoids unnecessary weight downloads. ([#14432](https://github.com/huggingface/diffusers/pull/14432), [#14797](https://github.com/huggingface/diffusers/pull/14797))\r\n- **More single-file loaders:** support for Krea 2 and MiniMax-H3. ([#14914](https://github.com/huggingface/diffusers/pull/14914), [#14839](https://github.com/huggingface/diffusers/pull/14839))\r\n- **Tests:** We removed the monolithic `test_pipelines_common.py` test suite to establish more modularity and transparent implementation of tests. Refer to https://github.com/huggingface/diffusers/pull/14669/ for more details.\r\n\r\n**Deprecations and compatibility**\r\n\r\n🚨 ONNX support is deprecated; use Optimum for ONNX Runtime workflows. ([#14658](https://github.com/huggingface/diffusers/pull/14658))\r\n\r\nPreviously deprecated APIs have been removed, including the `LuminaText2ImgPipeline` and `Lumina2Text2ImgPipeline` aliases. Use `LuminaPipeline` and `Lumina2Pipeline` instead. Older integrations should review the [removed code paths](https://github.com/huggingface/diffusers/pull/14838) before upgrading.\r\n\r\nThanks to everyone who contributed to this release!\r\n\r\n## All commits\r\n\r\n* [docs] Clean up links by @stevhliu in #14535\r\n* docs: fix 14 typos in docs, comments and docstrings by @iridescentWen in #14541\r\n* [docs] LTX-2.5 Modular Pipeline Docs by @dg845 in #14450\r\n* [agent docs] add lora test instructions. by @sayakpaul in #14549\r\n* refactor bria pipeline tests to the new mixin structure by @akshan-main in #14547\r\n* feat: improve issue reminder workflow and introduce conditional autoclose by @sayakpaul in #14477\r\n* [tests] AOT compilation failure fixes by @sayakpaul in #14553\r\n* [tests] skip hunyuan framepack group offloading tests by @sayakpaul in #14551\r\n* [tests] remove autoencodertestermixin and rename new one. by @sayakpaul in #14555\r\n* tests: fix CUDA OOM in VidTok slicing/tiling tests by @sayakpaul in #14554\r\n* refactor bria fibo edit pipeline tests to the new mixin structure by @akshan-main in #14577\r\n* refactor bria fibo pipeline tests to the new mixin structure by @akshan-main in #14570\r\n* refactor deepfloyd if pipeline tests to the new mixin structure by @akshan-main in #14580\r\n* Deprecate 'fp16_safetensors' command in CLI documentation by @sayakpaul in #14583\r\n* Fix duplicated words and a misspelling in messages and docstrings by @Sreekant13 in #14287\r\n* Fibo Edit: multi-reference conditioning and batching by @ShivamShrirao in #14566\r\n* [tests] Add Config to Exclude Modules from Leaf-Level Group Offloading by @dg845 in #14564\r\n* [tests] refactor flux control lora tests by @sayakpaul in #14557\r\n* [tests] migrate `test_pipelines.py` to use pytest. by @sayakpaul in #14222\r\n* [core] pass diffusers library name to kernels calls by @sayakpaul in #14441\r\n* [tests] hunyuan, ltx, ltx2 by @sayakpaul in #14587\r\n* make examples in docs device agnostic by @kaixuanliu in #14414\r\n* Move `LTX2Guidance` Guider to `guiders/` Folder by @dg845 in #14558\r\n* refactor deepfloyd if img2img pipeline tests to the new mixin structure by @akshan-main in #14596\r\n* refactor deepfloyd if inpainting pipeline tests to the new mixin structure by @akshan-main in #14602\r\n* refactor deepfloyd if superresolution pipeline tests to the new mixin structure by @akshan-main in #14603\r\n* refactor deepfloyd if img2img superresolution pipeline tests to the new mixin structure by @akshan-main in #14604\r\n* docs: correct the enable_gqa / cuDNN explanation by @yiyixuxu in #14561\r\n* refactor deepfloyd if inpainting superresolution pipeline tests to the new mixin structure by @akshan-main in #14606\r\n* [tests] migrate acestep, auraflow, cogview4, and helios tests by @sayakpaul in #14582\r\n* remove dead deepfloyd if shared test mixin by @akshan-main in #14611\r\n* [agent docs]add reporting guide by @yiyixuxu in #14531\r\n* migrate cogvideox lora tests to the pipeline-level mixins by @akshan-main in #14615\r\n* [tests] migrate flux2 lora. by @sayakpaul in #14610\r\n* migrate wan vace lora tests to the pipeline-level mixins by @akshan-main in #14614\r\n* post release 0.40.0 by @sayakpaul in #14545\r\n* migrate wan lora tests to the pipeline-level mixins by @akshan-main in #14613\r\n* tests: add ideogram4 tests for pipelines. by @sayakpaul in #14599\r\n* [tests] fix remote decoding tests and disable encode tests. by @sayakpaul in #14601\r\n* [tests] migrate remaining flux pipeline tests to use new mixins by @sayakpaul in #14560\r\n* [tests] refactor zimage and krea2 pipeline tests by @sayakpaul in #14563\r\n* [tests] refactor sdxl tests. by @sayakpaul in #14619\r\n* [tests] remove quanto tests. by @sayakpaul in #14254\r\n* tests: migrate tests from tests/lora by @sayakpaul in #14559\r\n* ci: fix invocation for compile tests. by @sayakpaul in #14552\r\n* Fix Ideogram 4 Callback Handling and Tests by @dg845 in #14621\r\n* Fix callback tensor inputs that are never bound in the denoising loop by @LuShadowX in #14416\r\n* [CI] Repair broken links by @stevhliu in #14627\r\n* migrate ideogram4 lora tests to the pipeline-level mixins by @akshan-main in #14628\r\n* refactor lumina2 pipeline tests to the new mixin structure by @akshan-main in #14629\r\n* [tests] refactor d series pipeline tests. by @sayakpaul in #14630\r\n* [tests] refactor a* pipeline tests. by @sayakpaul in #14622\r\n* [tests] refactor b* pipeline tests by @sayakpaul in #14625\r\n* [tests] refactor e and g series pipeline tests by @sayakpaul in #14631\r\n* [tests] refactor h and i series pipelines by @sayakpaul in #14633\r\n* [tests] refactor j series pipeline tests by @sayakpaul in #14632\r\n* [Download] Resolve the revision once at the beginning of from_pretrained by @Wauplin in #14340\r\n* Add LTX-2.5 DFR pipeline (keyframe slots, spatial detailing, tiled temporal rounds) by @alexanderar in #14567\r\n* skip these case for no-cuda device since the modeling contains cuda s… by @sywangyi in #14656\r\n* [tests] refactor remaining s series pipelines by @sayakpaul in #14654\r\n* [tests] refactor k-series pipeline tests by @sayakpaul in #14636\r\n* [tests] refactor v-series pipeline tests by @sayakpaul in #14653\r\n* [tests] refactor m and n series pipeline tests by @sayakpaul in #14638\r\n* [tests] refactor l-series pipeline tests by @sayakpaul in #14637\r\n* [tests] refactor c* pipeline tests. by @sayakpaul in #14626\r\n* [tests] refactor o and p series pipeline tests by @sayakpaul in #14646\r\n* [tests] refactor ltx2 dfr pipeline tests by @sayakpaul in #14655\r\n* [core] deprecate onnx by @sayakpaul in #14658\r\n* docs: correct stated defaults in Chroma pipeline docstrings by @iridescentWen in #14578\r\n* [tests] fix SVD tests by @sayakpaul in #14687\r\n* [tests] Split Pipeline Group Offloading Block-Level and Leaf-Level Tests by @dg845 in #14635\r\n* [tests] fix sana bf16 tests on ci. by @sayakpaul in #14688\r\n* Don't materialise the PRX attention mask by @DavidBert in #14677\r\n* [Cosmos 3] Fix Cosmos 3 Group Offloading Tests by @dg845 in #14693\r\n* Fix PriorTransformer Group Offloading Bug by @dg845 in #14695\r\n* [train_text_to_image_decoder.py] Fix the LR scheduler when num_train_epochs is passed in a distributed training env by @shoutoutuoadi325 in #14542\r\n* ModularPipeline.save_pretrained: change the default  `overwrite_modular_index` to be True by @yiyixuxu in #14659\r\n* add modular blockset for wan 2.2 vace by @akshan-main in #14432\r\n* Invalidate HookRegistry child-registries cache on enable/disable cache by @SuryanshSS1011 in #14093\r\n* Set scheduler begin index in remaining FlowMatch pipelines to avoid DtoH sync by @shoemoney in #14576\r\n* tests: add lora tester mixin for modular and migrate minimax h3. by @sayakpaul in #14605\r\n* agent doc: add a requirement for PR communications by @yiyixuxu in #14709\r\n* [Community] Add CachedSearch script: cheaper best-of-N for video pipelines by @shreshthsaini in #14735\r\n* [tests] partially fix the sd2 upscale tests by @sayakpaul in #14689\r\n* [httpx migration] Import httpx from huggingface_hub by @Wauplin in #14753\r\n* [docs] Improve navigation by @stevhliu in #14537\r\n* Route non-interactive library messages through loggers by @wunianze666-netizen in #14682\r\n* fix modular pipeline class resolution for families outside the auto-pipeline mappings by @akshan-main in #14736\r\n* docs: fix two docstrings that reference names the code does not have by @iridescentWen in #14733\r\n* [Cosmos3] Mixed W8A8/W8A16 denoising for ModelOpt FP8 checkpoints by @ConstBob in #14664\r\n* [torchao]: fix how FqnConfig is resolved and handled by @sayakpaul in #14686\r\n* [CI] Consolidate style, Serge review and GPU test bots under `@diffusers-bot` by @DN6 in #14623\r\n* fix(ci): harden GitHub Actions workflows (#14623) by @hf-security-analysis[bot] in #14788\r\n* changes in the pr_link_issue_reminder workjflow by @sayakpaul in #14798\r\n* fix(ci): harden GitHub Actions workflows (#14798) by @hf-security-analysis[bot] in #14800\r\n* [docs] Refactor get started section by @stevhliu in #14783\r\n* docs: pool eight small doc fixes into one PR by @simpleqt in #14757\r\n* Add Qwen-Image 2.1 by @naykun in #14804\r\n* Add SeaCache support for Cosmos3 pipelines by @yzhautouskay in #14663\r\n* extend tests/others/test_cli_commands.py::TestRunCommand::test_group_… by @sywangyi in #14697\r\n* Synchronize the compute stream before offloading to disk by @jiqing-feng in #14657\r\n* Fix flash/sage varlen prep under torch.compile with dynamic shapes by @ShivamShrirao in #14568\r\n* [core] Fix component device placement for split-device pipelines by @JingyaHuang in #14739\r\n* Fix Ascend NPU RMSNorm and fused-attention mask shapes by @mengchengTang in #14288\r\n* [docs] typo with hyperlink by @ariG23498 in #14826\r\n* [docs] Fix docstring arguments that don't match the signatures by @revanth-045 in #14778\r\n* [docs] Using diffusion pipelines by @stevhliu in #14805\r\n* [docs] Fix legacy hf CLI references (diffusers) by @Wauplin in #14830\r\n* Fix Wuerstchen LoRA scheduler steps for distributed epochs by @wunianze666-netizen in #14748\r\n* Add single file support for Qwen 2.1 by @DN6 in #14836\r\n* test and docs for xet dedup based file sharing. by @sayakpaul in #14835\r\n* Scope GITHUB_TOKEN permissions per job by @hf-security-analysis[bot] in #14852\r\n* Pin GitHub Actions to commit SHAs by @hf-security-analysis[bot] in #14853\r\n* [LoRA] add LoRA training for Qwen Image 2.1 by @linoytsaban in #14808\r\n* [docs] Adapters by @stevhliu in #14842\r\n* Fix TaylorSeer cache crash when the feature shape changes between steps by @hide3tu in #14831\r\n* downcast MiniMax-H3 position_ids at the device transfer on fp64-less backends by @SammyTourani in #14767\r\n* [MInimax H3] Fix VAE decode by @asomoza in #14754\r\n* [realfill] Fix the LR scheduler when num_train_epochs is passed in a distributed training env by @825pranav in #14885\r\n* [LoRA] convert Z-Image LoRAs that only carry the fused qkv and bare out attention keys by @christopher5106 in #14875\r\n* Fix LoRA loading for flattened CLIP text encoders by @BeyondBirthday07 in #14872\r\n* [diffusers-cli] add a dockerfile for diffusers cli hf jobs by @sayakpaul in #14550\r\n* [core] propagate sage attention updates. by @sayakpaul in #14584\r\n* [docs] document release philosophy by @sayakpaul in #14904\r\n* spit output to stderr when extracting GPU tests for PRs by @sayakpaul in #14847\r\n* Remove deprecated code paths by @DN6 in #14838\r\n* [Cosmos3] Fix Transfer SeaCache artifacts with control CFG by @yzhautouskay in #14897\r\n* [fix] Add return types by @stevhliu in #14874\r\n* [core] Shard tensor-parallel checkpoints on load and save by @JingyaHuang in #14544\r\n* [Modular] Avoid downloading weights when loading from an existing local path by @DN6 in #14797\r\n* Add single file support for Minimax H3 by @DN6 in #14839\r\n* Consolidate torch device backend dispatch by @DN6 in #14792\r\n* chore: add one additional copied from in qwenimage 2.1 vae by @sayakpaul in #14810\r\n* Add single file support for Krea 2 by @DN6 in #14914\r\n* Tag Krea 2 text encoder outputs as denoiser_input_fields by @tbsbngrtz in #14925\r\n* [Bugfix] Fix Cosmos3 FP8 tensor parallelism by @yzhautouskay in #14921\r\n* agent docs: support only what released checkpoints use by @yiyixuxu in #14750\r\n* Fix: Deprecating Siglip2ImageProcessorFast by @ariG23498 in #14781\r\n* [modular] Echo team joy future academy jd echo by @Gelercatty by @sayakpaul in #14941\r\n* [tests] refactor the pipeline-level attention processor tests by @sayakpaul in #14701\r\n* Configure fixed sampling sigmas on QwenImage21Pipeline by @naykun in #14950\r\n* [chore] remove force_upcast from autoencoder flux2 by @sayakpaul in #14946\r\n* [tests] remove `test_pipelines_common.py` by @sayakpaul in #14669\r\n* Release: v0.41.0-release by @sayakpaul (direct commit on v0.41.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @dg845\r\n    * [docs] LTX-2.5 Modular Pipeline Docs (#14450)\r\n    * [tests] Add Config to Exclude Modules from Leaf-Level Group Offloading (#14564)\r\n    * Move `LTX2Guidance` Guider to `guiders/` Folder (#14558)\r\n    * Fix Ideogram 4 Callback Handling and Tests (#14621)\r\n    * [tests] Split Pipeline Group Offloading Block-Level and Leaf-Level Tests (#14635)\r\n    * [Cosmos 3] Fix Cosmos 3 Group Offloading Tests (#14693)\r\n    * Fix PriorTransformer Group Offloading Bug (#14695)\r\n* @akshan-main\r\n    * refactor bria pipeline tests to the new mixin structure (#14547)\r\n    * refactor bria fibo edit pipeline tests to the new mixin structure (#14577)\r\n    * refactor bria fibo pipeline tests to the new mixin structure (#14570)\r\n    * refactor deepfloyd if pipeline tests to the new mixin structure (#14580)\r\n    * refactor deepfloyd if img2img pipeline tests to the new mixin structure (#14596)\r\n    * refactor deepfloyd if inpainting pipeline tests to the new mixin structure (#14602)\r\n    * refactor deepfloyd if superresolution pipeline tests to the new mixin structure (#14603)\r\n    * refactor deepfloyd if img2img superresolution pipeline tests to the new mixin structure (#14604)\r\n    * refactor deepfloyd if inpainting superresolution pipeline tests to the new mixin structure (#14606)\r\n    * remove dead deepfloyd if shared test mixin (#14611)\r\n    * migrate cogvideox lora tests to the pipeline-level mixins (#14615)\r\n    * migrate wan vace lora tests to the pipeline-level mixins (#14614)\r\n    * migrate wan lora tests to the pipeline-level mixins (#14613)\r\n    * migrate ideogram4 lora tests to the pipeline-level mixins (#14628)\r\n    * refactor lumina2 pipeline tests to the new mixin structure (#14629)\r\n    * add modular blockset for wan 2.2 vace (#14432)\r\n    * fix modular pipeline class resolution for families outside the auto-pipeline mappings (#14736)\r\n* @kaixuanliu\r\n    * make examples in docs device agnostic (#14414)\r\n* @alexanderar\r\n    * Add LTX-2.5 DFR pipeline (keyframe slots, spatial detailing, tiled temporal rounds) (#14567)\r\n* @ConstBob\r\n    * [Cosmos3] Mixed W8A8/W8A16 denoising for ModelOpt FP8 checkpoints (#14664)\r\n* @naykun\r\n    * Add Qwen-Image 2.1 (#14804)\r\n    * Configure fixed sampling sigmas on QwenImage21Pipeline (#14950)\r\n* @yzhautouskay\r\n    * Add SeaCache support for Cosmos3 pipelines (#14663)\r\n    * [Cosmos3] Fix Transfer SeaCache artifacts with control CFG (#14897)\r\n    * [Bugfix] Fix Cosmos3 FP8 tensor parallelism (#14921)\r\n","publishedAt":"2026-10-06T06:43:25.000Z","fetchedAt":"2026-10-06T08:37:40.906Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.41.0","media":[],"coverageCount":0},{"id":"rel_KE0EsMXgzIQ6e7slpXyYL","version":"v0.40.0","type":"feature","title":"Diffusers 0.40.0: New pipelines, tensor-parallel support, improved CLI, and more","summary":"New pipelines include MiniMax-H3 (video+audio), MiniMax Music 3, Stable Audio 3, LTX-2.5, Wan-Animate-2, and JoyAI-Image-Edit-Plus. Modular Diffusers is no longer experimental, and minimal tensor-parallel support is added.","titleGenerated":"Diffusers 0.40.0 adds MiniMax-H3, Stable Audio 3, and tensor-parallel support","titleShort":"MiniMax-H3, Stable Audio 3, tensor-parallel land","breaking":"none","importance":4,"content":"> [!TIP]\r\n> This release features several new pipelines, including LTX2.5, MiniMax H3, and Wan Animate 2. We're also graduating Modular Diffusers out of the experimental phase and announcing its stable support. Additionally, this release includes minimal support for tensor-parallel. There's a lot more that went down in this release. So, please consult the notes for details. \r\n\r\n## New Pipelines\r\n\r\n### MiniMax-H3\r\n\r\n[**MiniMax-H3**](https://huggingface.co/docs/diffusers/main/api/pipelines/minimax_h3) generates video and its soundtrack together. A single transformer denoises one packed sequence containing the text conditioning, the conditioning media, and the target video *and* audio latents — there is no separate vocoder and no post-hoc audio pass. Its conditioner is a `Qwen3VLForConditionalGeneration` whose unnormalized 50th-decoder-layer hidden state is read instead of the last one.\r\n\r\nMiniMax-H3 is integrated as [Modular Diffusers](https://huggingface.co/docs/diffusers/main/modular_diffusers/overview) blocks only — `MiniMaxH3Blocks` and their `MiniMaxH3ModularPipeline` are the whole integration. The conversion ships both checkpoint partitions in one repository and exposes three workflows (`t2va`, `fl2va`, `ref2va`) that can be pruned at `from_pretrained` time so only that task's components are declared and downloaded.\r\n\r\n### MiniMax Music 3\r\n\r\n[**MiniMax Music 3**](https://huggingface.co/docs/diffusers/main/api/pipelines/minimax_music3) produces complete songs up to five minutes long from lyrics and a music description, with expressive vocals and long-range structure. It is a hybrid of an autoregressive and a diffusion stage: an 8B Qwen3-based global language model predicts one semantic audio token per frame while a small depth decoder fills in seven residual RVQ codebooks, and their fused hidden states condition a 2.4B flow-matching transformer that produces Flow-VAE latents in overlapping chunks. A DAC-style decoder turns the latents into 44.1 kHz stereo audio.\r\n\r\n### Stable Audio 3\r\n\r\n[**Stable Audio 3**](https://huggingface.co/docs/diffusers/main/api/pipelines/stable_audio_3) is a text-to-audio model from Stability AI that generates high-quality stereo audio at 44.1 kHz. It uses a rectified-flow DiT conditioned on a frozen T5Gemma text encoder (via cross-attention) and on duration (a float embedded by `StableAudio3DurationEmbedder` and used for adaptive layer norm), and decodes with the SAME (Semantically-Aligned Music Encoder) autoencoder, `AutoencoderSAME`.\r\n\r\nThree pipelines ship: `StableAudio3Pipeline`, `StableAudio3AudioToAudioPipeline`, and `StableAudio3InpaintPipeline`.\r\n\r\nThanks to @buffett0323 for the contribution (https://github.com/huggingface/diffusers/pull/14119).\r\n\r\n### LTX-2.5\r\n\r\n[**LTX-2.5**](https://huggingface.co/docs/diffusers/main/api/pipelines/ltx2#ltx-25) reuses the existing `LTX2Pipeline` / `LTX2VideoTransformer3DModel` / `AutoencoderKLLTX2Video` classes — there is no separate pipeline class. The user-visible difference is the text encoder: LTX-2.5 is paired with a Gemma 4 (`gemma4_unified`) checkpoint, loaded automatically from a converted LTX-2.5 repo.\r\n\r\n[`Lightricks/LTX-2.5-Diffusers`](https://huggingface.co/Lightricks/LTX-2.5-Diffusers) ships both the distilled DiT (`transformer/`) and the full/SFT DiT (`transformer_full/`), plus everything two-stage generation needs. Alongside the checkpoint support, this release adds:\r\n\r\n- `LTX2VideoDiffusionDecoderModel` and `LTX2VideoDiffusionDecodePipeline` — a second video decoder over the same latent space, so latents are interchangeable between decoders.\r\n- A `duration_head` that predicts shot length from the text-connector output, so `num_frames` is auto-predicted by default when the loaded pipeline has one.\r\n- Prompt enhancement through a separate off-the-shelf `google/gemma-4-E2B-it` checkpoint (`enable_prompt_enhancement=True`).\r\n- `LTX25AutoBlocks` for Modular Diffusers ([#14453](https://github.com/huggingface/diffusers/pull/14453)).\r\n\r\n### Wan-Animate-2\r\n\r\n[**Wan-Animate-2**](https://huggingface.co/docs/diffusers/main/api/pipelines/wan_animate_2) by the Alibaba Wan Team animates a reference character image with the motion of a driving video. The driving video is processed in fixed-length segments: each segment runs a reference-extraction pass that caches the driving segment's K/V in every transformer layer, denoises against that cache, and is decoded inside the loop, because the next segment conditions on the previous segment's decoded tail frames.\r\n\r\nTwo presets are available — the base checkpoint samples with classifier-free guidance, and the distilled checkpoint samples in few steps without it. Guidance is owned by the pipeline's guider component, so there is no `guidance_scale` argument.\r\n\r\nThanks to @kelseyee for authoring the integration (https://github.com/huggingface/diffusers/pull/14413).\r\n\r\n### JoyAI-Image-Edit-Plus\r\n\r\n[**JoyAI-Image-Edit-Plus**](https://huggingface.co/docs/diffusers/main/api/pipelines/joyimage_edit_plus) extends the JoyAI-Image family (an 8B MLLM paired with a 16B MMDiT) to multi-image instruction-guided editing. It accepts 1–5 reference images plus a text instruction and composes elements from the references into a new image.\r\n\r\nThanks to @tangyanf for the contribution (https://github.com/huggingface/diffusers/pull/14032).\r\n\r\n### Cosmos 3 follow-ups\r\n\r\n[**Cosmos 3**](https://huggingface.co/docs/diffusers/main/api/pipelines/cosmos3) landed in 0.39.0 and gets substantially more coverage in this release:\r\n\r\n- A [Cosmos 3 Modular pipeline](https://github.com/huggingface/diffusers/pull/14110) (`Cosmos3OmniModularPipeline`), with [Transfer support](https://github.com/huggingface/diffusers/pull/14150) for precomputed control videos (edge, blur, depth, segmentation, world-scenario maps) generated autoregressively in chunks and stitched automatically.\r\n- [Edge support](https://github.com/huggingface/diffusers/pull/14181).\r\n- [Distilled (few-step) text-to-image and image-to-video](https://github.com/huggingface/diffusers/pull/14177) via `Cosmos3DistilledModularPipeline`.\r\n- [Model parallelism](https://github.com/huggingface/diffusers/pull/14054).\r\n\r\nThanks to @yzhautouskay and @atharvajoshi10 for the contributions.\r\n\r\n## Modular Pipeline Support\r\n\r\nModular Diffusers is **no longer marked experimental** ([#14525](https://github.com/huggingface/diffusers/pull/14525)) — the API warning has been dropped.\r\n\r\n- Three of this release's new integrations — **MiniMax-H3**, **MiniMax Music 3**, and **Wan-Animate-2** — ship as Modular blocks only, with no `DiffusionPipeline` half.\r\n- **Cosmos 3** ([#14110](https://github.com/huggingface/diffusers/pull/14110), [#14150](https://github.com/huggingface/diffusers/pull/14150), [#14177](https://github.com/huggingface/diffusers/pull/14177)) and **Krea 2** ([#14083](https://github.com/huggingface/diffusers/pull/14083), thanks to @Cedric-Perauer) gained modular pipelines, and **Anima** gained img2img blocks ([#13929](https://github.com/huggingface/diffusers/pull/13929), thanks to @PreethamNoelP).\r\n- **Branch-specific input defaults** ([#14234](https://github.com/huggingface/diffusers/pull/14234)): when sibling blocks of a `ConditionalPipelineBlocks` declare different defaults for the same input, `combine_inputs` now merges the default to `None` and records the per-block defaults in a new `InputParam.defaults_by_block` field. `get_block_state` falls back to the block's own declared default, so each branch resolves its own default when it actually runs. Docstrings render conflicted defaults as e.g. *\"defaults to None or 189, depending on the workflow\"*.\r\n- [Group offloading now works under auto offloading](https://github.com/huggingface/diffusers/pull/14358), and a [group-offload device mismatch](https://github.com/huggingface/diffusers/pull/14252) was fixed.\r\n- [Unused `intermediate_inputs` were cleaned up](https://github.com/huggingface/diffusers/pull/14278), [stale auto-docstrings are now detected in CI](https://github.com/huggingface/diffusers/pull/14241), and [Mellon custom-block required-input handling was fixed](https://github.com/huggingface/diffusers/pull/13888).\r\n\r\n> [!IMPORTANT]\r\n> Please try out Modular Diffusers and let us know about your feedback!\r\n\r\n## Core Library\r\n\r\n### Tensor parallelism\r\n\r\n[Tensor-parallel inference](https://github.com/huggingface/diffusers/pull/13718) is now supported for model inference on CUDA and AWS Neuron (Trainium/Inferentia), exposed through the same public API already used for context parallelism:\r\n\r\n```py\r\nfrom diffusers import TensorParallelConfig\r\n\r\npipe.transformer.enable_parallelism(config=TensorParallelConfig(mesh=tp_mesh))\r\n```\r\n\r\nSharding is model-agnostic and driven from a flat `_tp_plan`, which has been added to the FLUX.1, FLUX.2 and Qwen-Image DiTs. Check out the [docs](https://huggingface.co/docs/diffusers/main/en/training/distributed_inference#tensor-parallelism) for more details.\r\n\r\n### New quantization backends\r\n\r\n- [**SDNQ**](https://github.com/huggingface/diffusers/pull/14277) — a training-free backend supporting int8 down to 2-bit, FP8 and other low-bit float formats, with optional SVD correction, Hadamard rotation, and quantized INT8/FP8 matmul. Runs on CUDA, ROCm, XPU, MPS, and CPU. [SDNQ MiniMax-H3 loading](https://github.com/huggingface/diffusers/pull/14398) landed too. Thanks to @asomoza.\r\n- [**Nunchaku Lite**](https://github.com/huggingface/diffusers/pull/14100) for loading prequantized checkpoints, with [fused-kernel performance documented](https://github.com/huggingface/diffusers/pull/14458). Thanks to @rootonchair.\r\n\r\n### Attention, kernels and offloading\r\n\r\n- [Kernels are downloaded only when users request them](https://github.com/huggingface/diffusers/pull/14298)\r\n- [ROCm FlashAttention now uses the `kernels-community/aiter-flash-attn-ck` Hub kernel](https://github.com/huggingface/diffusers/pull/14436), dropping the `aiter` dependency. Thanks to @Abdennacer-Badaoui.\r\n- [Sequence-parallel support for the `_flash_3_varlen_hub` backend](https://github.com/huggingface/diffusers/pull/13809) and a [mask-handling fix](https://github.com/huggingface/diffusers/pull/14115). Thanks to @zhtmike.\r\n- [`DiffusionPipeline.device` deduction for split-device pipelines](https://github.com/huggingface/diffusers/pull/14383)\r\n- [Hook forward signatures are preserved](https://github.com/huggingface/diffusers/pull/14285). Thanks to @jloftin-nv.\r\n\r\n### CLI\r\n\r\nThe `diffusers-cli` was reworked for agentic use ([#13966](https://github.com/huggingface/diffusers/pull/13966)) and then cleaned up ([#14381](https://github.com/huggingface/diffusers/pull/14381)): `modular_model_index.json` is written when saving a custom block so `ModularPipeline.from_pretrained` can load and run custom blocks as pipelines, auto CPU offload works for Modular pipelines, `workflow` can be passed to Modular pipelines, and output saving handles multimodal output (e.g. LTX video frames + audio) and batched video.\r\n\r\nSkills are now installed through the CLI rather than the `Makefile` ([#14454](https://github.com/huggingface/diffusers/pull/14454)):\r\n\r\n```bash\r\ndiffusers-cli skills list\r\ndiffusers-cli skills add <skill name>\r\n```\r\n\r\n## 🚨 Breaking changes and deprecations\r\n\r\n- **JAX/Flax support has been removed** ([#14169](https://github.com/huggingface/diffusers/pull/14169)) — roughly 12k lines deleted. All `Flax*` classes and the `flax` extras are gone.\r\n- **Mixed-rank LoRAs without alpha keys now load at their intended scale** ([#14409](https://github.com/huggingface/diffusers/pull/14409)). Previously `get_peft_kwargs` took `lora_alpha` from the first entry of the rank dict and never revisited it, so every module whose rank differed from the first key's rank got an arbitrary, key-order-dependent scale. Ranks are now mirrored into the alphas when a checkpoint brings no alpha information (the diffusers/PEFT convention: alpha == rank, scale 1.0). Adapters with a declared alpha keep it, and uniform-rank adapters are unaffected. Existing mixed-rank, no-alpha LoRAs will now produce different (correct) results.\r\n- **`torch_dtype` is deprecated in favour of `dtype`** ([#14205](https://github.com/huggingface/diffusers/pull/14205), [#14313](https://github.com/huggingface/diffusers/pull/14313)), following `transformers`. `torch_dtype` still works but warns, and will be removed in 1.0.0. A [`torch.dtype` alias](https://github.com/huggingface/diffusers/pull/14162) was added for the docs.\r\n- **DDUF is deprecated** ([#14141](https://github.com/huggingface/diffusers/pull/14141)). `dduf_file` warns and will be removed in **0.41.0**.\r\n\r\n## Security\r\n\r\n- [Fixed a path-traversal / arbitrary out-of-directory file read via sharded checkpoint index files](https://github.com/huggingface/diffusers/pull/14182). Thanks to @buffett0323.\r\n- [A `SECURITY.md` was added](https://github.com/huggingface/diffusers/pull/14174).\r\n\r\n## Training\r\n\r\n- [Caption dropout and aspect-ratio buckets for the Krea 2 and Qwen-Image LoRA scripts](https://github.com/huggingface/diffusers/pull/14089), plus an [aspect-ratio bucketing fix and on-the-fly buckets across the DreamBooth scripts](https://github.com/huggingface/diffusers/pull/14158). Thanks to @linoytsaban.\r\n- [Krea 2 LoRA cards are tagged with the Turbo base model first](https://github.com/huggingface/diffusers/pull/14171) so the inference widget works.\r\n\r\n## LoRA\r\n\r\n- [ACE-Step LoRA support](https://github.com/huggingface/diffusers/pull/14193). Thanks to @chenyangzhu1.\r\n- [Fix LoRA hot-swapping recompilation with `different_shapes_for_compilation`](https://github.com/huggingface/diffusers/pull/14297). Thanks to @jiqing-feng.\r\n- [Only drop an adapter from `_merged_adapters` when it is unfused from all components](https://github.com/huggingface/diffusers/pull/14385).\r\n- [Fix local LoRA weight auto-discovery in offline mode](https://github.com/huggingface/diffusers/pull/14204). Thanks to @fropych.\r\n\r\n## Notable fixes\r\n\r\n- [Fix Kandinsky 5 I2V conditioning](https://github.com/huggingface/diffusers/pull/14282) — the image latent is no longer injected into `visual_cond` channels.\r\n- [Fix batched DiffusionGemma adaptive stopping](https://github.com/huggingface/diffusers/pull/14386)\r\n- [Fix image preprocessing for Cosmos 3](https://github.com/huggingface/diffusers/pull/14519) and [Cosmos 3 Edge generator K normalization](https://github.com/huggingface/diffusers/pull/14246)\r\n- [Fix AuraFlow model-parallelism device mismatch](https://github.com/huggingface/diffusers/pull/14273) and [AuraFlow VAE dtype mismatch on pipeline reuse](https://github.com/huggingface/diffusers/pull/14184)\r\n- [Make `WanTransformer3DModel`](https://github.com/huggingface/diffusers/pull/14236) and [`SD3Transformer2DModel`](https://github.com/huggingface/diffusers/pull/14186) hidden states contiguous\r\n- [Fix the rectified-flow time scheduler](https://github.com/huggingface/diffusers/pull/14011)\r\n- [Fix Helios auto-offload decode](https://github.com/huggingface/diffusers/pull/14140)\r\n- [Align `snapshot_download` with the latest `huggingface_hub`](https://github.com/huggingface/diffusers/pull/14118)\r\n- [Reduce FLUX int8 test peak memory with sequential offload](https://github.com/huggingface/diffusers/pull/13776)\r\n\r\n## Tests and infrastructure\r\n\r\nA large chunk of this release is test modernization: pipeline tests continue migrating to the new mixin structure (Wan, Qwen-Image, FLUX.2, CogVideoX, Stable Diffusion, and the LoRA pipeline tests), `tests/others`, training tests, and attention-processor tests moved to `pytest`, model-level and pipeline-level quantization tests were standardized, and an `output_shape` property was introduced in the pipeline tests. The agent-facing docs and skills under `.ai/` were expanded to cover tests, model implementation, and blockset conventions. \r\n\r\n## All commits\r\n\r\n* Fix model offloading and training tests + prevent examples timeout by @GiGiKoneti in #14091\r\n* fix `_flash_3_varlen_hub` mask handling by @zhtmike in #14115\r\n* Make doc builds faster by @mishig25 in #14131\r\n* [tests] fix autoencoderdc ml training fix. by @sayakpaul in #14129\r\n* [tests] fix tests for transformers latest stable. by @sayakpaul in #14120\r\n* fix rf time scheduler problem by @TheLovesOfLadyPurple in #14011\r\n* docs: improve docstring scheduling_lcm.py by @delmalih in #14133\r\n* feat: add JoyImage edit plus by @tangyanf in #14032\r\n* update licensing for others to 2026. by @sayakpaul in #14128\r\n* [fix] missing doc-builder imports by @stevhliu in #14134\r\n* add SP support for `_flash_3_varlen_hub` backend by @zhtmike in #13809\r\n* post release v0.39.0 by @sayakpaul in #14116\r\n* deprecate dduf. by @sayakpaul (direct commit on v0.40.0-release)\r\n* Revert \"deprecate dduf.\" by @sayakpaul (direct commit on v0.40.0-release)\r\n* docs: improve docstring scheduling_scm.py by @delmalih in #14136\r\n* Cosmos3 ModularPipeline by @yzhautouskay in #14110\r\n* docs: improve docstring scheduling_sasolver.py by @delmalih in #14148\r\n* Fix Helios auto offload decode by @pzarzycki in #14140\r\n* docs: improve docstring scheduling_sde_ve.py by @delmalih in #14172\r\n* Add Nunchaku Lite single-file quantization by @rootonchair in #14100\r\n* Transfer support for Cosmos3 ModularPipeline by @yzhautouskay in #14150\r\n* torch.dtype alias by @stevhliu in #14162\r\n* ask to share self-review notes by @yiyixuxu in #14185\r\n* Make `SD3Transformer2DModel` hidden states contiguous by @menglcai in #14186\r\n* align snapshot_download to respect hfh latest version by @sayakpaul in #14118\r\n* [skills] add notes about model implementation in our skills. by @sayakpaul in #14191\r\n* [lora training] tag krea2 LoRA card with Turbo base model first to enable inference widget by @linoytsaban in #14171\r\n* docs: improve docstring scheduling_tcd.py by @delmalih in #14192\r\n* docs: improve docstring scheduling_unclip.py by @delmalih in #14196\r\n* docs: improve docstring scheduling_repaint.py by @delmalih in #14199\r\n* [core] deprecate dduf by @sayakpaul in #14141\r\n* Fix local LoRA weight auto-discovery in offline mode by @fropych in #14204\r\n* Add tests and agent docs for `kwargs_type` input/output by @yiyixuxu in #14157\r\n* [Anima] Add img2img pipeline blocks by @PreethamNoelP in #13929\r\n* update agent doc to cover more on tests + include it in review CI scope by @yiyixuxu in #14197\r\n* Cosmos3 edge support by @atharvajoshi10 in #14181\r\n* Fixing path traversal/arbitrary out-of-directory file read via sharde… by @buffett0323 in #14182\r\n* add security.md as per internal notice. by @sayakpaul in #14174\r\n* [Quantization] Fix ModelOpt pre-quantized loading by @yzhautouskay in #14188\r\n* [tests] Pipeline test refactor by @sayakpaul in #14113\r\n* docs: improve docstring scheduling_k_dpm_2_discrete.py by @delmalih in #14212\r\n* Cosmos3 Distilled support by @yzhautouskay in #14177\r\n* Add not_params to ModularPipelineTesterMixin by @yiyixuxu in #14207\r\n* [agents doc] notes on when to create new blocksets for checkpoint variant by @yiyixuxu in #14208\r\n* Fix AuraFlow VAE dtype mismatch on pipeline reuse by @IvenHsu01 in #14184\r\n* [tests] fix autoencoderkl dtype tests by @sayakpaul in #14190\r\n* refactor qwenimage pipeline tests to the new mixin structure by @akshan-main in #14220\r\n* Add ace step lora support by @chenyangzhu1 in #14193\r\n* [skills] update test skills for standard pipelines. by @sayakpaul in #14223\r\n* Make `WanTransformer3DModel` hidden states contiguous before the block loop by @menglcai in #14236\r\n* refactor wan 2.2 image-to-video pipeline tests to the new mixin structure by @akshan-main in #14242\r\n* refactor wan vace pipeline tests to the new mixin structure by @akshan-main in #14231\r\n* refactor wan 2.2 pipeline tests to the new mixin structure by @akshan-main in #14240\r\n* refactor wan image-to-video pipeline tests to the new mixin structure by @akshan-main in #14228\r\n* refactor wan pipeline tests to the new mixin structure by @akshan-main in #14224\r\n* refactor wan video-to-video pipeline tests to the new mixin structure by @akshan-main in #14235\r\n* refactor wan animate pipeline tests to the new mixin structure by @akshan-main in #14239\r\n* fix test_pag_sdxl::StableDiffusionXLPAGPipelineIntegrationTests by @sywangyi in #13892\r\n* [chore] remove experimental api warning from lora modules. by @sayakpaul in #14248\r\n* [tests] fix cosmos3 tests by @sayakpaul in #14229\r\n* Fix Cosmos3 Edge generator K normalization by @atharvajoshi10 in #14246\r\n* [core] deprecate `torch_dtype` and prefer `dtype` following transformers. by @sayakpaul in #14205\r\n* Remove JAX/Flax by @DN6 in #14169\r\n* [tests] port attention processor tests to use pytest by @sayakpaul in #14161\r\n* [Modular Diffusers] Fix group offload device mismatch by @asomoza in #14252\r\n* [lora training] fix aspect ratio bucketing in dreambooth scripts (+ caption dropout, on-the-fly buckets) by @linoytsaban in #14158\r\n* Reduce FLUX int8 test peak memory with sequential offload by @jiqing-feng in #13776\r\n* Update `diffusers-cli` for agentic use by @DN6 in #13966\r\n* [modular] detect stale auto docstrings in CI + regenerate current ones by @yiyixuxu in #14241\r\n* Fix Wan and Motif video pipeline fast test failures by @sywangyi in #14269\r\n* Krea2 Modular Pipeline Support, Documentation, Test Cases by @Cedric-Perauer in #14083\r\n* [ci] ignore the token in vq_diffusion converter. by @sayakpaul in #14275\r\n* Cosmos3 Model Parallelism by @atharvajoshi10 in #14054\r\n* [tests] component manager tests by @sayakpaul in #13961\r\n* [modular] clean up unused intermediate_inputs by @yiyixuxu in #14278\r\n* refactor cogvideox video to video pipeline tests to the new mixin structure by @akshan-main in #14289\r\n* refactor cogvideox pipeline tests to the new mixin structure by @akshan-main in #14276\r\n* refactor cogvideox image to video pipeline tests to the new mixin structure by @akshan-main in #14283\r\n* refactor cogvideox fun control pipeline tests to the new mixin structure by @akshan-main in #14284\r\n* [tests] migrate training tests to pytest. by @sayakpaul in #14267\r\n* [tests] fix some CLI command tests by @sayakpaul in #14302\r\n* [lora training] add caption dropout and aspect ratio buckets to krea2 and qwen-image by @linoytsaban in #14089\r\n* added the technical blog by @charchit7 in #14306\r\n* [core] restrict logging of quant config based on the header size. by @sayakpaul in #14262\r\n* docs: improve docstring scheduling_k_dpm_2_ancetstral_discrete.py by @delmalih in #14226\r\n* [docs] add a warning note about device_map='cuda' usage. by @sayakpaul in #14261\r\n* [docs] minor corrections in the overview of quantization table by @sayakpaul in #14301\r\n* [docs] deprecate torch_dtype for dtype by @stevhliu in #14313\r\n* refactor qwenimage controlnet pipeline tests to the new mixin structure by @akshan-main in #14309\r\n* refactor qwenimage edit plus pipeline tests to the new mixin structure by @akshan-main in #14315\r\n* refactor qwenimage edit pipeline tests to the new mixin structure by @akshan-main in #14314\r\n* Preserve hook forward signature by @jloftin-nv in #14285\r\n* Fix LoRA hot-swapping recompilation with `different_shapes_for_compilation` by @jiqing-feng in #14297\r\n* refactor qwenimage img2img pipeline tests to the new mixin structure by @akshan-main in #14320\r\n* [docs] remove image generation benchmarks by @stevhliu in #14310\r\n* docs: improve docstring scheduling_ddpm_wuerstchen.py by @delmalih in #14319\r\n* [docs] update agentic contribution guidelines by @stevhliu in #14312\r\n* [tests] unify keep_in_32 tests in quantization test suites by @sayakpaul in #14257\r\n* [quantization] SDNQ core loading by @asomoza in #14277\r\n* docs: improve docstring scheduling folder - last batch by @delmalih in #14330\r\n* Modular branch specific defaults by @yiyixuxu in #14234\r\n* fix Mellon custom block required input handling by @wunianze666-netizen in #13888\r\n* gguf: fix dequantization. by @sayakpaul in #14333\r\n* [tests] standardize model-level quant tests by @sayakpaul in #14332\r\n* Add missing `Args:` entries to scheduler docstrings by @4ktLuffy in #14354\r\n* support group offloading under auto offloading by @yiyixuxu in #14358\r\n* refactor flux2 klein inpaint pipeline tests to the new mixin structure by @akshan-main in #14337\r\n* [kernels] download kernels when users request for it. by @sayakpaul in #14298\r\n* refactor flux2 klein pipeline tests to the new mixin structure by @akshan-main in #14336\r\n* refactor flux2 klein kv pipeline tests to the new mixin structure by @akshan-main in #14344\r\n* Auto-reply to new model requests with remote code guidance by @yiyixuxu in #14343\r\n* Add XPU expected slice for `SlowBnb4BitFluxControlWithLoraTests::test_lora_loading` by @jiqing-feng in #14202\r\n* [tests] Migrate `tests/others` to `pytest`. by @sayakpaul in #14299\r\n* [Kandinsky 5] Fix I2V conditioning: don't inject the image latent into visual_cond channels by @sashakunitsyn in #14282\r\n* use assert_tensors_close in the migrated pipeline tests by @akshan-main in #14369\r\n* Add MiniMax-H3 by @apolinario in #14355\r\n* [Quantization] SDNQ Minimax H3 loading by @asomoza in #14398\r\n* refactor qwenimage inpaint pipeline tests to the new mixin structure by @akshan-main in #14321\r\n* refactor flux2 pipeline tests to the new mixin structure by @akshan-main in #14326\r\n* [tests] introduce `output_shape` property in the pipeline tests. by @sayakpaul in #14253\r\n* Point the MiniMax-H3 docs install note at main by @apolinario in #14401\r\n* [core] support cp in h3. by @sayakpaul in #14407\r\n* [tests] tighten tests for `unload_components()` by @sayakpaul in #14406\r\n* [tests] implement todos in the modular tests for H3 followup by @sayakpaul in #14404\r\n* [tests] fix torchao tests by @sayakpaul in #14258\r\n* fix(lora): only drop adapter from _merged_adapters when unfused from all components by @AloysJehwin in #14385\r\n* [tests] guard peft imports in test_lora_loader_utils by @sayakpaul in #14434\r\n* [core] `DiffusionPipeline.device` deduction for split-device pipelines by @JingyaHuang in #14383\r\n* 🚨 Give mixed-rank LoRAs without alpha keys their intended scale by @apolinario in #14409\r\n* Ltx 2.5 by @sayakpaul in #14447\r\n* docs: add installation instructions for NVIDIA Spark (ARM64) devices by @mfuntowicz in #14448\r\n* Wan-Animate-2 (authored by @kelseyee) by @yiyixuxu in #14413\r\n* Move `LTX25AutoBlocks` to new file with new model name by @dg845 in #14453\r\n* [tests] tighten keep_in_32 modules tests by @sayakpaul in #14399\r\n* Fix AuraFlow model parallelism device mismatch and update XPU IP-Adap… by @sywangyi in #14273\r\n* feat: clean up peft related versioning voodoo. by @sayakpaul in #14463\r\n* docs: document fused-kernel performance in Nunchaku Lite guide by @rootonchair in #14458\r\n* [Agent docs] some updated based on recent integration by @yiyixuxu in #14452\r\n* [CI][tests] Fix LTX-2.5 Diffuson Decoder Tiling CI CPU Timeout by @dg845 in #14462\r\n* Add MiniMax Music 3 by @apolinario in #14456\r\n* Add LoRA loading support for MiniMax-H3 by @apolinario in #14408\r\n* [FA2] Use `kernels-community/aiter-flash-attn-ck` Hub kernel for ROCm FlashAttention (drop `aiter` dependency) by @Abdennacer-Badaoui in #14436\r\n* split up tests in modular pipelines by @sayakpaul in #14444\r\n* svd failures. by @sayakpaul (direct commit on v0.40.0-release)\r\n* Revert \"svd failures.\" by @sayakpaul (direct commit on v0.40.0-release)\r\n* Bump transformers from 4.47.0 to 5.5.0 in /examples/flux-control by @dependabot[bot] in #14179\r\n* FIX LoRA tests warning about unexpected keys by @BenjaminBossan in #14476\r\n* [tests] use eval() on t5 for deterministic results. by @sayakpaul in #14472\r\n* tests: fix qwen tests from getting oom'd in our CI. by @sayakpaul in #14474\r\n* fix SVD tests by @sayakpaul in #14475\r\n* tests: fix cuda model tests. by @sayakpaul in #14464\r\n* ci: drop stale tokenizers<0.23.0 override by @sayakpaul in #14504\r\n* Drop the experimental warning from Modular Diffusers by @yiyixuxu in #14525\r\n* [tests] skip parallelism tests for some models. by @sayakpaul in #14505\r\n* Fix batched DiffusionGemma adaptive stopping by @kashif in #14386\r\n* docs: fix typos in Kandinsky 5.0 video docs by @iridescentWen in #14345\r\n* Support DiffSynth-Studio MiniMax-H3 LoRAs by @apolinario in #14484\r\n* [tests] refactor stable diffusion pipeline tests by @sayakpaul in #14339\r\n* [tests] refactor pipeline-level quantization tests by @sayakpaul in #14435\r\n* replace enable_gpa with repeat_interleave for krea2 by @yiyixuxu in #14523\r\n* [CLI] Clean up and improvements to diffusers CLI by @DN6 in #14381\r\n* [CI] Allow single file tests to run as fast tests by @DN6 in #14324\r\n* Feat -- Stable Audio 3 by @buffett0323 in #14119\r\n* [core] Support tensor parallelism for model inference (CUDA, Neuron) by @JingyaHuang in #13718\r\n* [CI] Fix authentication on forked PRs by @DN6 in #14534\r\n* fix: image preprocessing for cosmos3 by @atharvajoshi10 in #14519\r\n* [tests] migrate lora tests for pipelines to use new mixins by @sayakpaul in #14268\r\n* [distributed] fix corrupted gradient problem under ring CP. by @sayakpaul in #14274\r\n* Restructure skill files and reference guides for CLI based installation. by @DN6 in #14454\r\n* [CI] Fix build and test step in release workflow by @DN6 in #14543\r\n* Release: v0.40.0-release by @sayakpaul (direct commit on v0.40.0-release)\r\n","publishedAt":"2026-08-20T14:53:43.000Z","fetchedAt":"2026-08-21T05:07:32.738Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.40.0","media":[],"coverageCount":0},{"id":"rel_3WBlN1zs_ipokoV2dmqUU","version":"v0.39.0","type":"feature","title":"Diffusers 0.39.0: New image and video pipelines, core library improvements, and more","summary":"Nine new pipelines are now available: Cosmos 3 (NVIDIA's unified world foundation model combining generation, reasoning, and action), Ideogram 4 (flow-matching text-to-image with asymmetric guidance), Krea 2 (single-stream MMDiT with Qwen3-VL encoding), DreamLite (ByteDance text-to-image and editing), PRX Pixel (pixel-space generation by Photoroom), Motif-Video (2B text-to-video and image-to-video), AnyFlow (any-step video diffusion from NVIDIA/NUS/MIT), JoyAI-Image-Edit (unified multimodal for editing with spatial control), and DiffusionGemma (block-diffusion language model). Additional enhancements across schedulers, training utilities, and core library components.","titleGenerated":"Diffusers 0.39.0 adds nine new image and video pipelines including Cosmos 3 and Ideogram 4","titleShort":"Nine new pipelines ship; Cosmos 3, Ideogram 4, Krea 2, DreamLite, PRX Pixel, Motif-Video, AnyFlow, JoyAI-Image-Edit, DiffusionGemma","breaking":"minor","importance":4,"content":"## New Pipelines\r\n\r\n### Cosmos 3\r\n\r\n[**Cosmos 3**](https://huggingface.co/docs/diffusers/main/api/pipelines/cosmos3) is NVIDIA's unified world foundation model (WFM) for Physical AI — a single omni-model built on a Mixture-of-Transformers (MoT) architecture that combines world generation, physical reasoning, and action generation, replacing the separate Predict, Reason, and Transfer models from earlier Cosmos releases. A single `Cosmos3OmniTransformer` runs a Qwen-style language model in parallel with a diffusion generation pathway, joined by a 3D multimodal RoPE. This release also lands video-to-video and action-conditioned generation, and a sound encoder.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13818](https://github.com/huggingface/diffusers/pull/13818)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/cosmos3](https://huggingface.co/docs/diffusers/main/api/pipelines/cosmos3)\r\n\r\nThanks to @atharvajoshi10, @yzhautouskay, and @MaciejBalaNV for the contributions.\r\n\r\n### Ideogram 4\r\n\r\n[**Ideogram 4**](https://huggingface.co/docs/diffusers/main/api/pipelines/ideogram4) is a flow-matching text-to-image model that uses a multimodal text encoder and an asymmetric classifier-free guidance scheme: a dedicated `unconditional_transformer` produces the negative branch with zeroed text features, while the main `transformer` consumes the full packed text + image sequence. The pipeline ships with structured prompt upsampling and LoRA loading support.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13859](https://github.com/huggingface/diffusers/pull/13859)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/ideogram4](https://huggingface.co/docs/diffusers/main/api/pipelines/ideogram4)\r\n\r\nThanks to @JinLiIdeogram for the contribution.\r\n\r\n### Krea 2\r\n\r\n[**Krea 2 (K2)**](https://huggingface.co/docs/diffusers/main/api/pipelines/krea2) is a flow-matching text-to-image model built around a single-stream MMDiT with grouped-query attention. A Qwen3-VL text encoder provides the conditioning — hidden states from twelve decoder layers are tapped per token and fused inside the transformer by a small text-fusion stage — and images are decoded with the Qwen-Image VAE. Both the base (midtrain) and TDM (distilled, few-step) checkpoints are supported, alongside a LoRA DreamBooth trainer.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/14045](https://github.com/huggingface/diffusers/pull/14045)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/krea2](https://huggingface.co/docs/diffusers/main/api/pipelines/krea2)\r\n\r\nThanks to @EleaZhong and @Abhinay1997 for the contribution.\r\n\r\n### DreamLite\r\n\r\n[**DreamLite**](https://huggingface.co/docs/diffusers/main/api/pipelines/dreamlite) is a text-to-image and image-editing model from ByteDance. It pairs a custom 2D U-Net (`DreamLiteUNetModel`) with the `Qwen3-VL` multimodal encoder as its prompt / image-instruction encoder, and uses an `AutoencoderTiny` (TAESD-style) VAE for fast latent encode/decode. A distilled `DreamLiteMobilePipeline` targets on-device, low-latency generation.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13815](https://github.com/huggingface/diffusers/pull/13815)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/dreamlite](https://huggingface.co/docs/diffusers/main/api/pipelines/dreamlite)\r\n\r\nThanks to @Carlofkl for the contribution.\r\n\r\n### PRX Pixel\r\n\r\n[**PRXPixel**](https://huggingface.co/docs/diffusers/main/api/pipelines/prx_pixel) is a pixel-space text-to-image generation model by Photoroom. A ~7B `PRXTransformer2DModel` denoises raw RGB images directly — no VAE is needed. The model is conditioned on a Qwen3-VL text encoder and uses flow matching where the transformer predicts the clean image at each step (x-prediction).\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13928](https://github.com/huggingface/diffusers/pull/13928)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/prx_pixel](https://huggingface.co/docs/diffusers/main/api/pipelines/prx_pixel)\r\n\r\nThanks to @DavidBert for the contribution.\r\n\r\n### Motif-Video\r\n\r\n[**Motif-Video**](https://huggingface.co/docs/diffusers/main/api/pipelines/motif_video) is a 2B parameter diffusion transformer for text-to-video and image-to-video generation. It features a three-stage architecture (12 dual-stream + 16 single-stream + 8 DDT decoder layers), Shared Cross-Attention for stable text-video alignment over long sequences, a T5Gemma2 text encoder, and rectified flow matching for velocity prediction.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13551](https://github.com/huggingface/diffusers/pull/13551)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/motif_video](https://huggingface.co/docs/diffusers/main/api/pipelines/motif_video)\r\n\r\nThanks to @waitingcheung for the contribution.\r\n\r\n### AnyFlow\r\n\r\n[**AnyFlow**](https://huggingface.co/docs/diffusers/main/api/pipelines/anyflow) from NVIDIA, NUS, and MIT is the first any-step video diffusion framework built on flow maps, enabling a single model (bidirectional or causal) to adapt to arbitrary inference budgets. It ships both bidirectional and FAR causal pipelines built on Wan2.1 backbones, covering text-to-video, image-to-video, and video-to-video.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13745](https://github.com/huggingface/diffusers/pull/13745)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/anyflow](https://huggingface.co/docs/diffusers/main/api/pipelines/anyflow)\r\n\r\nThanks to @Enderfga for the contribution.\r\n\r\n### JoyAI-Image-Edit\r\n\r\n[**JoyAI-Image**](https://huggingface.co/docs/diffusers/main/api/pipelines/joyimage_edit) is a unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing. It combines an 8B Multimodal LLM with a 16B Multimodal Diffusion Transformer (MMDiT). `JoyImageEditPipeline` supports general image editing as well as spatial editing capabilities including object move, object rotation, and camera control.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13444](https://github.com/huggingface/diffusers/pull/13444)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/joyimage_edit](https://huggingface.co/docs/diffusers/main/api/pipelines/joyimage_edit)\r\n\r\nThanks to @Moran232 for the contribution.\r\n\r\n### DiffusionGemma\r\n\r\n[**DiffusionGemma**](https://huggingface.co/docs/diffusers/main/api/pipelines/diffusion_gemma) is a block-diffusion encoder-decoder language model. A causal encoder reads the clean prompt (and any previously generated blocks) into a KV cache, and a bidirectional decoder denoises a fixed-size \"canvas\" of tokens by cross-attending to that cache, committing the most confident tokens via the new `BlockRefinementScheduler`. The released checkpoint is [`google/diffusiongemma-26B-A4B-it`](https://huggingface.co/google/diffusiongemma-26B-A4B-it).\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13986](https://github.com/huggingface/diffusers/pull/13986)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/diffusion_gemma](https://huggingface.co/docs/diffusers/main/api/pipelines/diffusion_gemma)\r\n\r\n### Anima\r\n\r\n[Anima](https://huggingface.co/docs/diffusers/main/api/pipelines/anima) is a 2 billion parameter text-to-image model created via a collaboration between CircleStone Labs and Comfy Org. It is focused mainly on anime concepts, characters, and styles, but is also capable of generating a wide variety of other non-photorealistic content.\r\n\r\nIt reuses the [**CosmosTransformer3DModel**](https://huggingface.co/docs/diffusers/main/en/api/models/cosmos_transformer3d#diffusers.CosmosTransformer3DModel) with a Qwen3 text encoder, a T5-token text conditioner, and the [**AutoencoderKLQwenImage**](https://huggingface.co/docs/diffusers/main/en/api/models/autoencoderkl_qwenimage#diffusers.AutoencoderKLQwenImage) VAE.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13732](https://github.com/huggingface/diffusers/pull/13732)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/anima](https://huggingface.co/docs/diffusers/main/api/pipelines/anima)\r\n\r\nThanks to @rmatif for the contribution.\r\n\r\n### LTX-2.X IC LoRA and HDR Pipelines\r\n\r\nNew `LTX2InContextPipeline` (in-context LoRA) and `LTX2HDRPipeline` extend the LTX-2 family with in-context conditioning and HDR video generation.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13572](https://github.com/huggingface/diffusers/pull/13572)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/ltx2](https://huggingface.co/docs/diffusers/main/api/pipelines/ltx2)\r\n\r\n## Modular Pipeline Support\r\n\r\n- We added a modular pipeline for **Stable Diffusion 3 (SD3)** in [https://github.com/huggingface/diffusers/pull/13324](https://github.com/huggingface/diffusers/pull/13324) (thanks to @AlanPonnachan).\r\n- We added a modular pipeline for **Anima** in [https://github.com/huggingface/diffusers/pull/13732](https://github.com/huggingface/diffusers/pull/13732) (thanks to @rmatif).\r\n- LoRA loading is now enabled on `ErnieImageModularPipeline` (#13948) and `Ideogram4ModularPipeline` (#13980), thanks to @SamuelTallet.\r\n\r\n## Core Library\r\n\r\n- [AutoRound quantization integration](https://github.com/huggingface/diffusers/pull/13552)\r\n- [safetensors support in the TorchAO backend](https://github.com/huggingface/diffusers/pull/13719) and [`_dequantize` for the TorchAO quantizer](https://github.com/huggingface/diffusers/pull/13538)\r\n- [BitsAndBytes quantization on MPS](https://github.com/huggingface/diffusers/pull/13915)\r\n- [`AutoPipelineForText2Audio`](https://github.com/huggingface/diffusers/pull/13511)\r\n- [AWS Neuron (Trainium/Inferentia) as an officially supported device](https://github.com/huggingface/diffusers/pull/13289) with [`torch.compile` compatibility](https://github.com/huggingface/diffusers/pull/13485)\r\n- [Bump `safetensors` to 0.8.0](https://github.com/huggingface/diffusers/pull/13971)\r\n- [Minimum supported `torch` version is now 2.6](https://github.com/huggingface/diffusers/pull/13725)\r\n- [Eliminate GPU sync overhead and CPU→GPU transfers across the LTX-2 pipeline](https://github.com/huggingface/diffusers/pull/13564)\r\n\r\n## All commits\r\n\r\n* [CI] Update all workflows with permissions  by @DN6 in #13672\r\n* [agents docs] update models.md with class attributes and attention mask  by @yiyixuxu in #13665\r\n* Fix ignored generator in FlowMatchEulerDiscreteScheduler  by @RobbinMarcus in #13678\r\n* [core] remove `txt_seq_lens` from qwen transformer.  by @sayakpaul in #13674\r\n* [tests] fix lora tests involving clip.  by @sayakpaul in #13675\r\n* post release 0.38.0  by @sayakpaul in #13670\r\n* Fix NameError in ZImageOmniPipeline when guidance_scale=0  by @Ricardo-M-L in #13527\r\n* Enable TorchAO int4wo quantization tests on XPU  by @jiqing-feng in #13537\r\n* [CI] QOL improvement for PR size labeler  by @DN6 in #13554\r\n* Fix BucketBatchSampler cache alignment in DreamBooth scripts  by @azolotenkov in #13353\r\n* chore: update pr_labeler.yml  by @hf-security-analysis[bot] in #13685\r\n* Address ernie-image review findings #13577  by @akshan-main in #13663\r\n* feat: Add Modular Pipeline for Stable Diffusion 3 (SD3)  by @AlanPonnachan in #13324\r\n* Update attention_backends.md to update FA3 minimum support to Ampere  by @sayakpaul in #13283\r\n* [CI] Bump style-bot SHA + switch to GitHub App  by @paulinebm in #13690\r\n* [feat] JoyAI-JoyImage-Edit support  by @Moran232 in #13444\r\n* Add LoRA support for Cosmos Predict 2.5 and fix pipeline to match official Cosmos repo  by @terarachang in #13664\r\n* Eliminate GPU sync overhead and CPU→GPU transfers across LTX2 pipeline  by @ViktoriiaRomanova in #13564\r\n* Gate deep imports from `torch.distributed`  by @hlky in #13673\r\n* Bump diffusers from 0.20.1 to 0.38.0 in /examples/research_projects/realfill  by @dependabot[bot] in #13692\r\n* Reduce WanAnimate TorchAO test input sizes to prevent OOM  by @jiqing-feng in #13541\r\n* add SP support for `flash_varlen_hub` backend  by @zhtmike in #13479\r\n* [ci] allow claude to open PRs for certain instructions.  by @sayakpaul in #13536\r\n* [ci] remove compel.  by @sayakpaul in #13715\r\n* styling fix. by @sayakpaul (direct commit on v0.39.0-release)\r\n* better usage of UV_PRERELEASE=allow  by @sayakpaul in #13716\r\n* [docs] add magcache to caching api listing  by @sayakpaul in #13714\r\n* [tests] refactor autoencoderkl tests  by @sayakpaul in #13368\r\n* [docs] add docs for JoyAI-Image-Edit  by @feice-huang in #13726\r\n* [tests] add attention backend tests.  by @sayakpaul in #13174\r\n* Install `transformers` from main for doc and staging  by @sayakpaul in #13723\r\n* Update Flax removal version  by @DN6 in #13729\r\n* examples/dreambooth: fix LR scheduler step count for multi-GPU in train_dreambooth_lora_sd3.py  by @Dev-X25874 in #13731\r\n* Serge reviewer  by @sayakpaul in #13735\r\n* [ci] switch to a more unique name  by @sayakpaul in #13738\r\n* fix autoencoder memory tests  by @sayakpaul in #13734\r\n* Fix GGUF to Work Better with `modules_to_not_convert` / `keep_in_fp32_modules`  by @dg845 in #13697\r\n* [tests] refactor ltx2 autoencoder tests to use latest mixins  by @sayakpaul in #13739\r\n* feat: Add Motif-Video model and pipelines  by @waitingcheung in #13551\r\n* Update contribution guidelines  by @DN6 in #13753\r\n* [agents] add a section on tests in the ai skill and integration guides.  by @sayakpaul in #13752\r\n* Add LTX-2.X IC LoRA and HDR Pipelines  by @dg845 in #13572\r\n* [tests] Fix controlnet tests  by @sayakpaul in #13736\r\n* [tests] fix bitsandbytes compile tests for flux.  by @sayakpaul in #13750\r\n* [core] minimum torch version is 2.6  by @sayakpaul in #13725\r\n* [tests] fix lora checkpoint serialization issues  by @sayakpaul in #13676\r\n* fix(randn_tensor): compare device.type, not torch.device, when suppressing MPS info log  by @Ricardo-M-L in #13508\r\n* [LLADA2] Fix llada2 review #13598  by @kashif in #13698\r\n* fix lfs pointer rejection problems for hub tests  by @sayakpaul in #13733\r\n* Fix training gradient underflow in quantization tests  by @jiqing-feng in #13539\r\n* examples/dreambooth: fix missing `weighting` chunk when using prior preservation in Flux and SD3 LoRA training  by @Dev-X25874 in #13743\r\n* Implement _dequantize for TorchAO quantizer  by @jiqing-feng in #13538\r\n* fix device mismatch issue for HiDreamTransformerTests  by @kaixuanliu in #13766\r\n* [docs] remove pipeline examples section  by @stevhliu in #13771\r\n* [CI] Replace print_env step in CI with diffusers-cli env  by @DN6 in #13662\r\n* update safetensors.torch._tobytes to safetensors.torch._to_ndarray  by @sywangyi in #13770\r\n* [agents docs] update pipelines.md:   by @yiyixuxu in #13570\r\n* fix(gguf): correct mismatched-shape error message in check_quantized_param_shape  by @Ricardo-M-L in #13504\r\n* [CI] claude_review: target source PR's branch for follow-up PRs  by @yiyixuxu in #13774\r\n* [WIP] chore: add utilities to check if call/forward methods are documented.  by @sayakpaul in #13758\r\n* Fix OOM in WanAnimate BitsAndBytes Training Test  by @jiqing-feng in #13777\r\n* ci: use uv overrides to make sure tokenizers install from <=0.23.0 under subs  by @sayakpaul in #13767\r\n* [LTX 2.3] update docs  by @linoytsaban in #13788\r\n* [docs] fix ace step checkpoint id.  by @sayakpaul in #13787\r\n* Add AnyFlow Any-Step Video Diffusion Pipelines (Bidirectional + FAR Causal)  by @Enderfga in #13745\r\n* Initialize ZImage pad tokens deterministically  by @sywangyi in #13805\r\n* note: torch.zeros -> torch.empty  by @sayakpaul in #13807\r\n* chore: enable Dependabot weekly GitHub Actions bumps  by @hf-dependantbot-rollout[bot] in #13812\r\n* [ci] shorten serge name.  by @sayakpaul in #13795\r\n* Adding Cosmos 3 to Diffusers  by @atharvajoshi10 in #13818\r\n* This PR updates the Stable Diffusion IP-Adapter integration  by @sywangyi in #13810\r\n* [AnyFlow] FAR: standalone causal-mask builder + torch.compile follow-up  by @Enderfga in #13792\r\n* Update repo_id for FLASH_4_HUB in attention_dispatch  by @WaterKnight1998 in #13822\r\n* Pin torchvision, torch, and torchaudio versions  by @sayakpaul in #13757\r\n* [docs] Follow ups for consistent forward docstrings  by @sayakpaul in #13779\r\n* refactor sana transformer tests  by @akshan-main in #13826\r\n* Fix redundant Z-Image terminal timestep  by @rootonchair in #13730\r\n* override torch stuff to prevent them from getting updated  by @sayakpaul in #13831\r\n* Add Anima modular pipeline  by @rmatif in #13732\r\n* [Feat] support AutoPipelineForText2Audio  by @RuixiangMa in #13511\r\n* moved to a webhook  by @tarekziade in #13836\r\n* refactor autoencoder tests (asymmetric_kl, ltx_video)  by @akshan-main in #13845\r\n* Fix duplicate safetensors.load_file call in _onload_from_disk when st…  by @gagandhakrey in #13851\r\n* Fix AttributeError in onnxruntime train_unconditional (args.report_to → args.logger)  by @Ricardo-M-L in #13524\r\n* [fix] CLIPTextModel with transformers >= 5.6 and from_single_file  by @asomoza in #13843\r\n* [tests] migrate group offloading tests to pytest  by @sayakpaul in #13234\r\n* [tests] refactor caching tests.  by @sayakpaul in #13235\r\n* Allow bucket reshuffling with DreamBooth caches  by @azolotenkov in #13712\r\n* [Neuron] Add AWS Neuron (Trainium/Inferentia) as an officially supported device  by @JingyaHuang in #13289\r\n* refactor autoencoder_magvit tests  by @akshan-main in #13834\r\n* refactor autoencoder_hunyuan_video tests  by @akshan-main in #13835\r\n* refactor autoencoder_kl_cogvideox tests  by @akshan-main in #13840\r\n* refactor autoencoder tests (vq, kvae_video, oobleck, consistency_decoder, tiny, vidtok)  by @akshan-main in #13849\r\n* updatge the test marigold to make it pass in xpu  by @sywangyi in #13856\r\n* [CI] Fix `torch_device` import in AutoencoderTesterMixin  by @DN6 in #13852\r\n* Add Ideogram 4  by @apolinario in #13859\r\n* Add structured prompt upsampling to Ideogram4  by @apolinario in #13860\r\n* [ci] add hook tests to our CI.  by @sayakpaul in #13848\r\n* fix kvae gradient checkpointing tests by @sayakpaul (direct commit on v0.39.0-release)\r\n* Revert \"fix kvae gradient checkpointing tests\" by @sayakpaul (direct commit on v0.39.0-release)\r\n* [tests] fix anyflow tests  by @sayakpaul in #13855\r\n* [CI] Refactor LTX Transformer Tests  by @DN6 in #13254\r\n* [CI] Refactor Bria Transformer Tests  by @DN6 in #13341\r\n* [CI] Refactor Chronoedit, PRX, EasyAnimate, Ovis transformer tests  by @DN6 in #13347\r\n* Add Cosmos3 action generation support  by @yzhautouskay in #13823\r\n* [docs] update philosophy.md (finally)  by @yiyixuxu in #13808\r\n* fix kvae gradient checkpointing tests  by @sayakpaul in #13865\r\n* [tests] Improve ideogram4 tests  by @sayakpaul in #13862\r\n* [tests] migrate test_hooks.py to pytest  by @sayakpaul in #13242\r\n* fix chronoedit tests on PRs  by @sayakpaul in #13870\r\n* Fix the QwenImage Attention mask under Ulysses SP  by @zhtmike in #13756\r\n* Add from_single_file support to ErnieImageTransformer2DModel  by @akshan-main in #13727\r\n* switch to a webhook  by @tarekziade in #13884\r\n* [chore] fix styling  by @sayakpaul in #13885\r\n* [cli] report all quant backends in diffusers-cli env.  by @sayakpaul in #13728\r\n* fix marigold depth failure in xpu and A100  by @sywangyi in #13886\r\n* refactor autoencoder tests (temporal decoder, cosmos, kvae, mochi)  by @akshan-main in #13832\r\n* refactor controlnet_cosmos tests  by @akshan-main in #13847\r\n* refactor unet_spatiotemporal tests  by @akshan-main in #13891\r\n* Fix fp16 LoRA unscale crash after validation in train_dreambooth_lora.py  by @HaozheZhang6 in #13895\r\n* [CI] Refactor Chroma , LongCat and HiDream Transformer Tests  by @DN6 in #13345\r\n* [CI] Refactor Skyreels, Lumina, Ominigen, Mochi transformer tests  by @DN6 in #13348\r\n* [CI] Refactor SD3 Transformer Test  by @DN6 in #13340\r\n* refactor unet tests (3d_condition, motion, controlnetxs)  by @akshan-main in #13897\r\n* refactor unet_1d tests  by @akshan-main in #13898\r\n* refactor unet_2d tests  by @akshan-main in #13901\r\n* [chore] log quant config to the user_agent  by @sayakpaul in #13850\r\n* Integrate AutoRound into Diffusers  by @xin3he in #13552\r\n* [tests] refactor UNet model tests to align with the new pattern  by @sayakpaul in #13153\r\n* [tests] fix vidtok tests  by @sayakpaul in #13894\r\n* quant config logging  by @sayakpaul in #13906\r\n* Use `device_map=\"auto\"` in single file tests to support large models on limited GPU memory  by @jiqing-feng in #13816\r\n* Fix incorrect batch temporal IDs for `cond_model_input` in Flux2 Klein img2img training  by @HaozheZhang6 in #13923\r\n* Incorporate safetensors support to TorchAO  by @hlky in #13719\r\n* [Pipelines] Add DreamLite text-to-image and image-edit pipelines  by @Carlofkl in #13815\r\n* [.ai] add self-review skill  by @yiyixuxu in #13917\r\n* update PR template and highlight AI-agent setup for contributors  by @yiyixuxu in #13913\r\n* [CI] implement a bot to remind prs to link issues if not.  by @sayakpaul in #13744\r\n* Point \"Coding with AI agents\" links at the rendered docs site  by @yiyixuxu in #13952\r\n* [tests] fix consistency decoder tests  by @sayakpaul in #13905\r\n* Add tutorial translations in Chinese  by @liwd190019 in #13932\r\n* Make root PHILOSOPHY.md a symlink to the docs philosophy page  by @yiyixuxu in #13954\r\n* fix(flux): enable true CFG with precomputed negative embeds  by @akshan-main in #13957\r\n* Enable LoRA loading on `ErnieImageModularPipeline`  by @SamuelTallet in #13948\r\n* Fix typo in `AutoModel`  by @neo in #13889\r\n* keep the agent symlinks  by @yiyixuxu in #13968\r\n* [CI] allow running tests as PR comments through a bot  by @sayakpaul in #13873\r\n* Add Cosmos3 video2video generation support  by @yzhautouskay in #13896\r\n* [CI] Refactor Z Image Transformer Tests   by @DN6 in #13253\r\n* fix untrusted fork secret mixing  by @sayakpaul in #13970\r\n* start by @sayakpaul (direct commit on v0.39.0-release)\r\n* Revert \"start\" by @sayakpaul (direct commit on v0.39.0-release)\r\n* Add Sound Encoder to Cosmos3  by @MaciejBalaNV in #13911\r\n* Add PRXPixelPipeline: pixel-space PRX text-to-image pipeline  by @DavidBert in #13928\r\n* [tests] port final set of model tests and others  by @sayakpaul in #13974\r\n* Add Ideogram4LoraLoaderMixin (LoRA loading for Ideogram4)  by @linoytsaban in #13921\r\n* Enable LoRA loading on `Ideogram4ModularPipeline`  by @SamuelTallet in #13980\r\n* [Neuron] Enable `torch.compile` compatibility with Neuron device  by @JingyaHuang in #13485\r\n* ci: don't remind on prs from admins, etc.  by @sayakpaul in #13965\r\n* ci: use hosted runners  by @tarekziade in #13987\r\n* Fix LTX2 connector token/register layout (regression from #13564)  by @Boffee in #13931\r\n* Fix `Ideogram4MRoPE` collapsing under `torch.autocast` (compute rotary in float32)  by @HaozheZhang6 in #13922\r\n* [Fix] Fix three final_layer LoRA conversion bugs in _convert_sd_scripts_to_ai_toolkit  by @lcheng321 in #14001\r\n* Add Krea 2 (K2) text-to-image pipeline and transformer  by @yiyixuxu in #14045\r\n* [.ai doc] Refine .ai attention-mask and component-mutation guidance  by @yiyixuxu in #13982\r\n* Enable BitsAndBytes quantization in MPS  by @LucasSte in #13915\r\n* fix(flux): tighten check_inputs validation  by @akshan-main in #13955\r\n* Krea 2 LoRA DreamBooth trainer  by @apolinario in #14046\r\n* Fix model cuda tests  by @sayakpaul in #13975\r\n* [.ai] document single-file model layout and \"don't reimplement Diffus…  by @yiyixuxu in #14048\r\n* fix claude code review fix in PRs.  by @sayakpaul in #14058\r\n* fix(bria_fibo): fix guidance_embeds, prompt_embeds, tensor-image and multi-image crashes  by @akshan-main in #13981\r\n* [tests] implement base model output caching in model-level tests  by @sayakpaul in #14059\r\n* [discrete diffusion] Add DiffusionGemma pipeline and schedulers  by @kashif in #13986\r\n* Add from_single_file support for SkyReelsV2 and ChronoEdit transformers  by @HaozheZhang6 in #13946\r\n* multi-GPU VAE Fix for Cosmos 3  by @atharvajoshi10 in #13924\r\n* docs: fix repeated word typo in set_timesteps docstring  by @ramkumar27072006 in #13876\r\n* feat: bump safetensors to 0.8.0  by @porunov in #13971\r\n* Fix DreamLite legacy block type aliases  by @ElectricGoal in #14066\r\n* Fix Kohya UNet LoRA key conversion for conv_in/conv_out/time_embedding  by @dxqb in #14006\r\n* [Tests] Skip layerwise casting tests on devices without float8_e4m3fn support  by @GiGiKoneti in #14073\r\n* [lora] add non-diffusers LoRA loading support for Krea 2 LoRAs  by @linoytsaban in #14074\r\n* Add doc pages for the DiffusionGemma schedulers  by @kashif in #14092\r\n* [chore] update to 2026 finally.  by @sayakpaul in #14079\r\n* fix #14063 for Kandinsky5 pipeline load with device_map=balanced  by @kaixuanliu in #14050\r\n* Complete Kohya LoRA conversion for Qwen and Z-Image  by @dxqb in #14080\r\n* Ideogram4 lora training  by @apolinario in #13861\r\n* ovis_image: fix guidance_scale / max_sequence_length / batched CFG / precomputed embeds + add pipeline test  by @HaozheZhang6 in #13944\r\n* [docs] fix qwen tokenizer in docstrings.  by @sayakpaul in #14098\r\n* Bump transformers from 4.47.0 to 5.3.0 in /examples/cogview4-control  by @dependabot[bot] in #14109\r\n* Fix mutable default args in lora_base.py  by @PrakshaaleJain in #14064\r\n* Fix FA3 varlen wrapper when hub kernel returns single tensor  by @<NOT FOUND> in #14102\r\n* support loading pipeline from transformer style (flat) repo   by @yiyixuxu in #14096\r\n* diffusers test installation package  by @sayakpaul in #14078\r\n* [tests] fix test_from_save_pretrained_dtype_inference  by @sayakpaul in #13872\r\n* Release: v0.39.0-release by @sayakpaul (direct commit on v0.39.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @DN6\r\n    * [CI] Update all workflows with permissions (#13672)\r\n    * [CI] QOL improvement for PR size labeler (#13554)\r\n    * Update Flax removal version (#13729)\r\n    * Update contribution guidelines (#13753)\r\n    * [CI] Replace print_env step in CI with diffusers-cli env (#13662)\r\n    * [CI] Fix `torch_device` import in AutoencoderTesterMixin (#13852)\r\n    * [CI] Refactor LTX Transformer Tests (#13254)\r\n    * [CI] Refactor Bria Transformer Tests (#13341)\r\n    * [CI] Refactor Chronoedit, PRX, EasyAnimate, Ovis transformer tests (#13347)\r\n    * [CI] Refactor Chroma , LongCat and HiDream Transformer Tests (#13345)\r\n    * [CI] Refactor Skyreels, Lumina, Ominigen, Mochi transformer tests (#13348)\r\n    * [CI] Refactor SD3 Transformer Test (#13340)\r\n    * [CI] Refactor Z Image Transformer Tests  (#13253)\r\n* @yiyixuxu\r\n    * [agents docs] update models.md with class attributes and attention mask (#13665)\r\n    * [agents docs] update pipelines.md:  (#13570)\r\n    * [CI] claude_review: target source PR's branch for follow-up PRs (#13774)\r\n    * [docs] update philosophy.md (finally) (#13808)\r\n    * [.ai] add self-review skill (#13917)\r\n    * update PR template and highlight AI-agent setup for contributors (#13913)\r\n    * Point \"Coding with AI agents\" links at the rendered docs site (#13952)\r\n    * Make root PHILOSOPHY.md a symlink to the docs philosophy page (#13954)\r\n    * keep the agent symlinks (#13968)\r\n    * Add Krea 2 (K2) text-to-image pipeline and transformer (#14045)\r\n    * [.ai doc] Refine .ai attention-mask and component-mutation guidance (#13982)\r\n    * [.ai] document single-file model layout and \"don't reimplement Diffus… (#14048)\r\n    * support loading pipeline from transformer style (flat) repo  (#14096)\r\n* @akshan-main\r\n    * Address ernie-image review findings #13577 (#13663)\r\n    * refactor sana transformer tests (#13826)\r\n    * refactor autoencoder tests (asymmetric_kl, ltx_video) (#13845)\r\n    * refactor autoencoder_magvit tests (#13834)\r\n    * refactor autoencoder_hunyuan_video tests (#13835)\r\n    * refactor autoencoder_kl_cogvideox tests (#13840)\r\n    * refactor autoencoder tests (vq, kvae_video, oobleck, consistency_decoder, tiny, vidtok) (#13849)\r\n    * Add from_single_file support to ErnieImageTransformer2DModel (#13727)\r\n    * refactor autoencoder tests (temporal decoder, cosmos, kvae, mochi) (#13832)\r\n    * refactor controlnet_cosmos tests (#13847)\r\n    * refactor unet_spatiotemporal tests (#13891)\r\n    * refactor unet tests (3d_condition, motion, controlnetxs) (#13897)\r\n    * refactor unet_1d tests (#13898)\r\n    * refactor unet_2d tests (#13901)\r\n    * fix(flux): enable true CFG with precomputed negative embeds (#13957)\r\n    * fix(flux): tighten check_inputs validation (#13955)\r\n    * fix(bria_fibo): fix guidance_embeds, prompt_embeds, tensor-image and multi-image crashes (#13981)\r\n* @AlanPonnachan\r\n    * feat: Add Modular Pipeline for Stable Diffusion 3 (SD3) (#13324)\r\n* @Moran232\r\n    * [feat] JoyAI-JoyImage-Edit support (#13444)\r\n* @terarachang\r\n    * Add LoRA support for Cosmos Predict 2.5 and fix pipeline to match official Cosmos repo (#13664)\r\n* @dg845\r\n    * Fix GGUF to Work Better with `modules_to_not_convert` / `keep_in_fp32_modules` (#13697)\r\n    * Add LTX-2.X IC LoRA and HDR Pipelines (#13572)\r\n* @waitingcheung\r\n    * feat: Add Motif-Video model and pipelines (#13551)\r\n* @kashif\r\n    * [LLADA2] Fix llada2 review #13598 (#13698)\r\n    * [discrete diffusion] Add DiffusionGemma pipeline and schedulers (#13986)\r\n    * Add doc pages for the DiffusionGemma schedulers (#14092)\r\n* @linoytsaban\r\n    * [LTX 2.3] update docs (#13788)\r\n    * Add Ideogram4LoraLoaderMixin (LoRA loading for Ideogram4) (#13921)\r\n    * [lora] add non-diffusers LoRA loading support for Krea 2 LoRAs (#14074)\r\n* @Enderfga\r\n    * Add AnyFlow Any-Step Video Diffusion Pipelines (Bidirectional + FAR Causal) (#13745)\r\n    * [AnyFlow] FAR: standalone causal-mask builder + torch.compile follow-up (#13792)\r\n* @atharvajoshi10\r\n    * Adding Cosmos 3 to Diffusers (#13818)\r\n    * multi-GPU VAE Fix for Cosmos 3 (#13924)\r\n* @rmatif\r\n    * Add Anima modular pipeline (#13732)\r\n* @JingyaHuang\r\n    * [Neuron] Add AWS Neuron (Trainium/Inferentia) as an officially supported device (#13289)\r\n    * [Neuron] Enable `torch.compile` compatibility with Neuron device (#13485)\r\n* @apolinario\r\n    * Add Ideogram 4 (#13859)\r\n    * Add structured prompt upsampling to Ideogram4 (#13860)\r\n    * Krea 2 LoRA DreamBooth trainer (#14046)\r\n    * Ideogram4 lora training (#13861)\r\n* @yzhautouskay\r\n    * Add Cosmos3 action generation support (#13823)\r\n    * Add Cosmos3 video2video generation support (#13896)\r\n* @xin3he\r\n    * Integrate AutoRound into Diffusers (#13552)\r\n* @Carlofkl\r\n    * [Pipelines] Add DreamLite text-to-image and image-edit pipelines (#13815)\r\n* @liwd190019\r\n    * Add tutorial translations in Chinese (#13932)\r\n* @MaciejBalaNV\r\n    * Add Sound Encoder to Cosmos3 (#13911)\r\n* @DavidBert\r\n    * Add PRXPixelPipeline: pixel-space PRX text-to-image pipeline (#13928)","publishedAt":"2026-07-03T08:55:32.000Z","fetchedAt":"2026-07-04T01:28:22.650Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.39.0","media":[],"coverageCount":0},{"id":"rel_IvR_7Xyyx8cX5KQMCq7kz","version":"v0.38.0","type":"feature","title":"Diffusers 0.38.0: New image and audio pipelines, Core library improvements, and more","summary":"## New Pipelines\r\n\r\n### LLaDA2\r\n\r\n[**LLaDA2**](https://huggingface.co/collections/inclusionAI/llada21) is a family of discrete diffusion language mode...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## New Pipelines\r\n\r\n### LLaDA2\r\n\r\n[**LLaDA2**](https://huggingface.co/collections/inclusionAI/llada21) is a family of discrete diffusion language models that generate text through block-wise iterative refinement. Instead of autoregressive token-by-token generation, LLaDA2 starts with a fully masked sequence and progressively unmasks tokens by confidence over multiple refinement steps. \r\n\r\n- PR: https://github.com/huggingface/diffusers/pull/13226\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/llada2](https://huggingface.co/docs/diffusers/main/api/pipelines/llada2)\r\n\r\n### Nucleus-MoE\r\n\r\nNucleusMoE-Image is a 2B active 17B parameter model trained with efficiency at its core. Our novel architecture highlights the scalability of a sparse MoE architecture for Image generation. \r\n\r\n- PR: https://github.com/huggingface/diffusers/pull/13317\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/nucleusmoe_image](https://huggingface.co/docs/diffusers/main/api/pipelines/nucleusmoe_image)\r\n\r\nThanks to @sippycoder for the contribution.\r\n\r\n### Ernie-Image\r\n\r\nERNIE-Image is a powerful and highly efficient image generation model with 8B parameters. \r\n\r\n- PR: https://github.com/huggingface/diffusers/pull/13432\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/ernie_image](https://huggingface.co/docs/diffusers/main/api/pipelines/ernie_image)\r\n\r\nThanks to @HsiaWinter for the contribution.\r\n\r\n### LongCat-AudioDiT\r\n\r\nLongCat-AudioDiT is a text-to-audio diffusion model from Meituan LongCat. \r\n\r\n- PR: https://github.com/huggingface/diffusers/pull/13483\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/longcat_audio_dit](https://huggingface.co/docs/diffusers/main/api/pipelines/longcat_audio_dit)\r\n\r\nThanks to @RuixiangMa for the contribution.\r\n\r\n### Ace-Step 1.5\r\n\r\nACE-Step 1.5 generates variable-length stereo audio at 48 kHz (10 seconds to 10 minutes) from text prompts and optional lyrics. The full system pairs a Language Model planner with a Diffusion Transformer (DiT) synthesizer; this pipeline wraps the DiT half of that stack, and consists of three components: an [**AutoencoderOobleck**](https://huggingface.co/docs/diffusers/main/en/api/models/autoencoder_oobleck#diffusers.AutoencoderOobleck) VAE that compresses waveforms into 25 Hz stereo latents, a Qwen3-based text encoder for prompt and lyric conditioning, and an [**AceStepTransformer1DModel**](https://huggingface.co/docs/diffusers/main/en/api/models/ace_step_transformer#diffusers.AceStepTransformer1DModel) DiT that operates in the VAE latent space using flow matching.\r\n\r\n- PR: [https://github.com/huggingface/diffusers/pull/13095](https://github.com/huggingface/diffusers/pull/13095)\r\n- Docs: [https://huggingface.co/docs/diffusers/main/api/pipelines/ace_step](https://huggingface.co/docs/diffusers/main/api/pipelines/ace_step)\r\n\r\nThanks to @[ChuxiJ](https://github.com/ChuxiJ) for the contribution.\r\n\r\n### Flux.2 Small Decoder\r\n\r\nMake your Flux.2 decoding faster with this new small decoder model from the Black Forest Labs. You can check it out [here](https://huggingface.co/black-forest-labs/FLUX.2-small-decoder). It was contributed by @huemin-art in [this PR](https://github.com/huggingface/diffusers/pull/13428).\r\n\r\n## Modular Pipeline Support\r\n\r\nWe added modular support for LTX-2 and Hunyuan 1.5. \r\n\r\n## Core Library\r\n\r\n- [Flash Attention 4 backend](https://github.com/huggingface/diffusers/issues/13280)\r\n- [FlashPack loading](https://github.com/huggingface/diffusers/issues/12700)\r\n- [Group offloading + TorchAO](https://github.com/huggingface/diffusers/pull/13276)\r\n- [`ring_anything` as a new CP backend](https://github.com/huggingface/diffusers/pull/13545)\r\n- [Profiling pipelines in Diffusers](https://github.com/huggingface/diffusers/pull/13356)\r\n\r\n## All commits\r\n\r\n* [Discrete Diffusion] Add LLaDA2 pipeline  by @kashif in #13226\r\n* [LLADA2] documentation fixes  by @kashif in #13333\r\n* [ci] claude in ci.  by @sayakpaul in #13297\r\n* [docs] kernels  by @stevhliu in #13139\r\n* [tests] Tests for conditional pipeline blocks  by @sayakpaul in #13247\r\n* avoid hardcode device in flux-control example  by @kaixuanliu in #13336\r\n* fix claude workflow to include id-token with write.  by @sayakpaul in #13338\r\n* Update LTX-2 Docs to Cover LTX-2.3 Models  by @dg845 in #13337\r\n* remove str option for quantization config in torchao  by @howardzhang-cv in #13291\r\n* [ci] include checkout step in claude review workflow  by @sayakpaul in #13352\r\n* change minimum version guard for torchao to 0.15.0  by @howardzhang-cv in #13355\r\n* [ci] move to assert instead of self.Assert*  by @sayakpaul in #13366\r\n* [docs] refactor model skill  by @stevhliu in #13334\r\n* Fix Ulysses SP backward with SDPA  by @zhtmike in #13328\r\n* Add train flux2 series lora config  by @tcaimm in #13011\r\n* [docs] Add NeMo Automodel training guide  by @pthombre in #13306\r\n* Fix: ensure consistent dtype and eval mode in pipeline save/load tests  by @YangKai0616 in #13339\r\n* [ci] support claude reviewing on forks.  by @sayakpaul in #13365\r\n* Fix MotionConv2d to cast blur_kernel to input dtype instead of reverse  by @YangKai0616 in #13364\r\n* chore: update claude_review.yml  by @hf-security-analysis[bot] in #13374\r\n* corrects single file path validation logic  by @andrew-w-ross in #13363\r\n* [docs] deprecate pipelines  by @stevhliu in #13157\r\n* 🔒 Pin GitHub Actions to commit SHAs  by @paulinebm in #13385\r\n* [docs] add auto docstring and parameter templates documentation for m…  by @yiyixuxu in #13382\r\n* Fix typos and grammar errors in documentation  by @GalacticAvenger in #13391\r\n* fix(ddim): validate eta is in [0, 1] in DDIMPipeline  by @NIK-TIGER-BILL in #13367\r\n* Fix Dynamo `lru_cache` warnings during `torch.compile`  by @jiqing-feng in #13384\r\n* [tests] refactor wan autoencoder tests  by @sayakpaul in #13371\r\n* NucleusMoE-Image  by @sippycoder in #13317\r\n* Add examples on how to profile a pipeline  by @sayakpaul in #13356\r\n* Update README.md of the profiling guide  by @sayakpaul in #13400\r\n* [CI] Refactor Cosmos Transformer Tests  by @DN6 in #13335\r\n* [tests] refactor autoencoderdc tests  by @sayakpaul in #13369\r\n* [CI] Hunyuan Transformer Tests Refactor  by @DN6 in #13342\r\n* Fix VAE offload encode device mismatch in DreamBooth scripts  by @azolotenkov in #13417\r\n* Remove references to torchao's AffineQuantizedTensor  by @andrewor14 in #13405\r\n* [tests] fix autoencoderdc tests  by @sayakpaul in #13424\r\n* [core] fix group offloading when using torchao  by @sayakpaul in #13276\r\n* Fix IndexError in HunyuanVideo I2V pipeline  by @kaixuanliu in #13244\r\n* improve Claude CI  by @yiyixuxu in #13397\r\n* FLUX.2 small decoder  by @huemin-art in #13428\r\n* [CI] Add PR/Issue Auto Labeler  by @DN6 in #13380\r\n* [CI] Add GLM Image Transformer Model Tests  by @DN6 in #13344\r\n* [CI] Use finegrained token for Issue Labeler  by @DN6 in #13433\r\n* Handle prompt embedding concat in Qwen dreambooth example  by @chenyangzhu1 in #13387\r\n* fix(qwen-image dreambooth): correct prompt embed repeats when using `--with_prior_preservation`  by @chenyangzhu1 in #13396\r\n* Cache RoPE freqs on device to avoid repeated CPU-GPU copy in QwenImage  by @akshan-main in #13406\r\n* [tests] tighten dependency testing.  by @sayakpaul in #13332\r\n* Fix grammar in LoRA documentation  by @Xyc2016 in #13423\r\n* Fix HunyuanVideo 1.5 I2V by preprocessing image at pixel resolution i…  by @akshan-main in #13440\r\n* [modular] Add LTX Video modular pipeline  by @akshan-main in #13378\r\n* Add ernie image  by @HsiaWinter in #13432\r\n* [core] fix fa4 integration  by @sayakpaul in #13443\r\n* FlashPack  by @hlky in #12700\r\n* [ptxla] fix pytorch xla inference on TPUs.  by @entrpn in #13463\r\n* fix some dtype issue for gguf / some gpu backends  by @HsiaWinter in #13464\r\n* Fix Qwen Image DreamBooth prior-preservation batch ordering  by @azolotenkov in #13441\r\n* [tests] fix deprecated attention processor testing.  by @sayakpaul in #13469\r\n* [tests] xfail clip related issues.  by @sayakpaul in #13454\r\n* [agent] add modular doc  by @yiyixuxu in #13410\r\n* [tests] fix training tests  by @sayakpaul in #13442\r\n* fix(profiling): preserve instance isolation when decorating methods  by @Akash504-ai in #13471\r\n* [Feat] Adds LongCat-AudioDiT pipeline   by @RuixiangMa in #13390\r\n* Fix Flux2 DreamBooth prior preservation prompt repeats  by @azolotenkov in #13415\r\n* chore: bump doc-builder SHA for PR upload workflow  by @rtrompier in #13476\r\n* Remove compile bottlenecks from ZImage pipeline  by @hitchhiker3010 in #13461\r\n* [chore] Add diffusers-format example to LongCatAudioDiTPipeline  by @RuixiangMa in #13483\r\n* [core] fix autoencoderkl qwenimage for xla  by @sayakpaul in #13480\r\n* add PR fork workable  by @paulinebm in #13438\r\n* Add modular pipeline for HunyuanVideo 1.5  by @akshan-main in #13389\r\n* [agents docs] add float64 gotcha  by @yiyixuxu in #13472\r\n* fix(ernie-image): avoid locals() comprehension scope issue in callback kwargs  by @songh11 in #13478\r\n* [Bugfix] Fix shape mismatch in LongCatAudioDiTTransformer conversion  by @RuixiangMa in #13494\r\n* feat: bump safetensors to `0.8.0-rc.0`  by @McPatate in #13470\r\n* fix(qwen): fix CFG failing when passing neg prompt embeds with none mask  by @Sunhill666 in #13379\r\n* add an example of spmd for flux on v5e-8  by @sayakpaul in #13474\r\n* Add FLUX.2 Klein Inpaint Pipeline  by @adi776borate in #13050\r\n* [docs] add a mention of torchao and other backends in speed memory docs.  by @sayakpaul in #13499\r\n* Fix Flux2 non-diffusers guidance LoRA conversion  by @yadferhad in #13486\r\n* add _native_npu_attention support mask shape like [B,1,1,S]  by @chang-zhijie in #13490\r\n* fix(freeu): run FFT in float32 for float16 inputs to avoid ComplexHalf  by @Ricardo-M-L in #13503\r\n* Fix non-deterministic T5 outputs in HiDream pipeline tests  by @kaixuanliu in #13534\r\n* Fix AuraFlow attn processors applying norm_added_q to key projection  by @Ricardo-M-L in #13533\r\n* add _repeated_blocks for ErnieImageTransformer2DModel  by @kaixuanliu in #13496\r\n* [CI] Fix BnB tests  by @DN6 in #13481\r\n* [tests] fix group offloading with disk tests  by @sayakpaul in #13491\r\n* [ci] feat: have pr labeler label for closing issues.  by @sayakpaul in #13548\r\n* Improve `trust_remote_code`  by @hlky in #13448\r\n* chore: bump doc-builder SHA for main doc build workflow  by @rtrompier in #13555\r\n* [ci] simplify release workflow.  by @sayakpaul in #13329\r\n* [attention backends] fix ring CP for flash and flash 3  by @sayakpaul in #13182\r\n* [agents docs] add pipelines.md etc  by @yiyixuxu in #13567\r\n* Add Ernie-Image modular pipeline  by @akshan-main in #13498\r\n* [agents docs] update modular.md  by @yiyixuxu in #13568\r\n* [docs] fix typo in AutoencoderOobleck docs  by @ivnvalex in #13642) \r\n* Fix ErnieImagePipeline pre-computed prompt_embeds + num_images_per_prompt shape mismatch  by @Ricardo-M-L in #13532\r\n* feat: support ring attention with arbitrary KV sequence lengths  by @songh11 in #13545\r\n* [ci] use tokenizers stable installtion in CI.  by @sayakpaul in #13562\r\n* NucleusMoE docs  by @sayakpaul in #13661\r\n* Fix UniPC scheduler device mismatch when using offloading  by @ParamChordiya in #13489\r\n* [Ernie-Image] Add lora support  by @asomoza in #13575\r\n* Add ACE-Step pipeline for text-to-music generation  by @ChuxiJ in #13095\r\n* Fix missing latents_bn_std dtype cast in VAE normalization  by @adi776borate in #13299\r\n* Release: v0.38.0-release by @sayakpaul (direct commit on v0.38.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @kashif\r\n    * [Discrete Diffusion] Add LLaDA2 pipeline (#13226)\r\n    * [LLADA2] documentation fixes (#13333)\r\n* @howardzhang-cv\r\n    * remove str option for quantization config in torchao (#13291)\r\n    * change minimum version guard for torchao to 0.15.0 (#13355)\r\n* @sippycoder\r\n    * NucleusMoE-Image (#13317)\r\n* @DN6\r\n    * [CI] Refactor Cosmos Transformer Tests (#13335)\r\n    * [CI] Hunyuan Transformer Tests Refactor (#13342)\r\n    * [CI] Add PR/Issue Auto Labeler (#13380)\r\n    * [CI] Add GLM Image Transformer Model Tests (#13344)\r\n    * [CI] Use finegrained token for Issue Labeler (#13433)\r\n    * [CI] Fix BnB tests (#13481)\r\n* @akshan-main\r\n    * Cache RoPE freqs on device to avoid repeated CPU-GPU copy in QwenImage (#13406)\r\n    * Fix HunyuanVideo 1.5 I2V by preprocessing image at pixel resolution i… (#13440)\r\n    * [modular] Add LTX Video modular pipeline (#13378)\r\n    * Add modular pipeline for HunyuanVideo 1.5 (#13389)\r\n    * Add Ernie-Image modular pipeline (#13498)\r\n* @HsiaWinter\r\n    * Add ernie image (#13432)\r\n    * fix some dtype issue for gguf / some gpu backends (#13464)\r\n* @hlky\r\n    * FlashPack (#12700)\r\n    * Improve `trust_remote_code` (#13448)\r\n* @RuixiangMa\r\n    * [Feat] Adds LongCat-AudioDiT pipeline  (#13390)\r\n    * [chore] Add diffusers-format example to LongCatAudioDiTPipeline (#13483)\r\n    * [Bugfix] Fix shape mismatch in LongCatAudioDiTTransformer conversion (#13494)\r\n* @adi776borate\r\n    * Add FLUX.2 Klein Inpaint Pipeline (#13050)\r\n    * Fix missing latents_bn_std dtype cast in VAE normalization (#13299)\r\n* @ChuxiJ\r\n    * Add ACE-Step pipeline for text-to-music generation (#13095)","publishedAt":"2026-05-01T05:52:27.000Z","fetchedAt":"2026-05-01T21:01:05.227Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.38.0","media":[],"coverageCount":0},{"id":"rel_TdmtCG-Re804wAMDMM_dF","version":"v0.37.1","type":"feature","title":"Fixes for AutoModel type hints in Modular Pipelines and Flux Klein LoRA loading ","summary":"-  Fix for loading `ModularPipelines` with `AutoModel` type hints in their `modular_model_index.json` #13271\r\n-  Fix Flux Klein LoRA loading #13313\r\n-...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"-  Fix for loading `ModularPipelines` with `AutoModel` type hints in their `modular_model_index.json` #13271\r\n-  Fix Flux Klein LoRA loading #13313\r\n-  Fix unguarded `torchvision` import in Cosmos Predict 2.5 #13321    \r\n","publishedAt":"2026-03-25T08:23:43.000Z","fetchedAt":"2026-04-07T17:27:25.592Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.37.1","media":[],"coverageCount":0},{"id":"rel_KkHFN8zt4taA9jQA70fAE","version":"v0.37.0","type":"feature","title":"Diffusers 0.37.0: Modular Diffusers, New image and video pipelines, multiple core library improvements, and more 🔥","summary":"## Modular Diffusers\r\n\r\nModular Diffusers introduces a new way to build diffusion pipelines by composing reusable blocks. Instead of writing entire pi...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## Modular Diffusers\r\n\r\nModular Diffusers introduces a new way to build diffusion pipelines by composing reusable blocks. Instead of writing entire pipelines from scratch, you can now mix and match building blocks to create custom workflows tailored to your specific needs! This complements the existing `DiffusionPipeline` class, providing a more flexible way to create custom diffusion pipelines.\r\n\r\nFind more details on how to get started with Modular Diffusers [here](https://huggingface.co/docs/diffusers/en/modular_diffusers/quickstart), and also check out the [announcement post](https://huggingface.co/blog/modular-diffusers).\r\n\r\n## New Pipelines and Models\r\n\r\n### Image 🌆\r\n\r\n- [Z Image Omni Base](https://huggingface.co/docs/diffusers/en/api/pipelines/z_image): Z-Image is the foundation model of the Z-Image family, engineered for good quality, robust generative diversity, broad stylistic coverage, and precise prompt adherence. While Z-Image-Turbo is built for speed, Z-Image is a full-capacity, undistilled transformer designed to be the backbone for creators, researchers, and developers who require the highest level of creative freedom. Thanks to @RuoyiDufor for contributing this in #12857.\r\n- [Flux2 Klein](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux2#diffusers.Flux2KleinPipeline):FLUX.2 [Klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference in as low as under a second. Built for applications that require real-time image generation without sacrificing quality, and runs on consumer hardware, with as little as 13GB VRAM.\r\n- [Qwen Image Layered](https://huggingface.co/Qwen/Qwen-Image-Layered): Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers. This layered representation unlocks inherent editability: each layer can be independently manipulated without affecting other content. Thanks to @naykun for contributing this in #12853.\r\n- [FIBO Edit](https://huggingface.co/docs/diffusers/main/en/api/pipelines/bria_fibo_edit): Fibo Edit is an 8B parameter image-to-image model that introduces a new paradigm of structured control, operating on JSON inputs paired with source images to enable deterministic and repeatable editing workflows. Featuring native masking for granular precision, it moves beyond simple prompt-based diffusion to offer explicit, interpretable control optimized for production environments. Its lightweight architecture is designed for deep customization, empowering researchers to build specialized “Edit” models for domain-specific tasks while delivering top-tier aesthetic quality. Thanks galbria for contributing it in [https://github.com/huggingface/diffusers/pull/12930](https://github.com/huggingface/diffusers/pull/12930).\r\n- [Cosmos Predict2.5](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cosmos): Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world. Thanks to @miguelmartin75 for contributing it in #12852.\r\n- [Cosmos Transfer2.5](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cosmos): Cosmos-Transfer2.5 is a conditional world generation model with adaptive multimodal control, that produces high-quality world simulations conditioned on multiple control inputs. These inputs can take different modalities—including edges, blurred video, segmentation maps, and depth maps. Thanks to @miguelmartin75 for contributing it in #13066.\r\n- [GLM-Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/glm_image): GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture, effectively pushing the upper bound of visual fidelity and fine-grained details. In general image generation quality, it aligns with industry-standard LDM-based approaches, while demonstrating significant advantages in knowledge-intensive image generation scenarios. Thanks to @zRzRzRzRzRzRzR for contributing it in [https://github.com/huggingface/diffusers/pull/12973](https://github.com/huggingface/diffusers/pull/12973).\r\n- [RAE](https://huggingface.co/docs/diffusers/main/api/models/autoencoder_rae): Representation Autoencoders (aka RAE) are an exciting alternative to traditional VAEs, typically used in the area of latent-space diffusion models of image generation. RAEs leverage pre-trained vision encoders and train lightweight decoders for the task of reconstruction.\r\n\r\n### Video + audio 🎥 🎼\r\n\r\n- [LTX-2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx2): LTX-2 is an audio-conditioned text-to-video generation model that can generate videos with synced audio. Full and distilled model inference, as well as two-stage inference with spatial sampling, is supported. We also support a conditioning pipeline that allows for passing different conditions (such as images, series of images, etc.). Check out the docs to learn more!\r\n- [Helios](https://huggingface.co/docs/diffusers/main/api/pipelines/helios): Helios is a 14B video generation model that runs at 17 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching a strong baseline in quality. Thanks to @SHYuanBest for contributing this in [https://github.com/huggingface/diffusers/pull/13208](https://github.com/huggingface/diffusers/pull/13208).\r\n\r\n## Improvements to Core Library\r\n\r\n### New caching methods\r\n\r\n- [MagCache](https://github.com/huggingface/diffusers/pull/12744) — thanks to @AlanPonnachan!\r\n- [TaylorSeer](https://github.com/huggingface/diffusers/pull/12648/) — thanks to @toilaluan!\r\n\r\n### New context-parallelism (CP) backends\r\n\r\n- [Unified Sequence Parallel attention](https://github.com/huggingface/diffusers/pull/12693) — thanks to @Bissmella!\r\n- [Ulysses Anything Attention](https://github.com/huggingface/diffusers/pull/12996) — thanks to @DefTruth!\r\n\r\n### Misc\r\n\r\n- Mambo-G Guidance: New guider implementation (#12862)\r\n- Laplace Scheduler for DDPM (#11320)\r\n- Custom Sigmas in UniPCMultistepScheduler (#12109)\r\n- MultiControlNet support for SD3 Inpainting (#11251)\r\n- Context parallel in native flash attention (#12829)\r\n- NPU Ulysses Attention Support (#12919)\r\n- Fix Wan 2.1 I2V Context Parallel Inference (#12909)\r\n- Fix Qwen-Image Context Parallel Inference (#12970)\r\n- Introduction to `@apply_lora_scale` decorator for simplifying model definitions (#12994)\r\n- Introduction of pipeline-level “cpu” `device_map` (#12811)\r\n- Enable CP for kernels-based attention backends (#12812)\r\n- Diffusers is fully functional with Transformers V5 (https://github.com/huggingface/diffusers/pull/12976)\r\n\r\nA lot of the above features/improvements came as part of the [MVP program](https://github.com/huggingface/diffusers/issues/12635) we have been running. Immense thanks to the contributors!\r\n\r\n## Bug Fixes\r\n\r\n- Fix QwenImageEditPlus on NPU (#13017)\r\n- Fix MT5Tokenizer → use `T5Tokenizer` for Transformers v5.0+ compatibility (#12877)\r\n- Fix Wan/WanI2V patchification (#13038)\r\n- Fix LTX-2 inference with `num_videos_per_prompt > 1` and CFG (#13121)\r\n- Fix Flux2 img2img prediction (#12855)\r\n- Fix QwenImage `txt_seq_lens` handling (#12702)\r\n- Fix `prefix_token_len` bug (#12845)\r\n- Fix ftfy imports in Wan and SkyReels-V2 (#12314, #13113)\r\n- Fix `is_fsdp` determination (#12960)\r\n- Fix GLM-Image `get_image_features` API (#13052)\r\n- Fix Wan 2.2 when either transformer isn't present (#13055)\r\n- Fix guider issue (#13147)\r\n- Fix torchao quantizer for new versions (#12901)\r\n- Fix GGUF for unquantized types with unquantize kernels (#12498)\r\n- Make Qwen hidden states contiguous for torchao (#13081)\r\n- Make Flux hidden states contiguous (#13068)\r\n- Fix Kandinsky 5 hardcoded CUDA autocast (#12814)\r\n- Fix `aiter` availability check (#13059)\r\n- Fix attention mask check for unsupported backends (#12892)\r\n- Allow `prompt` and `prior_token_ids` simultaneously in `GlmImagePipeline` (#13092)\r\n- GLM-Image batch support (#13007)\r\n- Cosmos 2.5 Video2World frame extraction fix (#13018)\r\n- ResNet: only use contiguous in training mode (#12977)\r\n\r\n## All commits\r\n\r\n* [PRX] Improve model compilation  by @WaterKnight1998 in #12787\r\n* Improve docstrings and type hints in scheduling_dpmsolver_singlestep.py  by @delmalih in #12798\r\n* [Modular]z-image  by @yiyixuxu in #12808\r\n* Fix Qwen Edit Plus modular for multi-image input  by @sayakpaul in #12601\r\n* [WIP] Add Flux2 modular  by @DN6 in #12763\r\n* [docs] improve distributed inference cp docs.  by @sayakpaul in #12810\r\n* post release 0.36.0  by @sayakpaul in #12804\r\n* Update distributed_inference.md to correct syntax  by @sayakpaul in #12827\r\n* [lora] Remove lora docs unneeded and add \" # Copied from ...\"  by @sayakpaul in #12824\r\n* support CP in native flash attention  by @sywangyi in #12829\r\n* [qwen-image] edit 2511 support  by @naykun in #12839\r\n* fix pytest tests/pipelines/pixart_sigma/test_pixart.py::PixArtSigmaPi…  by @sywangyi in #12842\r\n* Support for control-lora  by @lavinal712 in #10686\r\n* Add support for LongCat-Image  by @junqiangwu in #12828\r\n* fix the prefix_token_len bug  by @junqiangwu in #12845\r\n* extend TorchAoTest::test_model_memory_usage to other platform  by @sywangyi in #12768\r\n* Qwen Image Layered Support  by @naykun in #12853\r\n* Z-Image-Turbo ControlNet  by @hlky in #12792\r\n* Cosmos Predict2.5 Base: inference pipeline, scheduler & chkpt conversion  by @miguelmartin75 in #12852\r\n* more update in modular   by @yiyixuxu in #12560\r\n* Feature: Add Mambo-G Guidance as Guider  by @MatrixTeam-AI in #12862\r\n* Add `OvisImagePipeline` in `AUTO_TEXT2IMAGE_PIPELINES_MAPPING`  by @alvarobartt in #12876\r\n* Cosmos Predict2.5 14b Conversion  by @miguelmartin75 in #12863\r\n* Use `T5Tokenizer` instead of `MT5Tokenizer` (removed in Transformers v5.0+)  by @alvarobartt in #12877\r\n* Add z-image-omni-base implementation  by @RuoyiDu in #12857\r\n* fix torchao quantizer for new torchao versions  by @vkuzo in #12901\r\n* fix Qwen Image Transformer single file loading mapping function to be consistent with other loader APIs  by @mbalabanski in #12894\r\n* Z-Image-Turbo from_single_file fix  by @hlky in #12888\r\n* chore: fix dev version in setup.py  by @DefTruth in #12904\r\n* Community Pipeline: Add z-image differential img2img  by @r4inm4ker in #12882\r\n* Fix typo in src/diffusers/pipelines/cosmos/pipeline_cosmos2_5_predict.py  by @miguelmartin75 in #12914\r\n* Fix wan 2.1 i2v context parallel  by @DefTruth in #12909\r\n* fix the use of device_map in CP docs  by @sayakpaul in #12902\r\n* [core] remove unneeded autoencoder methods when subclassing from `AutoencoderMixin`  by @sayakpaul in #12873\r\n* Detect 2.0 vs 2.1 ZImageControlNetModel  by @hlky in #12861\r\n* Refactor environment variable assignments in workflow  by @paulinebm in #12916\r\n* Add codeQL workflow  by @paulinebm in #12917\r\n* Delete .github/workflows/codeql.yml by @paulinebm (direct commit on v0.37.0-release)\r\n* CodeQL workflow for security analysis by @paulinebm (direct commit on v0.37.0-release)\r\n* Check for attention mask in backends that don't support it  by @dxqb in #12892\r\n* [Flux.1] improve pos embed for ascend npu by computing on npu  by @zhangtao0408 in #12897\r\n* LTX Video 0.9.8  long multi prompt  by @yaoqih in #12614\r\n* Add FSDP option for Flux2  by @leisuzz in #12860\r\n* Add transformer cache context for SkyReels-V2 pipelines & Update docs  by @tolgacangoz in #12837\r\n* [docs] fix torchao typo.  by @sayakpaul in #12883\r\n* Update wan.md to remove unneeded hfoptions  by @sayakpaul in #12890\r\n* Improve docstrings and type hints in scheduling_edm_euler.py  by @delmalih in #12871\r\n* [Modular] Video for Mellon  by @asomoza in #12924\r\n* Add LTX 2.0 Video Pipelines  by @dg845 in #12915\r\n* Add environment variables to checkout step  by @paulinebm in #12927\r\n* Improve docstrings and type hints in scheduling_consistency_decoder.py  by @delmalih in #12928\r\n* Fix: Remove hardcoded CUDA autocast in Kandinsky 5 to fix import warning  by @adi776borate in #12814\r\n* Upgrade GitHub Actions for Node 24 compatibility  by @salmanmkc in #12865\r\n* fix the warning torch_dtype is deprecated  by @msdsm in #12841\r\n* [NPU] npu attention enable ulysses  by @TmacAaron in #12919\r\n* Torchao floatx version guard  by @howardzhang-cv in #12923\r\n* Bugfix for dreambooth flux2 img2img2  by @leisuzz in #12825\r\n* [Modular] qwen refactor  by @yiyixuxu in #12872\r\n* [modular] Tests for custom blocks in modular diffusers  by @sayakpaul in #12557\r\n* [chore] remove controlnet implementations outside controlnet module.  by @sayakpaul in #12152\r\n* [core] Handle progress bar and logging in distributed environments  by @sayakpaul in #12806\r\n* Improve docstrings and type hints in scheduling_consistency_models.py  by @delmalih in #12931\r\n* [Feature] MultiControlNet support for SD3Impainting  by @ishan-modi in #11251\r\n* Laplace Scheduler for DDPM  by @gapatron in #11320\r\n* Store vae.config.scaling_factor to prevent missing attr reference (sdxl advanced dreambooth training script)  by @Teriks in #12346\r\n* Add thread-safe wrappers for components in pipeline (examples/server-async/utils/requestscopedpipeline.py)  by @FredyRivera-dev in #12515\r\n* [Research] Latent Perceptual Loss (LPL) for Stable Diffusion XL  by @kashif in #11573\r\n* Change timestep device to cpu for xla  by @bhavya01 in #11501\r\n* [LoRA] add lora_alpha to sana README  by @linoytsaban in #11780\r\n* Fix wrong param types, docs, and handles noise=None in scale_noise of FlowMatching schedulers  by @Promisery in #11669\r\n* [docs] Remote inference  by @stevhliu in #12372\r\n* Align HunyuanVideoConditionEmbedding with CombinedTimestepGuidanceTextProjEmbeddings  by @samutamm in #12316\r\n* [Fix] syntax in QwenImageEditPlusPipeline  by @SahilCarterr in #12371\r\n* Fix ftfy name error in Wan pipeline  by @dsocek in #12314\r\n* [modular] error early in `enable_auto_cpu_offload`  by @sayakpaul in #12578\r\n* [ChronoEdit] support multiple loras  by @zhangjiewu in #12679\r\n* fix how `is_fsdp` is determined  by @sayakpaul in #12960\r\n* [LoRA] add LoRA support to LTX-2  by @sayakpaul in #12933\r\n* Fix: typo in autoencoder_dc.py  by @tvelovraf in #12687\r\n* [Modular] better docstring  by @yiyixuxu in #12932\r\n* [docs] polish caching docs.  by @sayakpaul in #12684\r\n* Fix typos  by @omahs in #12705\r\n* Fix link to diffedit implementation reference  by @JuanFKurucz in #12708\r\n*  Fix QwenImage txt_seq_lens handling  by @kashif in #12702\r\n* Bugfix for flux2 img2img2 prediction  by @leisuzz in #12855\r\n* Add Flag to `PeftLoraLoaderMixinTests` to Enable/Disable Text Encoder LoRA Tests  by @dg845 in #12962\r\n* Add Unified Sequence Parallel attention  by @Bissmella in #12693\r\n* [Modular] Changes for using WAN I2V  by @asomoza in #12959\r\n* Z rz rz rz rz rz rz r cogview  by @sayakpaul in #12973\r\n* Update distributed_inference.md to reposition sections  by @sayakpaul in #12971\r\n* [chore] make transformers version check stricter for glm image.  by @sayakpaul in #12974\r\n* Remove 8bit device restriction  by @SunMarc in #12972\r\n* `disable_mmap` in pipeline `from_pretrained`  by @hlky in #12854\r\n* [Modular] mellon utils  by @yiyixuxu in #12978\r\n* LongCat Image pipeline: Allow offloading/quantization of text_encoder component  by @Yahweasel in #12963\r\n* Add `ChromaInpaintPipeline`  by @hameerabbasi in #12848\r\n* fix Qwen-Image series context parallel  by @DefTruth in #12970\r\n* Flux2 klein  by @yiyixuxu in #12982\r\n* [modular] fix a bug in mellon param & improve docstrings  by @yiyixuxu in #12980\r\n* add klein docs.  by @sayakpaul in #12984\r\n* LTX 2 Single File Support  by @dg845 in #12983\r\n* [core] gracefully error out when attn-backend x cp combo isn't supported.  by @sayakpaul in #12832\r\n* Improve docstrings and type hints in scheduling_cosine_dpmsolver_multistep.py  by @delmalih in #12936\r\n* [Docs] Replace root CONTRIBUTING.md with symlink to source docs  by @delmalih in #12986\r\n* make style && make quality by @sayakpaul (direct commit on v0.37.0-release)\r\n* Revert \"make style && make quality\" by @sayakpaul (direct commit on v0.37.0-release)\r\n* [chore] make style to push new changes.  by @sayakpaul in #12998\r\n* Fibo edit pipeline  by @galbria in #12930\r\n* Fix variable name in docstring for PeftAdapterMixin.set_adapters  by @geekuillaume in #13003\r\n* Improve docstrings and type hints in scheduling_ddim_cogvideox.py  by @delmalih in #12992\r\n* [scheduler] Support custom sigmas in UniPCMultistepScheduler  by @a-r-r-o-w in #12109\r\n* feat: accelerate longcat-image with regional compile  by @lgyStoic in #13019\r\n* Improve docstrings and type hints in scheduling_ddim_flax.py  by @delmalih in #13010\r\n* Improve docstrings and type hints in scheduling_ddim_inverse.py  by @delmalih in #13020\r\n* fix Dockerfiles for cuda and xformers.  by @sayakpaul in #13022\r\n* Resnet only use contiguous in training mode.  by @jiqing-feng in #12977\r\n* feat: add qkv projection fuse for longcat transformers  by @lgyStoic in #13021\r\n* Improve docstrings and type hints in scheduling_ddim_parallel.py  by @delmalih in #13023\r\n* Improve docstrings and type hints in scheduling_ddpm_flax.py  by @delmalih in #13024\r\n* Improve docstrings and type hints in scheduling_ddpm_parallel.py  by @delmalih in #13027\r\n* Remove `*pooled_*` mentions from Chroma inpaint  by @hameerabbasi in #13026\r\n* Flag Flax schedulers as deprecated  by @delmalih in #13031\r\n* [modular] add auto_docstring & more doc related refactors   by @yiyixuxu in #12958\r\n* Upgrade GitHub Actions to latest versions  by @salmanmkc in #12866\r\n* [From Single File] support `from_single_file` method for `WanAnimateTransformer3DModel`  by @samadwar in #12691\r\n* Fix: Cosmos2.5 Video2World frame extraction and add default negative prompt  by @adi776borate in #13018\r\n* [GLM-Image] Add batch support for GlmImagePipeline  by @JaredforReal in #13007\r\n* [Qwen] avoid creating attention masks when there is no padding  by @kashif in #12987\r\n* [modular]support klein  by @yiyixuxu in #13002\r\n* [QwenImage] fix prompt isolation tests  by @sayakpaul in #13042\r\n* fast tok update  by @itazap in #13036\r\n* change to CUDA 12.9.  by @sayakpaul in #13045\r\n* remove torchao autoquant from diffusers docs  by @vkuzo in #13048\r\n* docs: improve docstring scheduling_dpm_cogvideox.py  by @delmalih in #13044\r\n* Fix Wan/WanI2V patchification  by @Jayce-Ping in #13038\r\n* LTX2 distilled checkpoint support  by @rootonchair in #12934\r\n* [wan] fix layerwise upcasting tests on CPU  by @sayakpaul in #13039\r\n* [ci] uniform run times and wheels for pytorch cuda.  by @sayakpaul in #13047\r\n* docs: fix grammar in fp16_safetensors CLI warning  by @Olexandr88 in #13040\r\n* [wan] fix wan 2.2 when either of the transformers isn't present.  by @sayakpaul in #13055\r\n* [bug fix] GLM-Image fit new `get_image_features` API  by @JaredforReal in #13052\r\n* Fix aiter availability check  by @lauri9 in #13059\r\n* [Modular]add a real quick start guide  by @yiyixuxu in #13029\r\n* feat: support Ulysses Anything Attention  by @DefTruth in #12996\r\n* Refactor Model Tests  by @DN6 in #12822\r\n* [Flux2] Fix LoRA loading for Flux2 Klein by adaptively enumerating transformer blocks  by @songkey in #13030\r\n* [Modular] loader related  by @yiyixuxu in #13025\r\n* [Modular] mellon doc etc  by @yiyixuxu in #13051\r\n* [modular] change the template modular pipeline card  by @sayakpaul in #13072\r\n* Add support for Magcache   by @AlanPonnachan in #12744\r\n* [docs] Fix syntax error in quantization configuration  by @sayakpaul in #13076\r\n* docs: improve docstring scheduling_dpmsolver_multistep_inverse.py  by @delmalih in #13083\r\n* [core] make flux hidden states contiguous  by @sayakpaul in #13068\r\n* [core] make qwen hidden states contiguous to make torchao happy.  by @sayakpaul in #13081\r\n* Feature/zimage inpaint pipeline  by @CalamitousFelicitousness in #13006\r\n* GGUF fix for unquantized types when using unquantize kernels  by @dxqb in #12498\r\n* docs: improve docstring scheduling_dpmsolver_multistep_inverse.py  by @delmalih in #13085\r\n* [modular]simplify components manager doc  by @yiyixuxu in #13088\r\n* ZImageControlNet cfg  by @hlky in #13080\r\n* [Modular] refactor Wan: modular pipelines by task etc  by @yiyixuxu in #13063\r\n* [Modular] guard `ModularPipeline.blocks` attribute  by @yiyixuxu in #13014\r\n* LTX 2 Improve `encode_video` by Accepting More Input Types  by @dg845 in #13057\r\n* Z image lora training  by @linoytsaban in #13056\r\n* [modular] add modular tests for Z-Image and Wan  by @sayakpaul in #13078\r\n* [Docs] Add guide for AutoModel with custom code  by @DN6 in #13099\r\n* [SkyReelsV2] Fix ftfy import  by @asomoza in #13113\r\n* [lora] fix non-diffusers lora key handling for flux2  by @sayakpaul in #13119\r\n* [CI] Refactor Wan Model Tests  by @DN6 in #13082\r\n* docs: improve docstring scheduling_edm_dpmsolver_multistep.py  by @delmalih in #13122\r\n* [Fix]Allow `prompt` and `prior_token_ids` to be provided simultaneously in `GlmImagePipeline`  by @JaredforReal in #13092\r\n* docs: improve docstring scheduling_flow_match_euler_discrete.py  by @delmalih in #13127\r\n* Cosmos Transfer2.5 inference pipeline: general/{seg, depth, blur, edge}  by @miguelmartin75 in #13066\r\n* [modular] add tests for robust model loading.  by @sayakpaul in #13120\r\n* Fix LTX-2 Inference when `num_videos_per_prompt > 1` and CFG is Enabled  by @dg845 in #13121\r\n* [CI] Fix `setuptools` `pkg_resources` Errors  by @dg845 in #13129\r\n* docs: improve docstring scheduling_flow_match_heun_discrete.py  by @delmalih in #13130\r\n* [CI] Fix `setuptools` `pkg_resources` Bug for PR GPU Tests  by @dg845 in #13132\r\n* fix cosmos transformer typing.  by @sayakpaul in #13134\r\n* Sunset Python 3.8 & get rid of explicit `typing` exports where possible  by @sayakpaul in #12524\r\n* feat: implement apply_lora_scale to remove boilerplate.  by @sayakpaul in #12994\r\n* [docs] fix ltx2 i2v docstring.  by @sayakpaul in #13135\r\n* [Modular] add different pipeine blocks to init  by @yiyixuxu in #13145\r\n* fix MT5Tokenizer  by @yiyixuxu in #13146\r\n* fix guider   by @yiyixuxu in #13147\r\n* [Modular] update doc for `ModularPipeline`  by @yiyixuxu in #13100\r\n* [Modular] add explicit workflow support   by @yiyixuxu in #13028\r\n* [LTX2] Fix wrong lora mixin  by @asomoza in #13144\r\n* [Pipelines] Remove k-diffusion  by @DN6 in #13152\r\n* [tests] accept recompile_limit from the user in tests  by @sayakpaul in #13150\r\n* [core] support device type device_maps to work with offloading.  by @sayakpaul in #12811\r\n* [Bug] Fix QwenImageEditPlus Series on NPU  by @zhangtao0408 in #13017\r\n* [CI] Add ftfy as a test dependency  by @DN6 in #13155\r\n* docs: improve docstring scheduling_flow_match_lcm.py  by @delmalih in #13160\r\n* [docs] add docs for qwenimagelayered  by @stevhliu in #13158\r\n* Flux2: Tensor tuples can cause issues for checkpointing  by @dxqb in #12777\r\n* [CI] Revert `setuptools` CI Fix as the Failing Pipelines are Deprecated  by @dg845 in #13149\r\n* Fix `ftfy` import for PRX Pipeline  by @dg845 in #13154\r\n* [core] Enable CP for kernels-based attention backends  by @sayakpaul in #12812\r\n* remove deps related to test from ci  by @sayakpaul in #13164\r\n* [CI] Fix new LoRAHotswap tests  by @DN6 in #13163\r\n* [gguf][torch.compile time] Convert to plain tensor earlier in dequantize_gguf_tensor  by @anijain2305 in #13166\r\n* Support Flux Klein peft (fal) lora format  by @asomoza in #13169\r\n* Fix T5GemmaEncoder loading for transformers 5.x composite T5GemmaConfig  by @DavidBert in #13143\r\n* Allow Automodel to use  `from_config` with custom code.  by @DN6 in #13123\r\n* Fix AutoModel `typing` Import Error  by @dg845 in #13178\r\n* migrate to `transformers` v5  by @sayakpaul in #12976\r\n* fix: graceful fallback when attention backends fail to import  by @sym-bot in #13060\r\n* [docs] Fix torchrun command argument order in docs  by @sayakpaul in #13181\r\n* [attention backends] use dedicated wrappers from fa3 for cp.  by @sayakpaul in #13165\r\n* Cosmos Transfer2.5 Auto-Regressive Inference Pipeline  by @miguelmartin75 in #13114\r\n* Fix wrong `do_classifier_free_guidance` threshold in ZImagePipeline  by @kirillsst in #13183\r\n* Fix Flash Attention 3 interface for new FA3 return format  by @veeceey in #13173\r\n* Fix LTX-2 image-to-video generation failure in two stages generation  by @Songrui625 in #13187\r\n* Fixing Kohya loras loading: Flux.1-dev loras with TE (\"lora_te1_\" prefix)  by @christopher5106 in #13188\r\n* [Modular] update the auto pipeline blocks doc  by @yiyixuxu in #13148\r\n* [tests] consistency tests for modular index  by @sayakpaul in #13192\r\n* [modular] fallback to default_blocks_name when loading base block classes in ModularPipeline  by @yiyixuxu in #13193\r\n* [chore] updates in the pypi publication workflow.  by @sayakpaul in #12805\r\n* [tests] enable cpu offload test in torchao without compilation.  by @sayakpaul in #12704\r\n* remove db utils from benchmarking  by @sayakpaul in #13199\r\n* [AutoModel] Fix bug with subfolders and local model paths when loading custom code  by @DN6 in #13197\r\n* [AutoModel] Allow registering `auto_map` to model config  by @DN6 in #13186\r\n* [Modular] Save Modular Pipeline weights to Hub  by @DN6 in #13168\r\n* docs: improve docstring scheduling_ipndm.py  by @delmalih in #13198\r\n* Clean up accidental files  by @DN6 in #13202\r\n* [modular]Update model card to include workflow  by @yiyixuxu in #13195\r\n* [modular] not pass trust_remote_code to external repos   by @yiyixuxu in #13204\r\n* [Modular] implement requirements validation for custom blocks  by @sayakpaul in #12196\r\n* cogvideo example: Distribute VAE video encoding across processes in CogVideoX LoRA training  by @jiqing-feng in #13207\r\n* Fix group-offloading bug  by @SHYuanBest in #13211\r\n* Add Helios-14B Video Generation Pipelines  by @dg845 in #13208\r\n* [Z-Image] Fix more `do_classifier_free_guidance` thresholds  by @asomoza in #13212\r\n* [lora] fix zimage lora conversion to support for more lora.  by @sayakpaul in #13209\r\n* adding lora support to z-image controlnet pipelines  by @christopher5106 in #13200\r\n* Add LTX2 Condition Pipeline  by @dg845 in #13058\r\n* Fix Helios paper link in documentation  by @SHYuanBest in #13213\r\n* [attention backends] change to updated repo and version.  by @sayakpaul in #13161\r\n* feat: implement rae autoencoder.  by @Ando233 in #13046\r\n* Release: v0.37.0-release by @sayakpaul (direct commit on v0.37.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @delmalih\r\n    * Improve docstrings and type hints in scheduling_dpmsolver_singlestep.py (#12798)\r\n    * Improve docstrings and type hints in scheduling_edm_euler.py (#12871)\r\n    * Improve docstrings and type hints in scheduling_consistency_decoder.py (#12928)\r\n    * Improve docstrings and type hints in scheduling_consistency_models.py (#12931)\r\n    * Improve docstrings and type hints in scheduling_cosine_dpmsolver_multistep.py (#12936)\r\n    * [Docs] Replace root CONTRIBUTING.md with symlink to source docs (#12986)\r\n    * Improve docstrings and type hints in scheduling_ddim_cogvideox.py (#12992)\r\n    * Improve docstrings and type hints in scheduling_ddim_flax.py (#13010)\r\n    * Improve docstrings and type hints in scheduling_ddim_inverse.py (#13020)\r\n    * Improve docstrings and type hints in scheduling_ddim_parallel.py (#13023)\r\n    * Improve docstrings and type hints in scheduling_ddpm_flax.py (#13024)\r\n    * Improve docstrings and type hints in scheduling_ddpm_parallel.py (#13027)\r\n    * Flag Flax schedulers as deprecated (#13031)\r\n    * docs: improve docstring scheduling_dpm_cogvideox.py (#13044)\r\n    * docs: improve docstring scheduling_dpmsolver_multistep_inverse.py (#13083)\r\n    * docs: improve docstring scheduling_dpmsolver_multistep_inverse.py (#13085)\r\n    * docs: improve docstring scheduling_edm_dpmsolver_multistep.py (#13122)\r\n    * docs: improve docstring scheduling_flow_match_euler_discrete.py (#13127)\r\n    * docs: improve docstring scheduling_flow_match_heun_discrete.py (#13130)\r\n    * docs: improve docstring scheduling_flow_match_lcm.py (#13160)\r\n    * docs: improve docstring scheduling_ipndm.py (#13198)\r\n* @yiyixuxu\r\n    * [Modular]z-image (#12808)\r\n    * more update in modular  (#12560)\r\n    * [Modular] qwen refactor (#12872)\r\n    * [Modular] better docstring (#12932)\r\n    * [Modular] mellon utils (#12978)\r\n    * Flux2 klein (#12982)\r\n    * [modular] fix a bug in mellon param & improve docstrings (#12980)\r\n    * [modular] add auto_docstring & more doc related refactors  (#12958)\r\n    * [modular]support klein (#13002)\r\n    * [Modular]add a real quick start guide (#13029)\r\n    * [Modular] loader related (#13025)\r\n    * [Modular] mellon doc etc (#13051)\r\n    * [modular]simplify components manager doc (#13088)\r\n    * [Modular] refactor Wan: modular pipelines by task etc (#13063)\r\n    * [Modular] guard `ModularPipeline.blocks` attribute (#13014)\r\n    * [Modular] add different pipeine blocks to init (#13145)\r\n    * fix MT5Tokenizer (#13146)\r\n    * fix guider  (#13147)\r\n    * [Modular] update doc for `ModularPipeline` (#13100)\r\n    * [Modular] add explicit workflow support  (#13028)\r\n    * [Modular] update the auto pipeline blocks doc (#13148)\r\n    * [modular] fallback to default_blocks_name when loading base block classes in ModularPipeline (#13193)\r\n    * [modular]Update model card to include workflow (#13195)\r\n    * [modular] not pass trust_remote_code to external repos  (#13204)\r\n* @sayakpaul\r\n    * Fix Qwen Edit Plus modular for multi-image input (#12601)\r\n    * [docs] improve distributed inference cp docs. (#12810)\r\n    * post release 0.36.0 (#12804)\r\n    * Update distributed_inference.md to correct syntax (#12827)\r\n    * [lora] Remove lora docs unneeded and add \" # Copied from ...\" (#12824)\r\n    * fix the use of device_map in CP docs (#12902)\r\n    * [core] remove unneeded autoencoder methods when subclassing from `AutoencoderMixin` (#12873)\r\n    * [docs] fix torchao typo. (#12883)\r\n    * Update wan.md to remove unneeded hfoptions (#12890)\r\n    * [modular] Tests for custom blocks in modular diffusers (#12557)\r\n    * [chore] remove controlnet implementations outside controlnet module. (#12152)\r\n    * [core] Handle progress bar and logging in distributed environments (#12806)\r\n    * [modular] error early in `enable_auto_cpu_offload` (#12578)\r\n    * fix how `is_fsdp` is determined (#12960)\r\n    * [LoRA] add LoRA support to LTX-2 (#12933)\r\n    * [docs] polish caching docs. (#12684)\r\n    * Z rz rz rz rz rz rz r cogview (#12973)\r\n    * Update distributed_inference.md to reposition sections (#12971)\r\n    * [chore] make transformers version check stricter for glm image. (#12974)\r\n    * add klein docs. (#12984)\r\n    * [core] gracefully error out when attn-backend x cp combo isn't supported. (#12832)\r\n    * make style && make quality\r\n    * Revert \"make style && make quality\"\r\n    * [chore] make style to push new changes. (#12998)\r\n    * fix Dockerfiles for cuda and xformers. (#13022)\r\n    * [QwenImage] fix prompt isolation tests (#13042)\r\n    * change to CUDA 12.9. (#13045)\r\n    * [wan] fix layerwise upcasting tests on CPU (#13039)\r\n    * [ci] uniform run times and wheels for pytorch cuda. (#13047)\r\n    * [wan] fix wan 2.2 when either of the transformers isn't present. (#13055)\r\n    * [modular] change the template modular pipeline card (#13072)\r\n    * [docs] Fix syntax error in quantization configuration (#13076)\r\n    * [core] make flux hidden states contiguous (#13068)\r\n    * [core] make qwen hidden states contiguous to make torchao happy. (#13081)\r\n    * [modular] add modular tests for Z-Image and Wan (#13078)\r\n    * [lora] fix non-diffusers lora key handling for flux2 (#13119)\r\n    * [modular] add tests for robust model loading. (#13120)\r\n    * fix cosmos transformer typing. (#13134)\r\n    * Sunset Python 3.8 & get rid of explicit `typing` exports where possible (#12524)\r\n    * feat: implement apply_lora_scale to remove boilerplate. (#12994)\r\n    * [docs] fix ltx2 i2v docstring. (#13135)\r\n    * [tests] accept recompile_limit from the user in tests (#13150)\r\n    * [core] support device type device_maps to work with offloading. (#12811)\r\n    * [core] Enable CP for kernels-based attention backends (#12812)\r\n    * remove deps related to test from ci (#13164)\r\n    * migrate to `transformers` v5 (#12976)\r\n    * [docs] Fix torchrun command argument order in docs (#13181)\r\n    * [attention backends] use dedicated wrappers from fa3 for cp. (#13165)\r\n    * [tests] consistency tests for modular index (#13192)\r\n    * [chore] updates in the pypi publication workflow. (#12805)\r\n    * [tests] enable cpu offload test in torchao without compilation. (#12704)\r\n    * remove db utils from benchmarking (#13199)\r\n    * [Modular] implement requirements validation for custom blocks (#12196)\r\n    * [lora] fix zimage lora conversion to support for more lora. (#13209)\r\n    * [attention backends] change to updated repo and version. (#13161)\r\n    * Release: v0.37.0-release\r\n* @DN6\r\n    * [WIP] Add Flux2 modular (#12763)\r\n    * Refactor Model Tests (#12822)\r\n    * [Docs] Add guide for AutoModel with custom code (#13099)\r\n    * [CI] Refactor Wan Model Tests (#13082)\r\n    * [Pipelines] Remove k-diffusion (#13152)\r\n    * [CI] Add ftfy as a test dependency (#13155)\r\n    * [CI] Fix new LoRAHotswap tests (#13163)\r\n    * Allow Automodel to use  `from_config` with custom code. (#13123)\r\n    * [AutoModel] Fix bug with subfolders and local model paths when loading custom code (#13197)\r\n    * [AutoModel] Allow registering `auto_map` to model config (#13186)\r\n    * [Modular] Save Modular Pipeline weights to Hub (#13168)\r\n    * Clean up accidental files (#13202)\r\n* @naykun\r\n    * [qwen-image] edit 2511 support (#12839)\r\n    * Qwen Image Layered Support (#12853)\r\n* @junqiangwu\r\n    * Add support for LongCat-Image (#12828)\r\n    * fix the prefix_token_len bug (#12845)\r\n* @hlky\r\n    * Z-Image-Turbo ControlNet (#12792)\r\n    * Z-Image-Turbo from_single_file fix (#12888)\r\n    * Detect 2.0 vs 2.1 ZImageControlNetModel (#12861)\r\n    * `disable_mmap` in pipeline `from_pretrained` (#12854)\r\n    * ZImageControlNet cfg (#13080)\r\n* @miguelmartin75\r\n    * Cosmos Predict2.5 Base: inference pipeline, scheduler & chkpt conversion (#12852)\r\n    * Cosmos Predict2.5 14b Conversion (#12863)\r\n    * Fix typo in src/diffusers/pipelines/cosmos/pipeline_cosmos2_5_predict.py (#12914)\r\n    * Cosmos Transfer2.5 inference pipeline: general/{seg, depth, blur, edge} (#13066)\r\n    * Cosmos Transfer2.5 Auto-Regressive Inference Pipeline (#13114)\r\n* @RuoyiDu\r\n    * Add z-image-omni-base implementation (#12857)\r\n* @r4inm4ker\r\n    * Community Pipeline: Add z-image differential img2img (#12882)\r\n* @yaoqih\r\n    * LTX Video 0.9.8  long multi prompt (#12614)\r\n* @dg845\r\n    * Add LTX 2.0 Video Pipelines (#12915)\r\n    * Add Flag to `PeftLoraLoaderMixinTests` to Enable/Disable Text Encoder LoRA Tests (#12962)\r\n    * LTX 2 Single File Support (#12983)\r\n    * LTX 2 Improve `encode_video` by Accepting More Input Types (#13057)\r\n    * Fix LTX-2 Inference when `num_videos_per_prompt > 1` and CFG is Enabled (#13121)\r\n    * [CI] Fix `setuptools` `pkg_resources` Errors (#13129)\r\n    * [CI] Fix `setuptools` `pkg_resources` Bug for PR GPU Tests (#13132)\r\n    * [CI] Revert `setuptools` CI Fix as the Failing Pipelines are Deprecated (#13149)\r\n    * Fix `ftfy` import for PRX Pipeline (#13154)\r\n    * Fix AutoModel `typing` Import Error (#13178)\r\n    * Add Helios-14B Video Generation Pipelines (#13208)\r\n    * Add LTX2 Condition Pipeline (#13058)\r\n* @kashif\r\n    * [Research] Latent Perceptual Loss (LPL) for Stable Diffusion XL (#11573)\r\n    *  Fix QwenImage txt_seq_lens handling (#12702)\r\n    * [Qwen] avoid creating attention masks when there is no padding (#12987)\r\n* @bhavya01\r\n    * Change timestep device to cpu for xla (#11501)\r\n* @linoytsaban\r\n    * [LoRA] add lora_alpha to sana README (#11780)\r\n    * Z image lora training (#13056)\r\n* @stevhliu\r\n    * [docs] Remote inference (#12372)\r\n    * [docs] add docs for qwenimagelayered (#13158)\r\n* @hameerabbasi\r\n    * Add `ChromaInpaintPipeline` (#12848)\r\n    * Remove `*pooled_*` mentions from Chroma inpaint (#13026)\r\n* @galbria\r\n    * Fibo edit pipeline (#12930)\r\n* @JaredforReal\r\n    * [GLM-Image] Add batch support for GlmImagePipeline (#13007)\r\n    * [bug fix] GLM-Image fit new `get_image_features` API (#13052)\r\n    * [Fix]Allow `prompt` and `prior_token_ids` to be provided simultaneously in `GlmImagePipeline` (#13092)\r\n* @rootonchair\r\n    * LTX2 distilled checkpoint support (#12934)\r\n* @AlanPonnachan\r\n    * Add support for Magcache  (#12744)\r\n* @CalamitousFelicitousness\r\n    * Feature/zimage inpaint pipeline (#13006)\r\n* @Ando233\r\n    * feat: implement rae autoencoder. (#13046)\r\n","publishedAt":"2026-03-05T15:05:21.000Z","fetchedAt":"2026-04-07T17:27:25.592Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.37.0","media":[],"coverageCount":0},{"id":"rel_OHA3BZv5YFYfyO3e9eTZD","version":"v0.36.0","type":"feature","title":"Diffusers 0.36.0: Pipelines galore, new caching method, training scripts, and more 🎄","summary":"The release features a number of new image and video pipelines, a new caching method, a new training script, new `kernels` - powered attention backend...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"The release features a number of new image and video pipelines, a new caching method, a new training script, new `kernels` - powered attention backends, and more. It is quite packed with a lot of new stuff, so make sure you read the release notes fully 🚀\r\n\r\n## New image pipelines\r\n\r\n- [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux2): Flux2 is the latest generation of image generation and editing model from Black Forest Labs. It’s capable of taking multiple input images as reference, making it versatile for different use cases.\r\n- [Z-Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/z_image): Z-Image is a best-of-its-kind image generation model in the 6B param regime. Thanks to @JerryWu-code in [https://github.com/huggingface/diffusers/pull/12703](https://github.com/huggingface/diffusers/pull/12703).\r\n- [QwenImage Edit Plus](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwenimage): It’s an upgrade of QwenImage Edit and is capable of taking multiple input images as references. It can act as both a generation and an editing model. Thanks to @naykun for contributing in https://github.com/huggingface/diffusers/issues/12357.\r\n- [Bria FIBO:](https://huggingface.co/docs/diffusers/main/en/api/pipelines/bria_fibo) FIBO is trained on structured JSON captions up to 1,000+ words and designed to understand and control different visual parameters such as lighting, composition, color, and camera settings, enabling precise and reproducible outputs. Thanks to @galbria for contributing this in [https://github.com/huggingface/diffusers/pull/12545](https://github.com/huggingface/diffusers/pull/12545).\r\n- [Kandinsky Image Lite](https://huggingface.co/docs/diffusers/main/en/api/pipelines/kandinsky5_image): Kandinsky 5.0 Image Lite is a lightweight image generation model (6B parameters). Thanks to @leffff for contributing this in [https://github.com/huggingface/diffusers/pull/12664](https://github.com/huggingface/diffusers/pull/12664).\r\n- [ChronoEdit](https://huggingface.co/docs/diffusers/main/en/api/pipelines/chronoedit): ChronoEdit reframes image editing as a video generation task, using input and edited images as start/end frames to leverage pretrained video models with temporal consistency. A temporal reasoning stage introduces reasoning tokens to ensure physically plausible edits and visualize the editing trajectory. Thanks to @zhangjiewu for contributing this in https://github.com/huggingface/diffusers/pull/12593.\r\n\r\n## New video pipelines\r\n\r\n- [Sana-Video](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana_video): Sana-Video is a fast and efficient video generation model, equipped to handle long video sequences, thanks to its incorporation of linear attention. Thanks to @lawrence-cj for contributing this in [https://github.com/huggingface/diffusers/pull/12634](https://github.com/huggingface/diffusers/pull/12634).\r\n- [Kandinsky 5](https://huggingface.co/docs/diffusers/main/en/api/pipelines/kandinsky5_video): Kandinsky 5.0 T2V Lite is a lightweight video generation model (2B parameters) that ranks #1 among open-source models in its class. It outperforms larger models and offers the best understanding of Russian concepts in the open-source ecosystem. Thanks to @leffff for contributing this in [https://github.com/huggingface/diffusers/pull/12478](https://github.com/huggingface/diffusers/pull/12478).\r\n- [Hunyuan 1.5](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video15): HunyuanVideo-1.5 is a lightweight yet powerful video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs.\r\n- [Wan Animate](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan#wan-animate-unified-character-animation-and-replacement-with-holistic-replication): Wan-Animate is a state-of-the-art character animation and replacement video model based on Wan2.1. Given a reference character image and driving motion video, it can either animate the character with motion from the driving video, or replace the existing character in that video with that character.\r\n\r\n## New `kernels`-powered attention backends\r\n\r\nThe `kernels` [library](https://github.com/huggingface/kernels) helps you save a lot of time by providing pre-built kernel interfaces for various environments and accelerators. This release features three new `kernels`-powered attention backends:\r\n\r\n- Flash Attention 3 (+ its `varlen` variant)\r\n- Flash Attention 2 (+ its `varlen` variant)\r\n- SAGE\r\n\r\nThis means if any of the above backend is supported by your development environment, you should be able to skip the manual process of building the corresponding kernels and just use:\r\n\r\n```python\r\n# Make sure you have `kernels` installed: `pip install kernels`.\r\n# You can choose `flash_hub` or `sage_hub`, too.\r\npipe.transformer.set_attention_backend(\"_flash_3_hub\")\r\n```\r\n\r\nFor more details, check out the [documentation](https://huggingface.co/docs/diffusers/main/en/optimization/attention_backends). \r\n\r\n## TaylorSeer cache\r\n\r\nTaylorSeer is now supported in Diffusers, delivering upto 3x speedups with negligible-to-none quality compromise. Thanks to @toilaluan for contributing this in [https://github.com/huggingface/diffusers/pull/12648](https://github.com/huggingface/diffusers/pull/12648). Check out the documentation [here](https://huggingface.co/docs/diffusers/main/en/optimization/cache#taylorseer-cache).\r\n\r\n## New training script\r\n\r\nOur Flux.2 integration features a LoRA fine-tuning script that you can check out [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux2.md). We provide a number of optimizations to help make it run on consumer GPUs.\r\n\r\n## Misc\r\n\r\n- Reusing `AttentionMixin`: Making certain compatible models subclass from the `AttentionMixin` class helped us get rid of 2K LoC. Going forward, users can expect more such refactorings that will help make the library leaner and simpler. Check out https://github.com/huggingface/diffusers/pull/12463 for more details.\r\n- Diffusers backend in SGLang: https://github.com/sgl-project/sglang/pull/14112.\r\n- We started the [Diffusers MVP program](https://github.com/huggingface/diffusers/issues/12635) to work with talented community members who will help us improve the library across multiple fronts. Check out the link for more information.\r\n\r\n## All commits\r\n\r\n* remove unneeded checkpoint imports.  by @sayakpaul in #12488\r\n* [tests] fix clapconfig for text backbone in audioldm2  by @sayakpaul in #12490\r\n* ltx0.9.8 (without IC lora,  autoregressive sampling)  by @yiyixuxu in #12493\r\n* [docs] Attention checks  by @stevhliu in #12486\r\n* [CI] Check links  by @stevhliu in #12491\r\n* [ci] xfail more incorrect transformer imports.  by @sayakpaul in #12455\r\n* [tests] introduce `VAETesterMixin` to consolidate tests for slicing and tiling  by @sayakpaul in #12374\r\n* docs: cleanup of runway model  by @EazyAl in #12503\r\n* Kandinsky 5 is finally in Diffusers!  by @leffff in #12478\r\n* Remove Qwen Image Redundant RoPE Cache  by @dg845 in #12452\r\n* Raise warning instead of error when imports are missing for custom code   by @DN6 in #12513\r\n* Fix: Use incorrect temporary variable key when replacing adapter name…  by @FeiXie8 in #12502\r\n* [docs] Organize toctree by modality  by @stevhliu in #12514\r\n* styling issues.  by @sayakpaul in #12522\r\n* Add Photon model and pipeline support  by @DavidBert in #12456\r\n* purge HF_HUB_ENABLE_HF_TRANSFER; promote Xet  by @Vaibhavs10 in #12497\r\n* Prx  by @DavidBert in #12525\r\n* [core] `AutoencoderMixin` to abstract common methods  by @sayakpaul in #12473\r\n* Kandinsky5 No cfg fix  by @asomoza in #12527\r\n* Fix: Add _skip_keys for AutoencoderKLWan  by @yiyixuxu in #12523\r\n* [CI] xfail the test_wuerstchen_prior test  by @sayakpaul in #12530\r\n* [tests] Test attention backends  by @sayakpaul in #12388\r\n* fix CI bug for kandinsky3_img2img case  by @kaixuanliu in #12474\r\n* Fix MPS compatibility in get_1d_sincos_pos_embed_from_grid #12432  by @Aishwarya0811 in #12449\r\n* Handle deprecated transformer classes  by @DN6 in #12517\r\n* fix constants.py to user `upper()`  by @sayakpaul in #12479\r\n* HunyuanImage21  by @yiyixuxu in #12333\r\n* Loose the criteria tolerance appropriately for Intel XPU devices  by @kaixuanliu in #12460\r\n* Deprecate Stable Cascade  by @DN6 in #12537\r\n* [chore] Move guiders experimental warning  by @sayakpaul in #12543\r\n* Fix Chroma attention padding order and update docs to use `lodestones/Chroma1-HD`  by @josephrocca in #12508\r\n* Add AITER attention backend  by @lauri9 in #12549\r\n* Fix small inconsistency in output dimension of \"_get_t5_prompt_embeds\" function in sd3 pipeline  by @alirezafarashah in #12531\r\n* Kandinsky 5 10 sec (NABLA suport)  by @leffff in #12520\r\n* Improve pos embed for Flux.1 inference on Ascend NPU  by @gameofdimension in #12534\r\n* support latest few-step wan LoRA.  by @sayakpaul in #12541\r\n* [Pipelines] Enable Wan VACE to run since single transformer  by @DN6 in #12428\r\n* fix crash if tiling mode is enabled  by @sywangyi in #12521\r\n* Fix typos in kandinsky5 docs  by @Meatfucker in #12552\r\n* [ci] don't run sana layerwise casting tests in CI.  by @sayakpaul in #12551\r\n* Bria fibo  by @galbria in #12545\r\n* Avoiding graph break by changing the way we infer dtype in vae.decoder  by @ppadjinTT in #12512\r\n* [Modular] Fix for custom block kwargs  by @DN6 in #12561\r\n* [Modular] Allow custom blocks to be saved to `local_dir`  by @DN6 in #12381\r\n* Fix Stable Diffusion 3.x pooled prompt embedding with multiple images  by @friedrich in #12306\r\n* Fix custom code loading in Automodel  by @DN6 in #12571\r\n* [modular] better warn message  by @yiyixuxu in #12573\r\n* [tests] add tests for flux modular (t2i, i2i, kontext)  by @sayakpaul in #12566\r\n* [modular]pass hub_kwargs to load_config  by @yiyixuxu in #12577\r\n* ulysses enabling in native attention path  by @sywangyi in #12563\r\n* Kandinsky 5.0 Docs fixes  by @leffff in #12582\r\n* [docs] sort doc  by @sayakpaul in #12586\r\n* [LoRA] add support for more Qwen LoRAs  by @linoytsaban in #12581\r\n* [Modular] Allow ModularPipeline to load from revisions  by @DN6 in #12592\r\n* Add optional precision-preserving preprocessing for examples/unconditional_image_generation/train_unconditional.py  by @turian in #12596\r\n* [SANA-Video] Adding 5s pre-trained 480p SANA-Video inference  by @lawrence-cj in #12584\r\n* Fix overflow and dtype handling in rgblike_to_depthmap (NumPy + PyTorch)  by @MohammadSadeghSalehi in #12546\r\n* [Modular] Some clean up for Modular tests  by @DN6 in #12579\r\n* feat: enable attention dispatch for huanyuan video  by @DefTruth in #12591\r\n* fix the crash in Wan-AI/Wan2.2-TI2V-5B-Diffusers if CP is enabled  by @sywangyi in #12562\r\n* [CI] Push test fix  by @DN6 in #12617\r\n* add ChronoEdit  by @zhangjiewu in #12593\r\n* [modular] wan!  by @yiyixuxu in #12611\r\n* [CI] Fix typo in uv install  by @DN6 in #12618\r\n* fix: correct import path for load_model_dict_into_meta in conversion scripts  by @yashwantbezawada in #12616\r\n* Fix Context Parallel validation checks  by @DN6 in #12446\r\n* [Modular] Clean up docs  by @DN6 in #12604\r\n* Fix: update type hints for Tuple parameters across multiple files to support variable-length tuples  by @cesaryuan in #12544\r\n* [CI] Remove unittest dependency from `testing_utils.py`  by @DN6 in #12621\r\n* Fix rotary positional embedding dimension mismatch in Wan and SkyReels V2 transformers  by @charchit7 in #12594\r\n* fix copies  by @yiyixuxu in #12637\r\n* Add MLU Support.  by @a120092009 in #12629\r\n* fix dispatch_attention_fn check  by @yiyixuxu in #12636\r\n* [modular] add tests for qwen modular  by @sayakpaul in #12585\r\n* ArXiv -> HF Papers  by @qgallouedec in #12583\r\n* [docs] Update install instructions  by @stevhliu in #12626\r\n* [modular] add a check   by @yiyixuxu in #12628\r\n* Improve docstrings and type hints in scheduling_amused.py  by @delmalih in #12623\r\n* [WIP]Add Wan2.2 Animate Pipeline (Continuation of #12442 by tolgacangoz)  by @dg845 in #12526\r\n* adjust unit tests for `test_save_load_float16`  by @kaixuanliu in #12500\r\n* skip autoencoderdl layerwise casting memory  by @sayakpaul in #12647\r\n* [utils] Update check_doc_toc  by @stevhliu in #12642\r\n* [docs] AutoModel  by @stevhliu in #12644\r\n* Improve docstrings and type hints in scheduling_ddim.py  by @delmalih in #12622\r\n* Improve docstrings and type hints in scheduling_ddpm.py  by @delmalih in #12651\r\n* [Modular] Add Custom Blocks guide to doc  by @DN6 in #12339\r\n* Improve docstrings and type hints in scheduling_euler_discrete.py  by @delmalih in #12654\r\n* Update Wan Animate Docs  by @dg845 in #12658\r\n* Rope in float32 for mps or npu compatibility  by @DavidBert in #12665\r\n* [PRX pipeline]: add 1024 resolution ratio bins  by @DavidBert in #12670\r\n* SANA-Video Image to Video pipeline `SanaImageToVideoPipeline` support  by @lawrence-cj in #12634\r\n* [CI] Make CI logs less verbose   by @DN6 in #12674\r\n* Revert `AutoencoderKLWan`'s `dim_mult` default value back to list  by @dg845 in #12640\r\n* [CI] Temporarily pin transformers  by @DN6 in #12677\r\n* [core] Refactor hub attn kernels  by @sayakpaul in #12475\r\n* [CI] Fix indentation issue in workflow files  by @DN6 in #12685\r\n* [CI] Fix failing Pipeline CPU tests  by @DN6 in #12681\r\n* Improve docstrings and type hints in scheduling_pndm.py  by @delmalih in #12676\r\n* Community Pipeline: FluxFillControlNetInpaintPipeline for FLUX Fill-Based Inpainting with ControlNet  by @pratim4dasude in #12649\r\n* Improve docstrings and type hints in scheduling_lms_discrete.py  by @delmalih in #12678\r\n* Add FluxLoraLoaderMixin to Fibo pipeline  by @SwayStar123 in #12688\r\n* bugfix: fix chrono-edit context parallel  by @DefTruth in #12660\r\n* [core] support sage attention + FA2 through `kernels`  by @sayakpaul in #12439\r\n* [i8n-pt] Fix grammar and expand Portuguese documentation  by @cdutr in #12598\r\n* Fix variable naming typos in community FluxControlNetFillInpaintPipeline  by @sqhuang in #12701\r\n* fix typo in docs  by @lawrence-cj in #12675\r\n* Add Support for Z-Image Series  by @JerryWu-code in #12703\r\n* let's go Flux2 🚀  by @sayakpaul in #12711\r\n* Update script names in README for Flux2 training  by @anvilarth in #12713\r\n* [lora]: Fix Flux2 LoRA NaN test  by @sayakpaul in #12714\r\n* [docs] Correct flux2 links  by @sayakpaul in #12716\r\n* [docs] put autopipeline after overview and hunyuanimage in images  by @sayakpaul in #12548\r\n* Improve docstrings and type hints in scheduling_dpmsolver_multistep.py  by @delmalih in #12710\r\n* Support unittest for Z-image ⚡️  by @JerryWu-code in #12715\r\n* [chore] remove torch.save from remnant code.  by @sayakpaul in #12717\r\n* Enable regional compilation on z-image transformer model  by @sayakpaul in #12736\r\n* Fix examples not loading LoRA adapter weights from checkpoint  by @SurAyush in #12690\r\n* [Modular] Add single file support to Modular  by @DN6 in #12383\r\n* fix type-check for z-image transformer  by @DefTruth in #12739\r\n* Hunyuanvideo15  by @yiyixuxu in #12696\r\n* [Docs] Update Imagen Video paper link in schedulers  by @delmalih in #12724\r\n* Improve docstrings and type hints in scheduling_heun_discrete.py  by @delmalih in #12726\r\n* Improve docstrings and type hints in scheduling_euler_ancestral_discrete.py  by @delmalih in #12766\r\n* fix FLUX.2 context parallel  by @DefTruth in #12737\r\n* Rename BriaPipeline to BriaFiboPipeline in documentation  by @galbria in #12758\r\n* Update bria_fibo.md with minor fixes  by @sayakpaul in #12731\r\n* [feat]: implement \"local\" caption upsampling for Flux.2  by @sayakpaul in #12718\r\n* Add ZImage LoRA support and integrate into ZImagePipeline  by @CalamitousFelicitousness in #12750\r\n* Add support for Ovis-Image  by @DoctorKey in #12740\r\n* Fix TPU (torch_xla) compatibility Error about tensor repeat func along with empty dim.  by @JerryWu-code in #12770\r\n* Fixes #12673. `record_stream` in group offloading is not working properly  by @KimbingNg in #12721\r\n* [core] start varlen variants for attn backend kernels.  by @sayakpaul in #12765\r\n* [core] reuse `AttentionMixin` for compatible classes  by @sayakpaul in #12463\r\n* Deprecate `upcast_vae` in SDXL based pipelines  by @DN6 in #12619\r\n* Kandinsky 5.0 Video Pro and Image Lite  by @leffff in #12664\r\n* Fix: leaf_level offloading breaks after delete_adapters  by @adi776borate in #12639\r\n* [tests] fix hunuyanvideo 1.5 offloading tests.  by @sayakpaul in #12782\r\n* [Z-Image] various small changes, Z-Image transformer tests, etc.  by @sayakpaul in #12741\r\n* Z-Image-Turbo `from_single_file`  by @hlky in #12756\r\n* Update attention_backends.md to format kernels  by @sayakpaul in #12757\r\n* Improve docstrings and type hints in scheduling_unipc_multistep.py  by @delmalih in #12767\r\n* fix spatial compression ratio error for AutoEncoderKLWan doing tiled encode  by @jerry2102 in #12753\r\n* [lora] support more ZImage LoRAs  by @sayakpaul in #12790\r\n* PRX Set downscale_freq_shift to 0 for consistency with internal implementation  by @DavidBert in #12791\r\n* Fix broken group offloading with block_level for models with standalone layers  by @rycerzes in #12692\r\n* [Docs] Add Z-Image docs  by @asomoza in #12775\r\n* move kandisnky docs. by @sayakpaul (direct commit on v0.36.0-release)\r\n* [docs] minor fixes to kandinsky docs  by @sayakpaul in #12797\r\n* Improve docstrings and type hints in scheduling_deis_multistep.py  by @delmalih in #12796\r\n* [Feat] TaylorSeer Cache  by @toilaluan in #12648\r\n* Update the TensorRT-ModelOPT to Nvidia-ModelOPT  by @jingyu-ml in #12793\r\n* add post init for safty checker  by @jiqing-feng in #12794\r\n* [HunyuanVideo1.5] support step-distilled  by @yiyixuxu in #12802\r\n* Add ZImageImg2ImgPipeline  by @CalamitousFelicitousness in #12751\r\n* Release: v0.36.0-release by @sayakpaul (direct commit on v0.36.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @yiyixuxu\r\n    * ltx0.9.8 (without IC lora,  autoregressive sampling) (#12493)\r\n    * Fix: Add _skip_keys for AutoencoderKLWan (#12523)\r\n    * HunyuanImage21 (#12333)\r\n    * [modular] better warn message (#12573)\r\n    * [modular]pass hub_kwargs to load_config (#12577)\r\n    * [modular] wan! (#12611)\r\n    * fix copies (#12637)\r\n    * fix dispatch_attention_fn check (#12636)\r\n    * [modular] add a check  (#12628)\r\n    * Hunyuanvideo15 (#12696)\r\n    * [HunyuanVideo1.5] support step-distilled (#12802)\r\n* @leffff\r\n    * Kandinsky 5 is finally in Diffusers! (#12478)\r\n    * Kandinsky 5 10 sec (NABLA suport) (#12520)\r\n    * Kandinsky 5.0 Docs fixes (#12582)\r\n    * Kandinsky 5.0 Video Pro and Image Lite (#12664)\r\n* @dg845\r\n    * Remove Qwen Image Redundant RoPE Cache (#12452)\r\n    * [WIP]Add Wan2.2 Animate Pipeline (Continuation of #12442 by tolgacangoz) (#12526)\r\n    * Update Wan Animate Docs (#12658)\r\n    * Revert `AutoencoderKLWan`'s `dim_mult` default value back to list (#12640)\r\n* @DN6\r\n    * Raise warning instead of error when imports are missing for custom code  (#12513)\r\n    * Handle deprecated transformer classes (#12517)\r\n    * Deprecate Stable Cascade (#12537)\r\n    * [Pipelines] Enable Wan VACE to run since single transformer (#12428)\r\n    * [Modular] Fix for custom block kwargs (#12561)\r\n    * [Modular] Allow custom blocks to be saved to `local_dir` (#12381)\r\n    * Fix custom code loading in Automodel (#12571)\r\n    * [Modular] Allow ModularPipeline to load from revisions (#12592)\r\n    * [Modular] Some clean up for Modular tests (#12579)\r\n    * [CI] Push test fix (#12617)\r\n    * [CI] Fix typo in uv install (#12618)\r\n    * Fix Context Parallel validation checks (#12446)\r\n    * [Modular] Clean up docs (#12604)\r\n    * [CI] Remove unittest dependency from `testing_utils.py` (#12621)\r\n    * [Modular] Add Custom Blocks guide to doc (#12339)\r\n    * [CI] Make CI logs less verbose  (#12674)\r\n    * [CI] Temporarily pin transformers (#12677)\r\n    * [CI] Fix indentation issue in workflow files (#12685)\r\n    * [CI] Fix failing Pipeline CPU tests (#12681)\r\n    * [Modular] Add single file support to Modular (#12383)\r\n    * Deprecate `upcast_vae` in SDXL based pipelines (#12619)\r\n* @DavidBert\r\n    * Add Photon model and pipeline support (#12456)\r\n    * Prx (#12525)\r\n    * Rope in float32 for mps or npu compatibility (#12665)\r\n    * [PRX pipeline]: add 1024 resolution ratio bins (#12670)\r\n    * PRX Set downscale_freq_shift to 0 for consistency with internal implementation (#12791)\r\n* @galbria\r\n    * Bria fibo (#12545)\r\n    * Rename BriaPipeline to BriaFiboPipeline in documentation (#12758)\r\n* @lawrence-cj\r\n    * [SANA-Video] Adding 5s pre-trained 480p SANA-Video inference (#12584)\r\n    * SANA-Video Image to Video pipeline `SanaImageToVideoPipeline` support (#12634)\r\n    * fix typo in docs (#12675)\r\n* @zhangjiewu\r\n    * add ChronoEdit (#12593)\r\n* @delmalih\r\n    * Improve docstrings and type hints in scheduling_amused.py (#12623)\r\n    * Improve docstrings and type hints in scheduling_ddim.py (#12622)\r\n    * Improve docstrings and type hints in scheduling_ddpm.py (#12651)\r\n    * Improve docstrings and type hints in scheduling_euler_discrete.py (#12654)\r\n    * Improve docstrings and type hints in scheduling_pndm.py (#12676)\r\n    * Improve docstrings and type hints in scheduling_lms_discrete.py (#12678)\r\n    * Improve docstrings and type hints in scheduling_dpmsolver_multistep.py (#12710)\r\n    * [Docs] Update Imagen Video paper link in schedulers (#12724)\r\n    * Improve docstrings and type hints in scheduling_heun_discrete.py (#12726)\r\n    * Improve docstrings and type hints in scheduling_euler_ancestral_discrete.py (#12766)\r\n    * Improve docstrings and type hints in scheduling_unipc_multistep.py (#12767)\r\n    * Improve docstrings and type hints in scheduling_deis_multistep.py (#12796)\r\n* @pratim4dasude\r\n    * Community Pipeline: FluxFillControlNetInpaintPipeline for FLUX Fill-Based Inpainting with ControlNet (#12649)\r\n* @JerryWu-code\r\n    * Add Support for Z-Image Series (#12703)\r\n    * Support unittest for Z-image ⚡️ (#12715)\r\n    * Fix TPU (torch_xla) compatibility Error about tensor repeat func along with empty dim. (#12770)\r\n* @CalamitousFelicitousness\r\n    * Add ZImage LoRA support and integrate into ZImagePipeline (#12750)\r\n    * Add ZImageImg2ImgPipeline (#12751)\r\n* @DoctorKey\r\n    * Add support for Ovis-Image (#12740)\r\n","publishedAt":"2025-12-08T10:17:31.000Z","fetchedAt":"2026-04-07T17:27:25.592Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.36.0","media":[],"coverageCount":0},{"id":"rel_WE76FCxKwvrtWfsbSEQ67","version":"v0.35.2","type":"feature","title":"🐞 fixes for `transformers` models, imports, ","summary":"## All commits\r\n\r\n* Release: v0.35.1-patch by @sayakpaul (direct commit on v0.35.2-patch)\r\n* handle offload_state_dict when initing transformers model...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## All commits\r\n\r\n* Release: v0.35.1-patch by @sayakpaul (direct commit on v0.35.2-patch)\r\n* handle offload_state_dict when initing transformers models  by @sayakpaul in #12438\r\n* [CI] Fix TRANSFORMERS_FLAX_WEIGHTS_NAME import issue  by @DN6 in #12354\r\n* Fix PyTorch 2.3.1 compatibility: add version guard for torch.library.…  by @Aishwarya0811 in #12206\r\n* fix scale_shift_factor being on cpu for wan and ltx  by @vladmandic in #12347\r\n* Release: v0.35.2-patch by @sayakpaul (direct commit on v0.35.2-patch)","publishedAt":"2025-10-15T04:14:33.000Z","fetchedAt":"2026-04-07T17:27:25.592Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.35.2","media":[],"coverageCount":0},{"id":"rel_IULuOPBxAM6SXCJQjg8Of","version":"v0.35.1","type":"feature","title":"v0.35.1 for improvements in Qwen-Image Edit","summary":"Thanks to @naykun for the following PRs that improve Qwen-Image Edit:\r\n\r\n* https://github.com/huggingface/diffusers/pull/12188\r\n* https://github.com/h...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"Thanks to @naykun for the following PRs that improve Qwen-Image Edit:\r\n\r\n* https://github.com/huggingface/diffusers/pull/12188\r\n* https://github.com/huggingface/diffusers/pull/12190","publishedAt":"2025-08-20T04:17:30.000Z","fetchedAt":"2026-04-07T17:27:25.592Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.35.1","media":[],"coverageCount":0},{"id":"rel_9J6dD6bkZBvsiBIS_73l6","version":"v0.35.0","type":"feature","title":"Diffusers 0.35.0: Qwen Image pipelines, Flux Kontext, Wan 2.2, and more","summary":"This release comes packed with new image generation and editing pipelines, a new video pipeline, new training scripts, quality-of-life improvements, a...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"This release comes packed with new image generation and editing pipelines, a new video pipeline, new training scripts, quality-of-life improvements, and much more. Read the rest of the release notes fully to not miss out on the fun stuff.\r\n\r\n## New pipelines 🧨\r\n\r\nWe welcomed new pipelines in this release:\r\n\r\n- Wan 2.2\r\n- Flux-Kontext\r\n- Qwen-Image\r\n- Qwen-Image-Edit\r\n\r\n### Wan 2.2 📹\r\n\r\nThis update to Wan provides significant improvements in video fidelity, prompt adherence, and style. Please check out the [official doc](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan) to learn more.\r\n\r\n### Flux-Kontext 🎇\r\n\r\nFlux-Kontext is a 12-billion-parameter rectified flow transformer capable of editing images based on text instructions. Please check out the [official doc](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#kontext) to learn more about it.\r\n\r\n### Qwen-Image 🌅\r\n\r\nAfter a successful run of delivering language models and vision-language models, the Qwen team is back with an image generation model, which is Apache-2.0 licensed! It achieves significant advances in complex text rendering and precise image editing. To learn more about this powerful model, refer to our [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwenimage).\r\n\r\nThanks to @naykun for contributing both Qwen-Image and Qwen-Image-Edit via [this PR](https://github.com/huggingface/diffusers//issues/12055) and [this PR](https://github.com/huggingface/diffusers/pull/12164/).\r\n\r\n## New training scripts 🎛️\r\n\r\nMake these newly added models your own with our training scripts:\r\n\r\n- [Kontext trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md#training-kontext)\r\n- [Qwen-Image trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md#training-kontext)\r\n\r\n## Single-file modeling implementations\r\n\r\nFollowing the 🤗 Transformers’ [philosophy](https://huggingface.co/blog/transformers-design-philosophy) of single-file modeling implementations, we have started implementing modeling code in single and self-contained files. The Flux Transformer [code](https://github.com/huggingface/diffusers/blob/baa9b582f348e52aa2fc245e366611f454e1082b/src/diffusers/models/transformers/transformer_flux.py) is one example of this.\r\n\r\n## Attention refactor\r\n\r\nWe have massively refactored how we do attention in the models. This allows us to provide support for different attention backends (such as PyTorch native `scaled_dot_product_attention`, Flash Attention 3, SAGE attention, etc.) in the library seamlessly. \r\n\r\nHaving attention supported this way also allows us to integrate different parallelization mechanisms, which we’re actively working on. Follow [this PR](https://github.com/huggingface/diffusers/pull/11941) if you’re interested.\r\n\r\nUsers shouldn’t be affected at all by these changes. Please open an issue if you face any problems.\r\n\r\n## Regional compilation\r\n\r\nRegional compilation trims cold-start latency by only compiling the small and frequently-repeated block(s) of a model - typically a transformer layer - and enables reusing compiled artifacts for every subsequent occurrence. For many diffusion architectures, this delivers the same runtime speedups as full-graph compilation and reduces compile time by 8–10x. Refer to [this doc](https://huggingface.co/docs/diffusers/main/en/optimization/fp16#regional-compilation) to learn more.\r\n\r\nThanks to @anijain2305 for contributing this feature in [this PR](https://github.com/huggingface/diffusers/pull/11705).\r\n\r\nWe have also authored a number of posts that center around the use of `torch.compile`. You can check them out at the links below:\r\n\r\n- [Presenting Flux Fast: Making Flux go brrr on H100s](https://pytorch.org/blog/presenting-flux-fast-making-flux-go-brrr-on-h100s/)\r\n- [torch.compile and Diffusers: A Hands-On Guide to Peak Performance](https://pytorch.org/blog/torch-compile-and-diffusers-a-hands-on-guide-to-peak-performance/)\r\n- [Fast LoRA inference for Flux with Diffusers and PEFT](https://huggingface.co/blog/lora-fast)\r\n\r\n## Faster pipeline loading ⚡️\r\n\r\nUsers can now load pipelines directly on an accelerator device leading to significantly faster load times. This particularly becomes evident when loading large pipelines like Wan and Qwen-Image.\r\n\r\n```diff\r\nfrom diffusers import DiffusionPipeline\r\nimport torch \r\n\r\nckpt_id = \"Qwen/Qwen-Image\"\r\npipe = DiffusionPipeline.from_pretrained(\r\n-    ckpt_id, torch_dtype=torch.bfloat16\r\n- ).to(\"cuda\")\r\n+    ckpt_id, torch_dtype=torch.bfloat16, device_map=\"cuda\"\r\n+ )\t\t\t\t\r\n```\r\n\r\nYou can speed up loading even more by enabling parallelized loading of state dict shards. This is particularly helpful when you’re working with large models like Wan and Qwen-Image, where the model state dicts are typically sharded across multiple files. \r\n\r\n```python\r\nimport os\r\nos.environ[\"HF_ENABLE_PARALLEL_LOADING\"] = \"yes\"\r\n\r\n# rest of the loading code\r\n....\r\n```\r\n\r\n## Better GGUF integration\r\n\r\n@Isotr0py contributed support for native GGUF CUDA kernels in [this PR](https://github.com/huggingface/diffusers/pull/11869). This should provide an approximately 10% improvement in inference speed. \r\n\r\nWe have also worked on a tool for converting regular checkpoints to GGUF, letting the community easily share their GGUF checkpoints. Learn more [here](https://huggingface.co/spaces/diffusers-internal-dev/diffusers-to-gguf/).\r\n\r\nWe now support loading of Diffusers format GGUF checkpoints. \r\n\r\nYou can learn more about all of this in our [GGUF official docs](https://huggingface.co/docs/diffusers/main/en/quantization/gguf).\r\n\r\n## Modular Diffusers (Experimental)\r\n\r\nModular Diffusers is a system for building diffusion pipelines pipelines with *individual* *pipeline blocks*. It is highly customisable, with blocks that can be mixed and matched to adapt to or create a pipeline for a specific workflow or multiple workflows.  \r\n\r\nThe API is currently in active development and is being released as an experimental feature. Learn more in our [docs](https://huggingface.co/docs/diffusers/main/en/modular_diffusers/overview).\r\n\r\n## All commits\r\n\r\n* [tests] skip instead of returning.  by @sayakpaul in #11793\r\n* adjust to get CI test cases passed on XPU  by @kaixuanliu in #11759\r\n* fix deprecation in lora after 0.34.0 release  by @sayakpaul in #11802\r\n* [chore] post release v0.34.0  by @sayakpaul in #11800\r\n* Follow up for Group Offload to Disk   by @DN6 in #11760\r\n* [rfc][compile] compile method for DiffusionPipeline  by @anijain2305 in #11705\r\n* [tests] add a test on torch compile for varied resolutions  by @sayakpaul in #11776\r\n* adjust tolerance criteria for `test_float16_inference` in unit test  by @kaixuanliu in #11809\r\n* Flux Kontext  by @a-r-r-o-w in #11812\r\n* Kontext training  by @sayakpaul in #11813\r\n* Kontext fixes  by @a-r-r-o-w in #11815\r\n* remove syncs before denoising in Kontext  by @sayakpaul in #11818\r\n* [CI] disable onnx, mps, flax from the CI  by @sayakpaul in #11803\r\n* TorchAO compile + offloading tests  by @a-r-r-o-w in #11697\r\n* Support dynamically loading/unloading loras with group offloading  by @a-r-r-o-w in #11804\r\n* [lora] fix: lora unloading behvaiour  by @sayakpaul in #11822\r\n* [lora]feat: use exclude modules to loraconfig.  by @sayakpaul in #11806\r\n* ENH: Improve speed of function expanding LoRA scales  by @BenjaminBossan in #11834\r\n* Remove print statement in SCM Scheduler  by @a-r-r-o-w in #11836\r\n* [tests] add test for hotswapping + compilation on resolution changes  by @sayakpaul in #11825\r\n* reset deterministic in tearDownClass  by @jiqing-feng in #11785\r\n* [tests] Fix failing float16 cuda tests  by @a-r-r-o-w in #11835\r\n* [single file] Cosmos  by @a-r-r-o-w in #11801\r\n* [docs] fix single_file example.  by @sayakpaul in #11847\r\n* Use real-valued instead of complex tensors in Wan2.1 RoPE  by @mjkvaak-amd in #11649\r\n* [docs] Batch generation  by @stevhliu in #11841\r\n* [docs] Deprecated pipelines  by @stevhliu in #11838\r\n* fix norm not training in train_control_lora_flux.py  by @Luo-Yihang in #11832\r\n* [From Single File] support `from_single_file` method for `WanVACE3DTransformer`  by @J4BEZ in #11807\r\n* [lora] tests for `exclude_modules` with Wan VACE  by @sayakpaul in #11843\r\n* update: FluxKontextInpaintPipeline support  by @vuongminh1907 in #11820\r\n* [Flux Kontext] Support Fal Kontext LoRA  by @linoytsaban in #11823\r\n* [docs] Add a note of `_keep_in_fp32_modules`  by @a-r-r-o-w in #11851\r\n* [benchmarks] overhaul benchmarks  by @sayakpaul in #11565\r\n* FIX set_lora_device when target layers differ  by @BenjaminBossan in #11844\r\n* Fix Wan AccVideo/CausVid fuse_lora  by @a-r-r-o-w in #11856\r\n* [chore] deprecate blip controlnet pipeline.  by @sayakpaul in #11877\r\n* [docs] fix references in flux pipelines.  by @sayakpaul in #11857\r\n* [tests] remove tests for deprecated pipelines.  by @sayakpaul in #11879\r\n* [docs] LoRA metadata  by @stevhliu in #11848\r\n* [training ] add Kontext i2i training  by @sayakpaul in #11858\r\n* [CI] Fix big GPU test marker  by @DN6 in #11786\r\n* First Block Cache  by @a-r-r-o-w in #11180\r\n* [tests] annotate compilation test classes with bnb  by @sayakpaul in #11715\r\n* Update chroma.md  by @shm4r7 in #11891\r\n* [CI] Speed up GPU PR Tests  by @DN6 in #11887\r\n* Pin k-diffusion for CI  by @sayakpaul in #11894\r\n* [Docker] update doc builder dockerfile to include quant libs.  by @sayakpaul in #11728\r\n* [tests] Remove more deprecated tests  by @sayakpaul in #11895\r\n* [tests] mark the wanvace lora tester flaky  by @sayakpaul in #11883\r\n* [tests] add compile + offload tests for GGUF.  by @sayakpaul in #11740\r\n* feat: add multiple input image support in Flux Kontext  by @Net-Mist in #11880\r\n* Fix unique memory address when doing group-offloading with disk  by @sayakpaul in #11767\r\n* [SD3] CFG Cutoff fix and official callback  by @asomoza in #11890\r\n* The Modular Diffusers  by @yiyixuxu in #9672\r\n* [quant] QoL improvements for pipeline-level quant config  by @sayakpaul in #11876\r\n* Bump torch from 2.4.1 to 2.7.0 in /examples/server  by @dependabot[bot] in #11429\r\n* [LoRA] fix: disabling hooks when loading loras.  by @sayakpaul in #11896\r\n* [utils] account for MPS when available in get_device().  by @sayakpaul in #11905\r\n* [ControlnetUnion] Multiple Fixes  by @asomoza in #11888\r\n* Avoid creating tensor in CosmosAttnProcessor2_0  by @chenxiao111222 in #11761) \r\n* [tests] Unify compilation + offloading tests in quantization  by @sayakpaul in #11910\r\n* Speedup model loading by 4-5x ⚡  by @a-r-r-o-w in #11904\r\n* [docs] torch.compile blog post  by @stevhliu in #11837\r\n* Flux: pass joint_attention_kwargs when using gradient_checkpointing  by @piercus in #11814\r\n* Fix: Align VAE processing in ControlNet SD3 training with inference  by @Henry-Bi in #11909\r\n* Bump aiohttp from 3.10.10 to 3.12.14 in /examples/server  by @dependabot[bot] in #11924\r\n* [tests] Improve Flux tests  by @a-r-r-o-w in #11919\r\n* Remove device synchronization when loading weights  by @a-r-r-o-w in #11927\r\n* Remove forced float64 from onnx stable diffusion pipelines  by @lostdisc in #11054\r\n* Fixed bug: Uncontrolled recursive calls that caused an infinite loop when loading certain pipelines containing Transformer2DModel  by @lengmo1996 in #11923\r\n* [ControlnetUnion] Propagate #11888 to img2img  by @asomoza in #11929\r\n* enable flux pipeline compatible with unipc and dpm-solver  by @gameofdimension in #11908\r\n* [training] add an offload utility that can be used as a context manager.  by @sayakpaul in #11775\r\n* Add SkyReels V2: Infinite-Length Film Generative Model  by @tolgacangoz in #11518\r\n* [refactor] Flux/Chroma single file implementation + Attention Dispatcher  by @a-r-r-o-w in #11916\r\n* [docs] clarify the mapping between `Transformer2DModel` and finegrained variants.  by @sayakpaul in #11947\r\n* [Modular] Updates for Custom Pipeline Blocks  by @DN6 in #11940\r\n* [docs] Update toctree  by @stevhliu in #11936\r\n* [docs] include bp link.  by @sayakpaul in #11952\r\n* Fix kontext finetune issue when batch size >1   by @mymusise in #11921\r\n* [tests] Add test slices for Hunyuan Video  by @a-r-r-o-w in #11954\r\n* [tests] Add test slices for Cosmos  by @a-r-r-o-w in #11955\r\n* [tests] Add fast test slices for HiDream-Image  by @a-r-r-o-w in #11953\r\n* [Modular] update the collection behavior  by @yiyixuxu in #11963\r\n* fix \"Expected all tensors to be on the same device, but found at least two devices\" error  by @yao-matrix in #11690\r\n* Remove logger warnings for attention backends and hard error during runtime instead  by @a-r-r-o-w in #11967\r\n* [Examples] Uniform notations in train_flux_lora  by @tomguluson92 in #10011\r\n* fix style   by @yiyixuxu in #11975\r\n* [tests] Add test slices for Wan  by @a-r-r-o-w in #11920\r\n* [docs] update `guidance_scale` docstring for guidance_distilled models.  by @sayakpaul in #11935\r\n* [tests] enforce torch version in the compilation tests.  by @sayakpaul in #11979\r\n* [modular diffusers] Wan  by @a-r-r-o-w in #11913\r\n* [compile] logger statements create unnecessary guards during dynamo tracing  by @a-r-r-o-w in #11987\r\n* enable quantcompile test on xpu  by @yao-matrix in #11988\r\n* [WIP] Wan2.2  by @yiyixuxu in #12004\r\n* [refactor] some shared parts between hooks + docs  by @a-r-r-o-w in #11968\r\n* [refactor] Wan single file implementation  by @a-r-r-o-w in #11918\r\n* Fix huggingface-hub failing tests  by @asomoza in #11994\r\n* feat: add flux kontext  by @jlonge4 in #11985\r\n* [modular] add Modular flux for text-to-image  by @sayakpaul in #11995\r\n* [docs] include lora fast post.  by @sayakpaul in #11993\r\n* [docs] quant_kwargs  by @stevhliu in #11712\r\n* [docs] Fix link  by @stevhliu in #12018\r\n* [wan2.2] add 5b i2v  by @yiyixuxu in #12006\r\n* wan2.2 i2v FirstBlockCache fix  by @okaris in #12013\r\n* [core] support attention backends for LTX  by @sayakpaul in #12021\r\n* [docs] Update index  by @stevhliu in #12020\r\n* [Fix] huggingface-cli to hf missed files  by @asomoza in #12008\r\n* [training-scripts] Make pytorch examples UV-compatible  by @sayakpaul in #12000\r\n* [wan2.2] fix vae patches  by @yiyixuxu in #12041\r\n* Allow SD pipeline to use newer schedulers, eg: FlowMatch  by @ppbrown in #12015\r\n* [LoRA] support lightx2v lora in wan  by @sayakpaul in #12040\r\n* Fix type of force_upcast to bool  by @BerndDoser in #12046\r\n* Update autoencoder_kl_cosmos.py  by @tanuj-rai in #12045\r\n* Qwen-Image  by @naykun in #12055\r\n* [wan2.2] follow-up  by @yiyixuxu in #12024\r\n* tests + minor refactor for QwenImage  by @a-r-r-o-w in #12057\r\n* Cross attention module to Wan Attention  by @samuelt0 in #12058\r\n* fix(qwen-image): update vae license  by @naykun in #12063\r\n* CI fixing  by @paulinebm in #12059\r\n* enable all gpus when running ci.  by @sayakpaul in #12062\r\n* fix the rest for all GPUs in CI  by @sayakpaul in #12064\r\n* [docs] Install  by @stevhliu in #12026\r\n* [wip] feat: support lora in qwen image and training script  by @sayakpaul in #12056\r\n* [docs] small corrections to the example in the Qwen docs  by @sayakpaul in #12068\r\n* [tests] Fix Qwen test_inference slices  by @a-r-r-o-w in #12070\r\n* [tests] deal with the failing AudioLDM2 tests  by @sayakpaul in #12069\r\n* optimize QwenImagePipeline to reduce unnecessary CUDA synchronization  by @chengzeyi in #12072\r\n* Add cuda kernel support for GGUF inference  by @Isotr0py in #11869\r\n* fix input shape for WanGGUFTexttoVideoSingleFileTests  by @jiqing-feng in #12081\r\n* [refactor] condense group offloading   by @a-r-r-o-w in #11990\r\n* Fix group offloading synchronization bug for parameter-only GroupModule's  by @a-r-r-o-w in #12077\r\n* Helper functions to return skip-layer compatible layers  by @a-r-r-o-w in #12048\r\n* Make `prompt_2` optional in Flux Pipelines   by @DN6 in #12073\r\n* [tests] tighten compilation tests for quantization  by @sayakpaul in #12002\r\n* Implement Frequency-Decoupled Guidance (FDG) as a Guider  by @dg845 in #11976\r\n* fix flux type hint  by @DefTruth in #12089\r\n* [qwen] device typo  by @yiyixuxu in #12099\r\n* [lora] adapt new LoRA config injection method  by @sayakpaul in #11999\r\n* lora_conversion_utils: replace lora up/down with a/b even if `transformer.` in key  by @Beinsezii in #12101\r\n* [tests] device placement for non-denoiser components in group offloading LoRA tests  by @sayakpaul in #12103\r\n* [Modular] Fast Tests  by @yiyixuxu in #11937\r\n* [GGUF] feat: support loading diffusers format gguf checkpoints.  by @sayakpaul in #11684\r\n* [docs] diffusers gguf checkpoints  by @sayakpaul in #12092\r\n* [core] add modular support for Flux I2I  by @sayakpaul in #12086\r\n* [lora] support loading loras from `lightx2v/Qwen-Image-Lightning`  by @sayakpaul in #12119\r\n* [Modular] More Updates for Custom Code Loading  by @DN6 in #11969\r\n* enable compilation in qwen image.  by @sayakpaul in #12061\r\n* [tests] Add inference test slices for SD3 and remove unnecessary tests  by @a-r-r-o-w in #12106\r\n* [chore] complete the licensing statement.  by @sayakpaul in #12001\r\n* [docs] Cache link  by @stevhliu in #12105\r\n* [Modular] Add experimental feature warning for Modular Diffusers  by @DN6 in #12127\r\n* Add low_cpu_mem_usage option to from_single_file to align with from_pretrained  by @IrisRainbowNeko in #12114\r\n* [docs] Modular diffusers  by @stevhliu in #11931\r\n* [Bugfix] typo fix in NPU FA  by @leisuzz in #12129\r\n* Add QwenImage Inpainting and Img2Img pipeline  by @Trgtuan10 in #12117\r\n* [core] parallel loading of shards  by @sayakpaul in #12028\r\n* try to use deepseek with an agent to auto i18n to zh  by @SamYuan1990 in #12032\r\n* [docs] Refresh effective and efficient doc  by @stevhliu in #12134\r\n* Fix bf15/fp16 for pipeline_wan_vace.py  by @SlimRG in #12143\r\n* make parallel loading flag a part of constants.  by @sayakpaul in #12137\r\n* [docs] Parallel loading of shards  by @stevhliu in #12135\r\n* feat: cuda device_map for pipelines.  by @sayakpaul in #12122\r\n* [core] respect `local_files_only=True` when using sharded checkpoints  by @sayakpaul in #12005\r\n* support `hf_quantizer` in cache warmup.  by @sayakpaul in #12043\r\n* make test_gguf all pass on xpu  by @yao-matrix in #12158\r\n* [docs] Quickstart  by @stevhliu in #12128\r\n* Qwen Image Edit Support  by @naykun in #12164\r\n* remove silu for CogView4  by @lambertwjh in #12150\r\n* [qwen] Qwen image edit followups  by @sayakpaul in #12166\r\n* Minor modification to support DC-AE-turbo  by @chenjy2003 in #12169\r\n* [Docs] typo error in qwen image  by @leisuzz in #12144\r\n* fix: caching allocator behaviour for quantization.  by @sayakpaul in #12172\r\n* fix(training_utils): wrap device in list for DiffusionPipeline  by @MengAiDev in #12178\r\n* [docs] Clarify guidance scale in Qwen pipelines  by @sayakpaul in #12181\r\n* [LoRA] feat: support more Qwen LoRAs from the community.  by @sayakpaul in #12170\r\n* Update README.md  by @Taechai in #12182\r\n* [chore] add lora button to qwenimage docs  by @sayakpaul in #12183\r\n* [Wan 2.2 LoRA] add support for 2nd transformer lora loading + wan 2.2 lightx2v lora   by @linoytsaban in #12074\r\n* Release: v0.35.0 by @sayakpaul (direct commit on v0.35.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @vuongminh1907\r\n    * update: FluxKontextInpaintPipeline support (#11820)\r\n* @Net-Mist\r\n    * feat: add multiple input image support in Flux Kontext (#11880)\r\n* @tolgacangoz\r\n    * Add SkyReels V2: Infinite-Length Film Generative Model (#11518)\r\n* @naykun\r\n    * Qwen-Image (#12055)\r\n    * fix(qwen-image): update vae license (#12063)\r\n    * Qwen Image Edit Support (#12164)\r\n* @Trgtuan10\r\n    * Add QwenImage Inpainting and Img2Img pipeline (#12117)\r\n* @SamYuan1990\r\n    * try to use deepseek with an agent to auto i18n to zh (#12032)\r\n","publishedAt":"2025-08-19T03:28:44.000Z","fetchedAt":"2026-04-07T17:27:25.723Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.35.0","media":[],"coverageCount":0},{"id":"rel_RPTKNQVq6NvbhyOjIccg_","version":"v0.34.0","type":"feature","title":"Diffusers 0.34.0: New Image and Video Models, Better torch.compile Support, and more","summary":"## 📹 New video generation pipelines\r\n\r\n### Wan VACE\r\n\r\nWan VACE supports various generation techniques which achieve controllable video generation. I...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## 📹 New video generation pipelines\r\n\r\n### Wan VACE\r\n\r\nWan VACE supports various generation techniques which achieve controllable video generation. It comes in two variants: a 1.3B model for fast iteration & prototyping, and a 14B for high quality generation. Some of the capabilities include:\r\n\r\n- Control to Video (Depth, Pose, Sketch, Flow, Grayscale, Scribble, Layout, Boundary Box, etc.). Recommended library for preprocessing videos to obtain control videos: [**huggingface/controlnet_aux**](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan)\r\n- Image/Video to Video (first frame, last frame, starting clip, ending clip, random clips)\r\n- Inpainting and Outpainting\r\n- Subject to Video (faces, object, characters, etc.)\r\n- Composition to Video (reference anything, animate anything, swap anything, expand anything, move anything, etc.)\r\n\r\nThe code snippets available in [**this**](https://github.com/huggingface/diffusers/pull/11582) pull request demonstrate some examples of how videos can be generated with controllability signals.\r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan#any-to-video-controllable-generation) to learn more.\r\n\r\n### Cosmos Predict2 Video2World\r\n\r\nCosmos-Predict2 is a key branch of the [Cosmos World Foundation Models](https://www.nvidia.com/en-us/ai/cosmos) (WFMs) ecosystem for Physical AI, specializing in future state prediction through advanced world modeling. It offers two powerful capabilities: text-to-image generation for creating high-quality images from text descriptions, and video-to-world generation for producing visual simulations from video inputs.\r\n\r\nThe Video2World model comes in a 2B and 14B variant. Check out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cosmos) to learn more.\r\n\r\n### LTX 0.9.7 and Distilled\r\n\r\nLTX 0.9.7 and its distilled variants are the latest in the family of models released by Lightricks.\r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/en/api/pipelines/ltx_video) to learn more.\r\n\r\n### Hunyuan Video Framepack and F1\r\n\r\n[Framepack](https://github.com/lllyasviel/FramePack) is a novel method for enabling long video generation. There are two released variants of Hunyuan Video trained using this technique. Check out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/framepack#framepack) to learn more.\r\n\r\n### FusionX\r\n\r\nThe [FusionX family of models and LoRAs](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX), built on top of Wan2.1-14B, should already be supported. To load the model, use `from_single_file()`:\r\n\r\n```python\r\nfrom diffusers import WanTransformer3DModel\r\n\r\ntransformer = WanTransformer3DModel.from_single_file(\r\n    \"https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/blob/main/Wan14Bi2vFusioniX_fp16.safetensors\",\r\n    torch_dtype=torch.bfloat16\r\n)\r\n```\r\n\r\nTo load the LoRAs, use `load_lora_weights()`:\r\n\r\n```python\r\npipe = DiffusionPipeline.from_pretrained(\r\n    \"Wan-AI/Wan2.1-T2V-14B-Diffusers\",\r\n    torch_dtype=torch.bfloat16\r\n).to(\"cuda\")\r\npipe.load_lora_weights(\r\n    \"vrgamedevgirl84/Wan14BT2VFusioniX\", weight_name=\"FusionX_LoRa/Wan2.1_T2V_14B_FusionX_LoRA.safetensors\"\r\n)\r\n```\r\n\r\n### AccVideo and CausVid (only LoRAs)\r\n\r\n[AccVideo](https://github.com/aejion/AccVideo) and [CausVid](https://github.com/tianweiy/CausVid) are two novel distillation techniques that speed up the generation time of video diffusion models while preserving quality. Diffusers supports loading their extracted LoRAs with their respective models.\r\n\r\n## 🌠 New image generation pipelines\r\n\r\n### Cosmos Predict2 Text2Image\r\n\r\nText-to-image models from the Cosmos-Predict2 release. The models comes in a 2B and 14B variant. Check out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cosmos) to learn more.\r\n\r\n### Chroma\r\n\r\nChroma is a **8.9B** parameter model based on **FLUX.1-schnell.** It’s fully **Apache 2.0 licensed**, ensuring that **anyone** can use, modify, and build on top of it. Checkout the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/chroma#chroma) to learn more\r\n\r\nThanks to @Ednaordinary for contributing it in [this PR](https://github.com/huggingface/diffusers/pull/11698)!\r\n\r\n### VisualCloze\r\n\r\n[VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning](https://huggingface.co/papers/2504.07960) is an innovative in-context learning framework based universal image generation framework that offers key capabilities:\r\n\r\n1. Support for various in-domain tasks\r\n2. Generalization to unseen tasks through in-context learning\r\n3. Unify multiple tasks into one step and generate both target image and intermediate results\r\n4. Support reverse-engineering conditions from target images\r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/visualcloze) to learn more. Thanks to @lzyhha for contributing this in [this PR](https://github.com/huggingface/diffusers/pull/11377)!\r\n\r\n## Better `torch.compile` support\r\n\r\nWe have worked with the PyTorch team to improve how we provide `torch.compile()` compatibility throughout the library. More specifically, we now test the widely used models like Flux for any recompilation and graph break issues which can get in the way of fully realizing `torch.compile()` benefits. Refer to the following links to learn more:\r\n\r\n- https://github.com/huggingface/diffusers/pull/11085\r\n- https://github.com/huggingface/diffusers/issues/11430\r\n\r\nAdditionally, users can combine offloading with compilation to get a better speed-memory trade-off. Below is an example:\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nimport torch\r\nfrom diffusers import DiffusionPipeline\r\ntorch._dynamo.config.cache_size_limit = 10000\r\n\r\npipeline = DiffusionPipeline.from_pretrained(\r\n    \"black-forest-labs/FLUX.1-schnell\", torch_dtype=torch.bfloat16\r\n)\r\npipline.enable_model_cpu_offload()\r\n# Compile.\r\npipeline.transformer.compile()\r\n\r\nimage = pipeline(\r\n    prompt=\"An astronaut riding a horse on Mars\",\r\n    guidance_scale=0.,\r\n    height=768,\r\n    width=1360,\r\n    num_inference_steps=4,\r\n    max_sequence_length=256,\r\n).images[0]\r\nprint(f\"Max memory reserved: {torch.cuda.max_memory_allocated() / 1024**3:.2f} GB\")\r\n```\r\n\r\n</details>\r\n\r\nThis is compatible with [group offloading](https://huggingface.co/docs/diffusers/main/en/optimization/memory#group-offloading), too. Interested readers can check out the concerned PRs below:\r\n\r\n- https://github.com/huggingface/diffusers/pull/11605\r\n- https://github.com/huggingface/diffusers/pull/11670\r\n\r\nYou can substantially reduce memory requirements by combining quantization with offloading and then improving speed with `torch.compile()`. Below is an example:\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nfrom diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig\r\nfrom transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig\r\nfrom diffusers import AutoModel, FluxPipeline\r\nfrom transformers import T5EncoderModel\r\n\r\nimport torch\r\ntorch._dynamo.config.recompile_limit = 1000 \r\n\r\nquant_kwargs = {\"load_in_4bit\": True, \"bnb_4bit_compute_dtype\": torch_dtype, \"bnb_4bit_quant_type\": \"nf4\"}\r\ntext_encoder_2_quant_config = TransformersBitsAndBytesConfig(**quant_kwargs)\r\ndit_quant_config = DiffusersBitsAndBytesConfig(**quant_kwargs)\r\n\r\nckpt_id = \"black-forest-labs/FLUX.1-dev\"\r\ntext_encoder_2 = T5EncoderModel.from_pretrained(\r\n    ckpt_id,\r\n    subfolder=\"text_encoder_2\",\r\n    quantization_config=text_encoder_2_quant_config,\r\n    torch_dtype=torch_dtype,\r\n)\r\ntransformer = AutoModel.from_pretrained(\r\n    ckpt_id,\r\n    subfolder=\"transformer\",\r\n    quantization_config=dit_quant_config,\r\n    torch_dtype=torch_dtype,\r\n)\r\npipe = FluxPipeline.from_pretrained(\r\n    ckpt_id,\r\n    transformer=transformer,\r\n    text_encoder_2=text_encoder_2,\r\n    torch_dtype=torch_dtype,\r\n)\r\npipe.enable_model_cpu_offload()\r\npipe.transformer.compile()\r\n\r\nimage = pipeline(\r\n    prompt=\"An astronaut riding a horse on Mars\",\r\n    guidance_scale=3.5,\r\n    height=768,\r\n    width=1360,\r\n    num_inference_steps=28,\r\n    max_sequence_length=512,\r\n).images[0]\r\n```\r\n\r\n</details>\r\n    \r\nStarting from `bitsandbytes==0.46.0` onwards, bnb-quantized models should be fully compatible with `torch.compile()` without graph-breaks. This means that when compiling a bnb-quantized model, users can do: `model.compile(fullgraph=True)`. This can significantly improve speed while still providing memory benefits. The figure below provides a comparison with Flux.1-Dev. Refer to [this benchmarking script](https://gist.github.com/sayakpaul/0db9d8eeeb3d2a0e5ed7cf0d9ca19b7d) to learn more. \r\n\r\n![image](https://github.com/user-attachments/assets/d0fd34bf-618e-41d2-b2bb-e821fe02f59b)\r\n\r\nNote that for 4bit bnb models, it’s currently needed to install PyTorch nightly if `fullgraph=True` is specified during compilation.\r\n\r\nHuge shoutout to @anijain2305 and @StrongerXi from the PyTorch team for the incredible support.\r\n\r\n## PipelineQuantizationConfig\r\n\r\nUsers can now provide a quantization config while initializing a pipeline:\r\n\r\n```python\r\nimport torch\r\nfrom diffusers import DiffusionPipeline\r\nfrom diffusers.quantizers import PipelineQuantizationConfig\r\n\r\npipeline_quant_config = PipelineQuantizationConfig(\r\n     quant_backend=\"bitsandbytes_4bit\",\r\n     quant_kwargs={\"load_in_4bit\": True, \"bnb_4bit_quant_type\": \"nf4\", \"bnb_4bit_compute_dtype\": torch.bfloat16},\r\n     components_to_quantize=[\"transformer\", \"text_encoder_2\"],\r\n)\r\npipe = DiffusionPipeline.from_pretrained(\r\n    \"black-forest-labs/FLUX.1-dev\",\r\n    quantization_config=pipeline_quant_config,\r\n    torch_dtype=torch.bfloat16,\r\n).to(\"cuda\")\r\n\r\nimage = pipe(\"photo of a cute dog\").images[0]\r\n```\r\n\r\nThis reduces the barrier to entry for our users willing to use quantization without having to write too much code. Refer to the documentation to learn more about [different configurations](https://huggingface.co/docs/diffusers/main/en/quantization/overview#pipeline-level-quantization) allowed through `PipelineQuantizationConfig`.\r\n\r\n## Group offloading with disk\r\n\r\nIn the [previous release](https://github.com/huggingface/diffusers/releases/tag/v0.33.0), we shipped “group offloading” which lets you offload blocks/nodes within a model, optimizing its memory consumption. It also lets you overlap this offloading with computation, providing a good speed-memory trade-off, especially in low VRAM environments.\r\n\r\nHowever, you still need a considerable amount of system RAM to make offloading work effectively. So, low VRAM and low RAM environments would still not work. \r\n\r\nStarting this release, users will additionally have the option to offload to disk instead of RAM, further lowering memory consumption. Set the `offload_to_disk_path` to enable this feature.\r\n\r\n```python\r\npipeline.transformer.enable_group_offload(\r\n    onload_device=\"cuda\", \r\n    offload_device=\"cpu\", \r\n    offload_type=\"leaf_level\", \r\n    offload_to_disk_path=\"path/to/disk\"\r\n)\r\n```\r\n\r\nRefer to these [two](https://github.com/huggingface/diffusers/pull/11682#issue-3129365363) [tables](https://github.com/huggingface/diffusers/pull/11682#issuecomment-2955715126) to compare the speed and memory trade-offs.\r\n\r\n## LoRA metadata parsing\r\n\r\nIt is beneficial to include the `LoraConfig` in a LoRA state dict that was used to train the LoRA. In its absence, users were restricted to using the same LoRA alpha as the LoRA rank. We have modified the most popular training scripts to allow passing custom `lora_alpha` through the CLI. Refer to [this thread](https://github.com/huggingface/diffusers/pull/11723) for more updates. Refer to [this comment](https://github.com/huggingface/diffusers/pull/11324#issuecomment-2998516012) for some extended clarifications.\r\n\r\n## New training scripts\r\n\r\n- We now have a capable training script for training robust timestep-distilled models through the SANA Sprint framework. Check out [this resource](https://github.com/huggingface/diffusers/tree/main/examples/research_projects/sana) for more details. Thanks to @scxue and @lawrence-cj for contributing it in [this PR](https://github.com/huggingface/diffusers/pull/11514).\r\n- HiDream LoRA DreamBooth training script ([docs](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_hidream.md)). The script supports training with quantization. [HiDream](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream) is an MIT-licensed model. So, make it yours with this training script.\r\n\r\n## Updates on educational materials on quantization\r\n\r\nWe have worked on a two-part series discussing the support of quantization in Diffusers. Check them out:\r\n\r\n- [Exploring Quantization Backends in Diffusers](https://huggingface.co/blog/diffusers-quantization)\r\n- [(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware](https://huggingface.co/blog/flux-qlora)\r\n\r\n## All commits\r\n\r\n* [LoRA] support musubi wan loras.  by @sayakpaul in #11243\r\n* fix test_vanilla_funetuning failure on XPU and A100  by @yao-matrix in #11263\r\n* make test_stable_diffusion_inpaint_fp16 pass on XPU  by @yao-matrix in #11264\r\n* make test_dict_tuple_outputs_equivalent pass on XPU  by @yao-matrix in #11265\r\n* add onnxruntime-qnn & onnxruntime-cann  by @xieofxie in #11269\r\n* make test_instant_style_multiple_masks pass on XPU  by @yao-matrix in #11266\r\n* [BUG] Fix convert_vae_pt_to_diffusers bug  by @lavinal712 in #11078\r\n* Fix LTX 0.9.5 single file  by @hlky in #11271\r\n* [Tests] Cleanup lora tests utils  by @sayakpaul in #11276\r\n* [CI] relax tolerance for unclip further  by @sayakpaul in #11268\r\n* do not use `DIFFUSERS_REQUEST_TIMEOUT` for notification bot  by @sayakpaul in #11273\r\n* Fix incorrect tile_latent_min_width calculation in AutoencoderKLMochi  by @kuantuna in #11294\r\n* HiDream Image  by @hlky in #11231\r\n* flow matching lcm scheduler  by @quickjkee in #11170\r\n* Update autoencoderkl_allegro.md  by @Forbu in #11303\r\n* Hidream refactoring follow ups  by @a-r-r-o-w in #11299\r\n* Fix incorrect tile_latent_min_width calculations  by @kuantuna in #11305\r\n* [ControlNet] Adds controlnet for SanaTransformer  by @ishan-modi in #11040\r\n* make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU  by @yao-matrix in #11308\r\n* make test_stable_diffusion_karras_sigmas pass on XPU  by @yao-matrix in #11310\r\n* make `KolorsPipelineFastTests::test_inference_batch_single_identical` pass on XPU  by @faaany in #11313\r\n* [LoRA] support more SDXL loras.  by @sayakpaul in #11292\r\n* [HiDream] code example  by @linoytsaban in #11317\r\n* import for FlowMatchLCMScheduler  by @asomoza in #11318\r\n* Use float32 on mps or npu in transformer_hidream_image's rope  by @hlky in #11316\r\n* Add `skrample` section to `community_projects.md`  by @Beinsezii in #11319\r\n* [docs] Promote `AutoModel` usage  by @sayakpaul in #11300\r\n* [LoRA] Add LoRA support to AuraFlow  by @hameerabbasi in #10216\r\n* Fix vae.Decoder prev_output_channel  by @hlky in #11280\r\n* fix CPU offloading related fail cases on XPU  by @yao-matrix in #11288\r\n* [docs] fix hidream docstrings.  by @sayakpaul in #11325\r\n* Rewrite AuraFlowPatchEmbed.pe_selection_index_based_on_dim to be torch.compile compatible  by @AstraliteHeart in #11297\r\n* post release 0.33.0  by @sayakpaul in #11255\r\n* another fix for FlowMatchLCMScheduler forgotten import  by @asomoza in #11330\r\n* Fix Hunyuan I2V for `transformers>4.47.1`    by @DN6 in #11293\r\n* unpin torch versions for onnx Dockerfile  by @sayakpaul in #11290\r\n* [single file] enable telemetry for single file loading when using GGUF.  by @sayakpaul in #11284\r\n* [docs] add a snippet for compilation in the auraflow docs.  by @sayakpaul in #11327\r\n* Hunyuan I2V fast tests fix  by @DN6 in #11341\r\n* [BUG] fixed _toctree.yml alphabetical ordering  by @ishan-modi in #11277\r\n* Fix wrong dtype argument name as torch_dtype  by @nPeppon in #11346\r\n* [chore] fix lora docs utils  by @sayakpaul in #11338\r\n* [docs] add note about use_duck_shape in auraflow docs.  by @sayakpaul in #11348\r\n* [LoRA] Propagate `hotswap` better  by @sayakpaul in #11333\r\n* [Hi Dream] follow-up  by @yiyixuxu in #11296\r\n* [bitsandbytes] improve dtype mismatch handling for bnb + lora.  by @sayakpaul in #11270\r\n* Update controlnet_flux.py  by @haofanwang in #11350\r\n* enable 2 test cases on XPU  by @yao-matrix in #11332\r\n* [BNB] Fix test_moving_to_cpu_throws_warning   by @SunMarc in #11356\r\n* support Wan-FLF2V  by @yiyixuxu in #11353\r\n* Fix: `StableDiffusionXLControlNetAdapterInpaintPipeline` incorrectly inherited `StableDiffusionLoraLoaderMixin`  by @Kazuki-Yoda in #11357\r\n* update output for Hidream transformer  by @yiyixuxu in #11366\r\n* [Wan2.1-FLF2V] update conversion script  by @yiyixuxu in #11365\r\n* [Flux LoRAs] fix lr scheduler bug in distributed scenarios  by @linoytsaban in #11242\r\n* [train_dreambooth_lora_sdxl.py] Fix the LR Schedulers when num_train_epochs is passed in a distributed training env  by @kghamilton89 in #11240\r\n* fix issue that training flux controlnet was unstable and validation r…  by @PromeAIpro in #11373\r\n* Fix Wan I2V prepare_latents dtype  by @a-r-r-o-w in #11371\r\n* [BUG] fixes in kadinsky pipeline  by @ishan-modi in #11080\r\n* Add Serialized Type Name kwarg in Model Output  by @anzr299 in #10502\r\n* [cogview4][feat] Support attention mechanism with variable-length support and batch packing  by @OleehyO in #11349\r\n* Support different-length pos/neg prompts for FLUX.1-schnell variants like Chroma  by @josephrocca in #11120\r\n* [Refactor] Minor Improvement for import utils  by @ishan-modi in #11161\r\n* Add stochastic sampling to FlowMatchEulerDiscreteScheduler  by @apolinario in #11369\r\n* [LoRA] add LoRA support to HiDream and fine-tuning script  by @linoytsaban in #11281\r\n* Update modeling imports  by @a-r-r-o-w in #11129\r\n* [HiDream] move deprecation to 0.35.0  by @yiyixuxu in #11384\r\n* Update README_hidream.md  by @AMEERAZAM08 in #11386\r\n* Fix group offloading with block_level and use_stream=True  by @a-r-r-o-w in #11375\r\n* [train_dreambooth_flux] Add LANCZOS as the default interpolation mode for image resizing  by @ishandutta0098 in #11395\r\n* [Feature] Added Xlab Controlnet support  by @ishan-modi in #11249\r\n* Kolors additional pipelines, community contrib  by @Teriks in #11372\r\n* [HiDream LoRA] optimizations + small updates  by @linoytsaban in #11381\r\n* Fix Flux IP adapter argument in the pipeline example  by @AeroDEmi in #11402\r\n* [BUG] fixed WAN docstring  by @ishan-modi in #11226\r\n* Fix typos in strings and comments  by @co63oc in #11407\r\n* [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing  by @merterbak in #11421\r\n* [tests] add tests to check for graph breaks, recompilation, cuda syncs in pipelines during torch.compile()  by @sayakpaul in #11085\r\n* enable group_offload cases and quanto cases on XPU  by @yao-matrix in #11405\r\n* enable test_layerwise_casting_memory cases on XPU  by @yao-matrix in #11406\r\n* [tests] fix import.  by @sayakpaul in #11434\r\n* [train_text_to_image] Better image interpolation in training scripts follow up  by @tongyu0924 in #11426\r\n* [train_text_to_image_lora] Better image interpolation in training scripts follow up  by @tongyu0924 in #11427\r\n* enable 28 GGUF test cases on XPU  by @yao-matrix in #11404\r\n* [Hi-Dream LoRA] fix bug in validation  by @linoytsaban in #11439\r\n* Fixing missing provider options argument  by @urpetkov-amd in #11397\r\n* Set LANCZOS as the default interpolation for image resizing in ControlNet training  by @YoulunPeng in #11449\r\n* Raise warning instead of error for block offloading with streams  by @a-r-r-o-w in #11425\r\n* enable marigold_intrinsics cases on XPU  by @yao-matrix in #11445\r\n* `torch.compile` fullgraph compatibility for Hunyuan Video  by @a-r-r-o-w in #11457\r\n* enable consistency test cases on XPU, all passed  by @yao-matrix in #11446\r\n* enable unidiffuser test cases on xpu  by @yao-matrix in #11444\r\n* Add generic support for Intel Gaudi accelerator (hpu device)  by @dsocek in #11328\r\n* Add StableDiffusion3InstructPix2PixPipeline  by @xduzhangjiayu in #11378\r\n* make safe diffusion test cases pass on XPU and A100  by @yao-matrix in #11458\r\n* [test_models_transformer_hunyuan_video] help us test torch.compile() for impactful models  by @tongyu0924 in #11431\r\n* Add LANCZOS as default interplotation mode.  by @Va16hav07 in #11463\r\n* make autoencoders. controlnet_flux and wan_transformer3d_single_file pass on xpu  by @yao-matrix in #11461\r\n* [WAN] fix recompilation issues  by @sayakpaul in #11475\r\n* Fix typos in docs and comments  by @co63oc in #11416\r\n* [tests] xfail recent pipeline tests for specific methods.  by @sayakpaul in #11469\r\n* cache packages_distributions  by @vladmandic in #11453\r\n* [docs] Memory optims  by @stevhliu in #11385\r\n* [docs] Adapters  by @stevhliu in #11331\r\n* [train_dreambooth_lora_sdxl_advanced] Add LANCZOS as the default interpolation mode for image resizing  by @yuanjua in #11471\r\n* [train_dreambooth_lora_flux_advanced] Add LANCZOS as the default interpolation mode for image resizing  by @ysurs in #11472\r\n* enable semantic diffusion and stable diffusion panorama cases on XPU  by @yao-matrix in #11459\r\n* [Feature] Implement tiled VAE encoding/decoding for Wan model.  by @c8ef in #11414\r\n* [train_text_to_image_sdxl]Add LANCZOS as default interpolation mode for image resizing  by @ParagEkbote in #11455\r\n* [train_dreambooth_lora_sdxl] Add --image_interpolation_mode option for image resizing (default to lanczos)  by @MinJu-Ha in #11490\r\n* [train_dreambooth_lora_lumina2] Add LANCZOS as the default interpolation mode for image resizing  by @cjfghk5697 in #11491\r\n* [training] feat: enable quantization for hidream lora training.  by @sayakpaul in #11494\r\n* Set LANCZOS as the default interpolation method for image resizing.  by @yijun-lee in #11492\r\n* Update training script for txt to img sdxl with lora supp with new interpolation.  by @RogerSinghChugh in #11496\r\n* Fix torchao docs typo for fp8 granular quantization  by @a-r-r-o-w in #11473\r\n* Update setup.py to pin min version of `peft`  by @sayakpaul in #11502\r\n* update dep table.  by @sayakpaul in #11504\r\n* [LoRA] use `removeprefix` to preserve sanity.  by @sayakpaul in #11493\r\n* Hunyuan Video Framepack  by @a-r-r-o-w in #11428\r\n* enable lora cases on XPU  by @yao-matrix in #11506\r\n* [lora_conversion] Enhance key handling for OneTrainer components in LORA conversion utility  by @iamwavecut in #11441) \r\n* [docs] minor updates to bitsandbytes docs.  by @sayakpaul in #11509\r\n* Cosmos  by @a-r-r-o-w in #10660\r\n* clean up the __Init__ for stable_diffusion  by @yiyixuxu in #11500\r\n* fix audioldm by @sayakpaul (direct commit on v0.34.0-release)\r\n* Revert \"fix audioldm\" by @sayakpaul (direct commit on v0.34.0-release)\r\n* [LoRA] make lora alpha and dropout configurable   by @linoytsaban in #11467\r\n* Add cross attention type for Sana-Sprint training in diffusers.  by @scxue in #11514\r\n* Conditionally import torchvision in Cosmos transformer  by @a-r-r-o-w in #11524\r\n* [tests] fix audioldm2 for transformers main.  by @sayakpaul in #11522\r\n* feat: pipeline-level quantization config  by @sayakpaul in #11130\r\n* [Tests] Enable more general testing for `torch.compile()` with LoRA hotswapping  by @sayakpaul in #11322\r\n* [LoRA] support non-diffusers hidream loras  by @sayakpaul in #11532\r\n* enable 7 cases on XPU  by @yao-matrix in #11503\r\n* [LTXPipeline] Update latents dtype to match VAE dtype  by @james-p-xu in #11533\r\n* enable dit integration cases on xpu  by @yao-matrix in #11523\r\n* enable print_env on xpu  by @yao-matrix in #11507\r\n* Change Framepack transformer layer initialization order  by @a-r-r-o-w in #11535\r\n* [tests] add tests for framepack transformer model.  by @sayakpaul in #11520\r\n* Hunyuan Video Framepack F1  by @a-r-r-o-w in #11534\r\n* enable several pipeline integration tests on XPU  by @yao-matrix in #11526\r\n* [test_models_transformer_ltx.py] help us test torch.compile() for impactful models  by @cjfghk5697 in #11512\r\n* Add VisualCloze  by @lzyhha in #11377\r\n* Fix typo in train_diffusion_orpo_sdxl_lora_wds.py  by @Meeex2 in #11541\r\n* fix: remove `torch_dtype=\"auto\"` option from docstrings  by @johannaSommer in #11513\r\n* [train_dreambooth.py] Fix the LR Schedulers when num_train_epochs is passed in a distributed training env  by @kghamilton89 in #11239\r\n* [LoRA] small change to support Hunyuan LoRA Loading for FramePack  by @linoytsaban in #11546\r\n* LTX Video 0.9.7  by @a-r-r-o-w in #11516\r\n* [tests] Enable testing for HiDream transformer  by @sayakpaul in #11478\r\n* Update pipeline_flux_img2img.py to add missing vae_slicing and vae_tiling calls.  by @Meatfucker in #11545\r\n*  Fix deprecation warnings in test_ltx_image2video.py  by @AChowdhury1211 in #11538\r\n* [tests] Add torch.compile test for UNet2DConditionModel  by @olccihyeon in #11537\r\n* [Single File] GGUF/Single File Support for HiDream  by @DN6 in #11550\r\n* [gguf] Refactor __torch_function__ to avoid unnecessary computation  by @anijain2305 in #11551\r\n* [tests] add tests for combining layerwise upcasting and groupoffloading.  by @sayakpaul in #11558\r\n* [docs] Regional compilation docs  by @sayakpaul in #11556\r\n* enhance value guard of _device_agnostic_dispatch  by @yao-matrix in #11553\r\n* Doc update  by @Player256 in #11531\r\n* Revert error to warning when loading LoRA from repo with multiple weights  by @apolinario in #11568\r\n* [docs] tip for group offloding + quantization  by @sayakpaul in #11576\r\n* [LoRA] support non-diffusers LTX-Video loras  by @linoytsaban in #11572\r\n* [WIP][LoRA] start supporting kijai wan lora.  by @sayakpaul in #11579\r\n* [Single File] Fix loading for LTX 0.9.7 transformer  by @DN6 in #11578\r\n* Use HF Papers  by @qgallouedec in #11567\r\n* LTX 0.9.7-distilled; documentation improvements  by @a-r-r-o-w in #11571\r\n* [LoRA] kijai wan lora support for I2V  by @linoytsaban in #11588\r\n* docs: fix invalid links  by @osrm in #11505\r\n* [docs] Remove fast diffusion tutorial  by @stevhliu in #11583\r\n* RegionalPrompting: Inherit from Stable Diffusion  by @b-sai in #11525\r\n* [chore] allow string device to be passed to randn_tensor.  by @sayakpaul in #11559\r\n* Type annotation fix  by @DN6 in #11597\r\n* [LoRA] minor fix for `load_lora_weights()` for Flux and a test  by @sayakpaul in #11595\r\n* Update Intel Gaudi doc  by @regisss in #11479\r\n* enable pipeline test cases on xpu  by @yao-matrix in #11527\r\n* [Feature] AutoModel can load components using model_index.json  by @ishan-modi in #11401\r\n* [docs] Pipeline-level quantization  by @stevhliu in #11604\r\n* Fix bug when `variant` and `safetensor` file does not match  by @kaixuanliu in #11587\r\n* [tests] Changes to the `torch.compile()` CI and tests  by @sayakpaul in #11508\r\n* Fix mixed variant downloading  by @DN6 in #11611\r\n* fix security issue in build docker ci  by @sayakpaul in #11614\r\n* Make group offloading compatible with torch.compile()  by @sayakpaul in #11605\r\n* [training docs] smol update to README files   by @linoytsaban in #11616\r\n* Adding NPU for get device function  by @leisuzz in #11617\r\n* [LoRA] improve LoRA fusion tests  by @sayakpaul in #11274\r\n* [Sana Sprint] add image-to-image pipeline   by @linoytsaban in #11602\r\n* [CI] fix the filename for displaying failures in lora ci.  by @sayakpaul in #11600\r\n* [docs] PyTorch 2.0  by @stevhliu in #11618\r\n* [textual_inversion_sdxl.py] fix lr scheduler steps count  by @yuanjua in #11557\r\n* Fix wrong indent for examples of controlnet script  by @Justin900429 in #11632\r\n* removing unnecessary else statement  by @YanivDorGalron in #11624\r\n* enable group_offloading and PipelineDeviceAndDtypeStabilityTests on XPU, all passed  by @yao-matrix in #11620\r\n* Bug: Fixed Image 2 Image example  by @vltmedia in #11619\r\n* typo fix in pipeline_flux.py  by @YanivDorGalron in #11623\r\n* Fix typos in strings and comments  by @co63oc in #11476\r\n* [docs] update torchao doc link  by @sayakpaul in #11634\r\n* Use float32 RoPE freqs in Wan with MPS backends  by @hvaara in #11643\r\n* [chore] misc changes in the bnb tests for consistency.  by @sayakpaul in #11355\r\n* [tests] chore: rename lora model-level tests.  by @sayakpaul in #11481\r\n* [docs] Caching methods  by @stevhliu in #11625\r\n* [docs] Model cards  by @stevhliu in #11112\r\n* [CI] Some improvements to Nightly reports summaries  by @DN6 in #11166\r\n* [chore] bring PipelineQuantizationConfig at the top of the import chain.  by @sayakpaul in #11656\r\n* [examples] flux-control: use num_training_steps_for_scheduler  by @Markus-Pobitzer in #11662\r\n* use deterministic to get stable result  by @jiqing-feng in #11663\r\n* [tests] add test for torch.compile + group offloading  by @sayakpaul in #11670\r\n* Wan VACE  by @a-r-r-o-w in #11582\r\n* fixed axes_dims_rope init (huggingface#11641)  by @sofinvalery in #11678\r\n* [tests] Fix how compiler mixin classes are used  by @sayakpaul in #11680\r\n* Introduce DeprecatedPipelineMixin to simplify pipeline deprecation process  by @DN6 in #11596\r\n* Add community class StableDiffusionXL_T5Pipeline  by @ppbrown in #11626\r\n* Update pipeline_flux_inpaint.py to fix padding_mask_crop returning only the inpainted area  by @Meatfucker in #11658\r\n* Allow remote code repo names to contain \".\"  by @akasharidas in #11652\r\n* [LoRA] support Flux Control LoRA with bnb 8bit.  by @sayakpaul in #11655\r\n* [`Wan`] Fix VAE sampling mode in `WanVideoToVideoPipeline`  by @tolgacangoz in #11639\r\n* enable torchao test cases on XPU and switch to device agnostic APIs for test cases  by @yao-matrix in #11654\r\n* [tests] tests for compilation + quantization (bnb)  by @sayakpaul in #11672\r\n* [tests] model-level `device_map` clarifications  by @sayakpaul in #11681\r\n* Improve Wan docstrings  by @a-r-r-o-w in #11689\r\n* Set _torch_version to N/A if torch is disabled.  by @rasmi in #11645\r\n* Avoid DtoH sync from access of nonzero() item in scheduler  by @jbschlosser in #11696\r\n* Apply Occam's Razor in position embedding calculation  by @tolgacangoz in #11562\r\n* [docs] add compilation bits to the bitsandbytes docs.  by @sayakpaul in #11693\r\n* swap out token for style bot.  by @sayakpaul in #11701\r\n* [docs] mention fp8 benefits on supported hardware.  by @sayakpaul in #11699\r\n* Support Wan AccVideo lora  by @a-r-r-o-w in #11704\r\n* [LoRA] parse metadata from LoRA and save metadata  by @sayakpaul in #11324\r\n* Cosmos Predict2  by @a-r-r-o-w in #11695\r\n* Chroma Pipeline  by @Ednaordinary in #11698\r\n* [LoRA ]fix flux lora loader when return_metadata is true for non-diffusers  by @sayakpaul in #11716\r\n* [training] show how metadata stuff should be incorporated in training scripts.  by @sayakpaul in #11707\r\n* Fix misleading comment  by @carlthome in #11722\r\n* Add Pruna optimization framework documentation  by @davidberenstein1957 in #11688\r\n* Support more Wan loras (VACE)  by @a-r-r-o-w in #11726\r\n* [LoRA training] update metadata use for lora alpha + README  by @linoytsaban in #11723\r\n* ⚡️ Speed up method `AutoencoderKLWan.clear_cache` by 886%  by @misrasaurabh1 in #11665\r\n* [training] add ds support to lora hidream  by @leisuzz in #11737\r\n* [tests] device_map tests for all models.  by @sayakpaul in #11708\r\n* [chore] change to 2025 licensing for remaining  by @sayakpaul in #11741\r\n* Chroma Follow Up   by @DN6 in #11725\r\n* [Quantizers] add `is_compileable` property to quantizers.  by @sayakpaul in #11736\r\n* Update more licenses to 2025  by @a-r-r-o-w in #11746\r\n* Add missing HiDream license  by @a-r-r-o-w in #11747\r\n* Bump urllib3 from 2.2.3 to 2.5.0 in /examples/server  by @dependabot[bot] in #11748\r\n* [LoRA] refactor lora loading at the model-level  by @sayakpaul in #11719\r\n* [CI] Fix WAN VACE tests  by @DN6 in #11757\r\n* [CI] Fix SANA tests  by @DN6 in #11756\r\n* Fix HiDream pipeline test module   by @DN6 in #11754\r\n* make group offloading work with disk/nvme transfers  by @sayakpaul in #11682\r\n* Update Chroma Docs  by @DN6 in #11753\r\n* fix invalid component handling behaviour in `PipelineQuantizationConfig`  by @sayakpaul in #11750\r\n* Fix failing cpu offload test for LTX Latent Upscale  by @DN6 in #11755\r\n* [docs] Quantization + torch.compile + offloading  by @stevhliu in #11703\r\n* [docs] device_map  by @stevhliu in #11711\r\n* [docs] LoRA scale scheduling  by @stevhliu in #11727\r\n* Fix dimensionalities in `apply_rotary_emb` functions' comments  by @tolgacangoz in #11717\r\n* enable deterministic in bnb 4 bit tests  by @jiqing-feng in #11738\r\n* enable cpu offloading of new pipelines on XPU & use device agnostic empty to make pipelines work on XPU  by @yao-matrix in #11671\r\n* [tests] properly skip tests instead of `return`  by @sayakpaul in #11771\r\n* [CI] Skip ONNX Upscale tests  by @DN6 in #11774\r\n* [Wan] Fix mask padding in Wan VACE pipeline.  by @bennyguo in #11778\r\n* Add --lora_alpha and metadata handling to train_dreambooth_lora_sana.py  by @imbr92 in #11744\r\n* [docs] minor cleanups in the lora docs.  by @sayakpaul in #11770\r\n* [lora] only remove hooks that we add back  by @yiyixuxu in #11768\r\n* [tests] Fix HunyuanVideo Framepack device tests  by @a-r-r-o-w in #11789\r\n* [chore] raise as early as possible in group offloading  by @sayakpaul in #11792\r\n* [tests] Fix group offloading and layerwise casting test interaction  by @a-r-r-o-w in #11796\r\n* guard omnigen processor.  by @sayakpaul in #11799\r\n* Release: v0.34.0 by @sayakpaul (direct commit on v0.34.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @yao-matrix\r\n    * fix test_vanilla_funetuning failure on XPU and A100 (#11263)\r\n    * make test_stable_diffusion_inpaint_fp16 pass on XPU (#11264)\r\n    * make test_dict_tuple_outputs_equivalent pass on XPU (#11265)\r\n    * make test_instant_style_multiple_masks pass on XPU (#11266)\r\n    * make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU (#11308)\r\n    * make test_stable_diffusion_karras_sigmas pass on XPU (#11310)\r\n    * fix CPU offloading related fail cases on XPU (#11288)\r\n    * enable 2 test cases on XPU (#11332)\r\n    * enable group_offload cases and quanto cases on XPU (#11405)\r\n    * enable test_layerwise_casting_memory cases on XPU (#11406)\r\n    * enable 28 GGUF test cases on XPU (#11404)\r\n    * enable marigold_intrinsics cases on XPU (#11445)\r\n    * enable consistency test cases on XPU, all passed (#11446)\r\n    * enable unidiffuser test cases on xpu (#11444)\r\n    * make safe diffusion test cases pass on XPU and A100 (#11458)\r\n    * make autoencoders. controlnet_flux and wan_transformer3d_single_file pass on xpu (#11461)\r\n    * enable semantic diffusion and stable diffusion panorama cases on XPU (#11459)\r\n    * enable lora cases on XPU (#11506)\r\n    * enable 7 cases on XPU (#11503)\r\n    * enable dit integration cases on xpu (#11523)\r\n    * enable print_env on xpu (#11507)\r\n    * enable several pipeline integration tests on XPU (#11526)\r\n    * enhance value guard of _device_agnostic_dispatch (#11553)\r\n    * enable pipeline test cases on xpu (#11527)\r\n    * enable group_offloading and PipelineDeviceAndDtypeStabilityTests on XPU, all passed (#11620)\r\n    * enable torchao test cases on XPU and switch to device agnostic APIs for test cases (#11654)\r\n    * enable cpu offloading of new pipelines on XPU & use device agnostic empty to make pipelines work on XPU (#11671)\r\n* @hlky\r\n    * Fix LTX 0.9.5 single file (#11271)\r\n    * HiDream Image (#11231)\r\n    * Use float32 on mps or npu in transformer_hidream_image's rope (#11316)\r\n    * Fix vae.Decoder prev_output_channel (#11280)\r\n* @quickjkee\r\n    * flow matching lcm scheduler (#11170)\r\n* @ishan-modi\r\n    * [ControlNet] Adds controlnet for SanaTransformer (#11040)\r\n    * [BUG] fixed _toctree.yml alphabetical ordering (#11277)\r\n    * [BUG] fixes in kadinsky pipeline (#11080)\r\n    * [Refactor] Minor Improvement for import utils (#11161)\r\n    * [Feature] Added Xlab Controlnet support (#11249)\r\n    * [BUG] fixed WAN docstring (#11226)\r\n    * [Feature] AutoModel can load components using model_index.json (#11401)\r\n* @linoytsaban\r\n    * [HiDream] code example (#11317)\r\n    * [Flux LoRAs] fix lr scheduler bug in distributed scenarios (#11242)\r\n    * [LoRA] add LoRA support to HiDream and fine-tuning script (#11281)\r\n    * [HiDream LoRA] optimizations + small updates (#11381)\r\n    * [Hi-Dream LoRA] fix bug in validation (#11439)\r\n    * [LoRA] make lora alpha and dropout configurable  (#11467)\r\n    * [LoRA] small change to support Hunyuan LoRA Loading for FramePack (#11546)\r\n    * [LoRA] support non-diffusers LTX-Video loras (#11572)\r\n    * [LoRA] kijai wan lora support for I2V (#11588)\r\n    * [training docs] smol update to README files  (#11616)\r\n    * [Sana Sprint] add image-to-image pipeline  (#11602)\r\n    * [LoRA training] update metadata use for lora alpha + README (#11723)\r\n* @hameerabbasi\r\n    * [LoRA] Add LoRA support to AuraFlow (#10216)\r\n* @DN6\r\n    * Fix Hunyuan I2V for `transformers>4.47.1`   (#11293)\r\n    * Hunyuan I2V fast tests fix (#11341)\r\n    * [Single File] GGUF/Single File Support for HiDream (#11550)\r\n    * [Single File] Fix loading for LTX 0.9.7 transformer (#11578)\r\n    * Type annotation fix (#11597)\r\n    * Fix mixed variant downloading (#11611)\r\n    * [CI] Some improvements to Nightly reports summaries (#11166)\r\n    * Introduce DeprecatedPipelineMixin to simplify pipeline deprecation process (#11596)\r\n    * Chroma Follow Up  (#11725)\r\n    * [CI] Fix WAN VACE tests (#11757)\r\n    * [CI] Fix SANA tests (#11756)\r\n    * Fix HiDream pipeline test module  (#11754)\r\n    * Update Chroma Docs (#11753)\r\n    * Fix failing cpu offload test for LTX Latent Upscale (#11755)\r\n    * [CI] Skip ONNX Upscale tests (#11774)\r\n* @yiyixuxu\r\n    * [Hi Dream] follow-up (#11296)\r\n    * support Wan-FLF2V (#11353)\r\n    * update output for Hidream transformer (#11366)\r\n    * [Wan2.1-FLF2V] update conversion script (#11365)\r\n    * [HiDream] move deprecation to 0.35.0 (#11384)\r\n    * clean up the __Init__ for stable_diffusion (#11500)\r\n    * [lora] only remove hooks that we add back (#11768)\r\n* @Teriks\r\n    * Kolors additional pipelines, community contrib (#11372)\r\n* @co63oc\r\n    * Fix typos in strings and comments (#11407)\r\n    * Fix typos in docs and comments (#11416)\r\n    * Fix typos in strings and comments (#11476)\r\n* @xduzhangjiayu\r\n    * Add StableDiffusion3InstructPix2PixPipeline (#11378)\r\n* @scxue\r\n    * Add cross attention type for Sana-Sprint training in diffusers. (#11514)\r\n* @lzyhha\r\n    * Add VisualCloze (#11377)\r\n* @b-sai\r\n    * RegionalPrompting: Inherit from Stable Diffusion (#11525)\r\n* @Ednaordinary\r\n    * Chroma Pipeline (#11698)\r\n","publishedAt":"2025-06-24T15:13:19.000Z","fetchedAt":"2026-04-07T17:27:25.723Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.34.0","media":[],"coverageCount":0},{"id":"rel_6xiTUXms4SEka8cLupkWu","version":"v0.33.1","type":"feature","title":"v0.33.1: fix ftfy import","summary":"## All commits\r\n* fix ftfy import for wan pipelines by @yiyixuxu  in #11262","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## All commits\r\n* fix ftfy import for wan pipelines by @yiyixuxu  in #11262","publishedAt":"2025-04-10T05:38:36.000Z","fetchedAt":"2026-04-07T17:27:25.723Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.33.1","media":[],"coverageCount":0},{"id":"rel_0Xwo8msOca6Tk968FwEnH","version":"v0.33.0","type":"feature","title":"Diffusers 0.33.0: New Image and Video Models, Memory Optimizations, Caching Methods, Remote VAEs, New Training Scripts, and more","summary":"## New Pipelines for Video Generation\r\n\r\n### Wan 2.1\r\n\r\nWan2.1 is a comprehensive and open suite of video foundation models that pushes the boundaries...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## New Pipelines for Video Generation\r\n\r\n### Wan 2.1\r\n\r\nWan2.1 is a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. The model release includes 4 different model variants and three different pipelines for Text to Video, Image to Video and Video to Video.\r\n\r\n- `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`\r\n- `Wan-AI/Wan2.1-T2V-14B-Diffusers`\r\n- `Wan-AI/Wan2.1-I2V-14B-480P-Diffusers`\r\n- `Wan-AI/Wan2.1-I2V-14B-720P-Diffusers`\r\n\r\nCheck out the docs [here](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan) to learn more. \r\n\r\n### LTX Video 0.9.5\r\n\r\nLTX Video 0.9.5 is the updated version of the super-fast LTX Video model series. The latest model introduces additional conditioning options, such as keyframe-based animation and video extension (both forward and backward). \r\n\r\nTo support these additional conditioning inputs, we’ve introduced the `LTXConditionPipeline` and `LTXVideoCondition` object. \r\n\r\nTo learn more about the usage, check out the docs [here](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video).\r\n\r\n### Hunyuan Image to Video\r\n\r\nHunyuan utilizes a pre-trained Multimodal Large Language Model (MLLM) with a Decoder-Only architecture as the text encoder.  The input image is processed by the MLLM to generate semantic image tokens. These tokens are then concatenated with the video latent tokens, enabling comprehensive full-attention computation across the combined data and seamlessly integrating information from both the image and its associated caption.\r\n\r\nTo learn more, check out the docs [here](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video).\r\n\r\n### Others\r\n\r\n- [EasyAnimateV5](https://huggingface.co/docs/diffusers/main/en/api/pipelines/easyanimate) (thanks to @bubbliiiing for contributing this in [this PR](https://github.com/huggingface/diffusers/pull/10626))\r\n- [ConsisID](https://huggingface.co/docs/diffusers/main/en/using-diffusers/consisid) (thanks to @SHYuanBest for contributing this in [this PR](https://github.com/huggingface/diffusers/pull/10140))\r\n\r\n## New Pipelines for Image Generation\r\n\r\n### Sana-Sprint\r\n\r\nSANA-Sprint is an efficient diffusion model for ultra-fast text-to-image generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4, rivaling the quality of models like Flux.\r\n\r\nShoutout to @lawrence-cj for their help and guidance on [this PR](https://github.com/huggingface/diffusers/pull/11074).\r\n\r\nCheck out the [pipeline docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana_sprint) of SANA-Sprint to learn more.\r\n\r\n### Lumina2\r\n\r\nLumina-Image-2.0 is a 2B parameter flow-based diffusion transformer for text-to-image generation released under the Apache 2.0 license. \r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/lumina2) to learn more. Thanks to @zhuole1025 for contributing this through [this PR](https://github.com/huggingface/diffusers/pull/10642).\r\n\r\nOne can also LoRA fine-tune Lumina2, taking advantage of its Apach2.0 licensing. Check out [the guide](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_lumina2.md) for more details.\r\n\r\n### Omnigen\r\n\r\nOmniGen is a unified image generation model that can handle multiple tasks including text-to-image, image editing, subject-driven generation, and various computer vision tasks within a single framework. The model consists of a VAE, and a single transformer based on Phi-3 that handles text and image encoding as well as the diffusion process.\r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/omnigen) to learn more about OmniGen. Thanks to @staoxiao for contributing OmniGen in [this PR](https://github.com/huggingface/diffusers/pull/10148).\r\n\r\n### Others\r\n\r\n- [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4) (thanks to @zRzRzRzRzRzRzR for contributing CogView4 in [this PR](https://github.com/huggingface/diffusers/pull/10649))\r\n\r\n## New Memory Optimizations\r\n\r\n### Layerwise Casting\r\n\r\nPyTorch supports `torch.float8_e4m3fn` and `torch.float8_e5m2` as weight storage `dtypes`, but they can’t be used for computation on many devices due to unimplemented kernel support. \r\n\r\nHowever, you can still use these `dtypes` to store model weights in FP8 precision and upcast them to a widely supported dtype such as `torch.float16` or `torch.bfloat16` on-the-fly when the layers are used in the forward pass. This is known as layerwise weight-casting. This can potentially cut down the VRAM requirements of a model by 50%.   \r\n\r\n<details>\r\n<summary>Code</summary>\r\n    \r\n```py\r\nimport torch\r\nfrom diffusers import CogVideoXPipeline, CogVideoXTransformer3DModel\r\nfrom diffusers.utils import export_to_video\r\n\r\nmodel_id = \"THUDM/CogVideoX-5b\"\r\n\r\n# Load the model in bfloat16 and enable layerwise casting\r\ntransformer = CogVideoXTransformer3DModel.from_pretrained(model_id, subfolder=\"transformer\", torch_dtype=torch.bfloat16)\r\ntransformer.enable_layerwise_casting(storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16)\r\n\r\n# Load the pipeline\r\npipe = CogVideoXPipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=torch.bfloat16)\r\npipe.to(\"cuda\")\r\n\r\nprompt = (\r\n    \"A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. \"\r\n    \"The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other \"\r\n    \"pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, \"\r\n    \"casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. \"\r\n    \"The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical \"\r\n    \"atmosphere of this unique musical performance.\"\r\n)\r\nvideo = pipe(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]\r\nexport_to_video(video, \"output.mp4\", fps=8)\r\n```\r\n\r\n</details>\r\n\r\n### Group Offloading\r\n\r\nGroup offloading is the middle ground between sequential and model offloading. It works by offloading groups of internal layers (either `torch.nn.ModuleList` or `torch.nn.Sequential`), which uses less memory than model-level offloading. It is also faster than sequential-level offloading because the number of device synchronizations is reduced. \r\n\r\nOn CUDA devices, we also have the option to enable using layer prefetching with [CUDA Streams](https://pytorch.org/docs/stable/generated/torch.cuda.Stream.html). The next layer to be executed is loaded onto the accelerator device while the current layer is being executed which makes inference substantially faster while still keeping VRAM requirements very low. With this, we introduce the idea of overlapping computation with data transfer.\r\n\r\nOne thing to note is that using CUDA streams can cause a considerable spike in CPU RAM usage. Please ensure that the available CPU RAM is 2 times the size of the model if you choose to set `use_stream=True`. You can reduce CPU RAM usage by setting `low_cpu_mem_usage=True`. This should limit the CPU RAM used to be roughly the same as the size of the model, but will introduce slight latency in the inference process.  \r\n\r\nYou can also use `record_stream=True` when using `use_stream=True` to obtain more speedups at the expense of slightly increased memory usage.\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nimport torch\r\nfrom diffusers import CogVideoXPipeline\r\nfrom diffusers.utils import export_to_video\r\n\r\n# Load the pipeline\r\nonload_device = torch.device(\"cuda\")\r\noffload_device = torch.device(\"cpu\")\r\npipe = CogVideoXPipeline.from_pretrained(\"THUDM/CogVideoX-5b\", torch_dtype=torch.bfloat16)\r\n\r\n# We can utilize the enable_group_offload method for Diffusers model implementations\r\npipe.transformer.enable_group_offload(\r\n\tonload_device=onload_device, \r\n\toffload_device=offload_device, \r\n\toffload_type=\"leaf_level\", \r\n\tuse_stream=True\r\n)\r\n\r\nprompt = (\r\n    \"A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. \"\r\n    \"The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other \"\r\n    \"pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, \"\r\n    \"casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. \"\r\n    \"The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical \"\r\n    \"atmosphere of this unique musical performance.\"\r\n)\r\nvideo = pipe(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]\r\n# This utilized about 14.79 GB. It can be further reduced by using tiling and using leaf_level offloading throughout the pipeline.\r\nprint(f\"Max memory reserved: {torch.cuda.max_memory_allocated() / 1024**3:.2f} GB\")\r\nexport_to_video(video, \"output.mp4\", fps=8)\r\n```\r\n\r\n</details>\r\n    \r\n\r\nGroup offloading can also be applied to non-Diffusers models such as text encoders from the `transformers` library.    \r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nimport torch\r\nfrom diffusers import CogVideoXPipeline\r\nfrom diffusers.hooks import apply_group_offloading\r\nfrom diffusers.utils import export_to_video\r\n\r\n# Load the pipeline\r\nonload_device = torch.device(\"cuda\")\r\noffload_device = torch.device(\"cpu\")\r\npipe = CogVideoXPipeline.from_pretrained(\"THUDM/CogVideoX-5b\", torch_dtype=torch.bfloat16)\r\n\r\n# For any other model implementations, the apply_group_offloading function can be used\r\napply_group_offloading(pipe.text_encoder, onload_device=onload_device, offload_type=\"block_level\", num_blocks_per_group=2)\r\n```\r\n\r\n</details>\r\n    \r\n\r\n## Remote Components\r\n\r\nRemote components are an experimental feature designed to offload memory-intensive steps of the inference pipeline to remote endpoints. The initial implementation focuses primarily on VAE decoding operations. Below are the currently supported model endpoints:\r\n\r\n| Model               | Endpoint                                                            | Model                                |\r\n|---------------------|---------------------------------------------------------------------|--------------------------------------|\r\n| Stable Diffusion v1 | https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud    | stabilityai/sd-vae-ft-mse            |\r\n| Stable Diffusion XL | https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud    | madebyollin/sdxl-vae-fp16-fix          |\r\n| Flux                | https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud    | black-forest-labs/FLUX.1-schnell       |\r\n| HunyuanVideo        | https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud    | hunyuanvideo-community/HunyuanVideo   |\r\n\r\n\r\nThis is an example of using remote decoding with the Hunyuan Video pipeline:\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nfrom diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel\r\n\r\nmodel_id = \"hunyuanvideo-community/HunyuanVideo\"\r\ntransformer = HunyuanVideoTransformer3DModel.from_pretrained(\r\n    model_id, subfolder=\"transformer\", torch_dtype=torch.bfloat16\r\n)\r\npipe = HunyuanVideoPipeline.from_pretrained(\r\n    model_id, transformer=transformer, vae=None, torch_dtype=torch.float16\r\n).to(\"cuda\")\r\n\r\nlatent = pipe(\r\n    prompt=\"A cat walks on the grass, realistic\",\r\n    height=320,\r\n    width=512,\r\n    num_frames=61,\r\n    num_inference_steps=30,\r\n    output_type=\"latent\",\r\n).frames\r\n\r\nvideo = remote_decode(\r\n    endpoint=\"https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/\",\r\n    tensor=latent,\r\n    output_type=\"mp4\",\r\n)\r\n\r\nif isinstance(video, bytes):\r\n    with open(\"video.mp4\", \"wb\") as f:\r\n        f.write(video) \r\n```\r\n\r\n</details>\r\n\r\nCheck out [the docs](https://huggingface.co/docs/diffusers/main/en/hybrid_inference/overview) to know more.\r\n\r\n## Introducing Cached Inference for DiTs\r\n\r\nCached Inference for Diffusion Transformer models is a performance optimization that significantly accelerates the denoising process by caching intermediate values. This technique reduces redundant computations across timesteps, resulting in faster generation with a slight dip in output quality.\r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/main/en/api/cache) to learn more about the available caching methods.\r\n\r\n**Pyramind Attention Broadcast**\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nimport torch\r\nfrom diffusers import CogVideoXPipeline, PyramidAttentionBroadcastConfig\r\n\r\npipe = CogVideoXPipeline.from_pretrained(\"THUDM/CogVideoX-5b\", torch_dtype=torch.bfloat16)\r\npipe.to(\"cuda\")\r\n\r\nconfig = PyramidAttentionBroadcastConfig(\r\n    spatial_attention_block_skip_range=2,\r\n    spatial_attention_timestep_skip_range=(100, 800),\r\n    current_timestep_callback=lambda: pipe.current_timestep,\r\n)\r\npipe.transformer.enable_cache(config)\r\n```\r\n\r\n</details>\r\n\r\n**FasterCache**\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nimport torch\r\nfrom diffusers import CogVideoXPipeline, FasterCacheConfig\r\n\r\npipe = CogVideoXPipeline.from_pretrained(\"THUDM/CogVideoX-5b\", torch_dtype=torch.bfloat16)\r\npipe.to(\"cuda\")\r\n\r\nconfig = FasterCacheConfig(\r\n        spatial_attention_block_skip_range=2,\r\n        spatial_attention_timestep_skip_range=(-1, 901),\r\n        unconditional_batch_skip_range=2,\r\n        attention_weight_callback=lambda _: 0.5,\r\n        is_guidance_distilled=True,\r\n)\r\npipe.transformer.enable_cache(config)\r\n```\r\n\r\n</details>\r\n    \r\n\r\n## Quantization\r\n\r\n### Quanto Backend\r\n\r\nDiffusers now has support for the [Quanto quantization backend](https://huggingface.co/docs/diffusers/main/en/quantization/quanto), which provides `float8` , `int8` , `int4` and `int2` quantization dtypes.  \r\n\r\n```python\r\nimport torch\r\nfrom diffusers import FluxTransformer2DModel, QuantoConfig\r\n\r\nmodel_id = \"black-forest-labs/FLUX.1-dev\"\r\nquantization_config = QuantoConfig(weights_dtype=\"float8\")\r\ntransformer = FluxTransformer2DModel.from_pretrained(\r\n      model_id,\r\n      subfolder=\"transformer\",\r\n      quantization_config=quantization_config,\r\n      torch_dtype=torch.bfloat16,\r\n)\r\n```\r\n\r\nQuanto `int8` models are also compatible with `torch.compile` :\r\n\r\n<details>\r\n<summary>Code</summary>\r\n\r\n```py\r\nimport torch\r\nfrom diffusers import FluxTransformer2DModel, QuantoConfig\r\n\r\nmodel_id = \"black-forest-labs/FLUX.1-dev\"\r\nquantization_config = QuantoConfig(weights_dtype=\"float8\")\r\ntransformer = FluxTransformer2DModel.from_pretrained(\r\n      model_id,\r\n      subfolder=\"transformer\",\r\n      quantization_config=quantization_config,\r\n      torch_dtype=torch.bfloat16,\r\n)\r\ntransformer.compile()\r\n```\r\n\r\n</details>    \r\n\r\n### Improved loading for `uintx` TorchAO checkpoints with `torch>=2.6`\r\n\r\nTorchAO checkpoints currently have to be serialized using pickle. For some quantization dtypes using the `uintx` format, such as `uint4wo` this involves saving subclassed TorchAO Tensor objects in the model file. This made loading the models directly with Diffusers a bit tricky since we do not allow deserializing artbitary Python objects from pickle files.    \r\n\r\nTorch 2.6 allows adding expected Tensors to torch safe globals, which lets us directly load TorchAO checkpoints with these objects. \r\n\r\n```diff\r\n- state_dict = torch.load(\"/path/to/flux_uint4wo/diffusion_pytorch_model.bin\", weights_only=False, map_location=\"cpu\")\r\n- with init_empty_weights():\r\n-     transformer = FluxTransformer2DModel.from_config(\"/path/to/flux_uint4wo/config.json\")\r\n- transformer.load_state_dict(state_dict, strict=True, assign=True)\r\n+ transformer = FluxTransformer2DModel.from_pretrained(\"/path/to/flux_uint4wo/\")  \r\n```\r\n\r\n## LoRAs\r\n\r\nWe have shipped a couple of improvements on the LoRA front in this release.\r\n\r\n**🚨 Improved coverage for loading non-diffusers LoRA checkpoints for Flux**\r\n\r\nTake note of the breaking change introduced in [this PR](https://github.com/huggingface/diffusers/pull/10985) 🚨 We suggest you upgrade your `peft` installation to the latest version - `pip install -U peft` especially when dealing with Flux LoRAs.\r\n\r\n**`torch.compile()` support when hotswapping LoRAs without triggering recompilation**\r\n\r\nA common use case when serving multiple adapters is to load one adapter first, generate images, load another adapter, generate more images, load another adapter, etc. This workflow normally requires calling [load_lora_weights()](https://huggingface.co/docs/diffusers/v0.33.0/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights), set_adapters(), and possibly [delete_adapters()](https://huggingface.co/docs/diffusers/v0.33.0/en/api/loaders/peft#diffusers.loaders.PeftAdapterMixin.delete_adapters) to save memory. Moreover, if the model is compiled using torch.compile, performing these steps requires recompilation, which takes time.\r\n\r\nTo better support this common workflow, you can “hotswap” a LoRA adapter, to avoid accumulating memory and in some cases, recompilation. It requires an adapter to already be loaded, and the new adapter weights are swapped in-place for the existing adapter.\r\n\r\nCheck out the [docs](https://huggingface.co/docs/diffusers/en/using-diffusers/loading_adapters#hotswapping-lora-adapters) to learn more about this feature.\r\n\r\nThe other major change is the support for\r\n\r\n- Loading LoRAs into quantized model checkpoints\r\n\r\n## `dtype` Maps for Pipelines\r\n\r\nSince various pipelines require their components to run in different compute dtypes, we now support passing a dtype map when initializing a pipeline:\r\n\r\n```python\r\nfrom diffusers import HunyuanVideoPipeline\r\nimport torch\r\n\r\npipe = HunyuanVideoPipeline.from_pretrained(\r\n    \"hunyuanvideo-community/HunyuanVideo\",\r\n    torch_dtype={\"transformer\": torch.bfloat16, \"default\": torch.float16},\r\n)\r\nprint(pipe.transformer.dtype, pipe.vae.dtype)  # (torch.bfloat16, torch.float16)\r\n```\r\n\r\n## AutoModel\r\n\r\nThis release includes an AutoModel object similar to the one found in `transformers` that automatically fetches the appropriate model class for the provided repo. \r\n\r\n```python\r\nfrom diffusers import AutoModel\r\n\r\nunet = AutoModel.from_pretrained(\"runwayml/stable-diffusion-v1-5\", subfolder=\"unet\")\r\n```\r\n\r\n## All commits\r\n\r\n* [Sana 4K] Add vae tiling option to avoid OOM  by @leisuzz in #10583\r\n* IP-Adapter for `StableDiffusion3Img2ImgPipeline`  by @guiyrt in #10589\r\n* [DC-AE, SANA] fix SanaMultiscaleLinearAttention apply_quadratic_attention bf16  by @chenjy2003 in #10595\r\n* Move buffers to device  by @hlky in #10523\r\n* [Docs] Update SD3 ip_adapter model_id to diffusers checkpoint  by @guiyrt in #10597\r\n* Scheduling fixes on MPS  by @hlky in #10549\r\n* [Docs] Add documentation about using ParaAttention to optimize FLUX and HunyuanVideo  by @chengzeyi in #10544\r\n* NPU adaption for RMSNorm  by @leisuzz in #10534\r\n* implementing flux on TPUs with ptxla  by @entrpn in #10515\r\n* [core] ConsisID  by @SHYuanBest in #10140\r\n* [training] set rest of the blocks with `requires_grad` False.  by @sayakpaul in #10607\r\n* chore: remove redundant words  by @sunxunle in #10609\r\n* bugfix for npu not support float64  by @baymax591 in #10123\r\n* [chore] change licensing to 2025 from 2024.  by @sayakpaul in #10615\r\n* Enable dreambooth lora finetune example on other devices  by @jiqing-feng in #10602\r\n* Remove the FP32 Wrapper when evaluating  by @lmxyy in #10617\r\n* [tests] make tests device-agnostic (part 3)   by @faaany in #10437\r\n* fix offload gpu tests etc  by @yiyixuxu in #10366\r\n* Remove cache migration script  by @Wauplin in #10619\r\n* [core] Layerwise Upcasting  by @a-r-r-o-w in #10347\r\n* Improve TorchAO error message  by @a-r-r-o-w in #10627\r\n* [CI] Update HF_TOKEN in all workflows  by @DN6 in #10613\r\n* add onnxruntime-migraphx as part of check for onnxruntime in import_utils.py  by @kahmed10 in #10624\r\n* [Tests] modify the test slices for the failing flax test  by @sayakpaul in #10630\r\n* [docs] fix image path in para attention docs  by @sayakpaul in #10632\r\n* [docs] uv installation  by @stevhliu in #10622\r\n* width and height are mixed-up  by @raulc0399 in #10629\r\n* Add IP-Adapter example to Flux docs  by @hlky in #10633\r\n* removing redundant requires_grad = False  by @YanivDorGalron in #10628\r\n* [chore] add a script to extract loras from full fine-tuned models  by @sayakpaul in #10631\r\n* Add pipeline_stable_diffusion_xl_attentive_eraser  by @Anonym0u3 in #10579\r\n* NPU Adaption for Sanna  by @leisuzz in #10409\r\n* Add sigmoid scheduler in `scheduling_ddpm.py` docs  by @JacobHelwig in #10648\r\n* create a script to train autoencoderkl  by @lavinal712 in #10605\r\n* Add community pipeline for semantic guidance for FLUX  by @Marlon154 in #10610\r\n* ControlNet Union controlnet_conditioning_scale for multiple control inputs  by @hlky in #10666\r\n* [training] Convert to ImageFolder script  by @hlky in #10664\r\n* Add provider_options to OnnxRuntimeModel  by @hlky in #10661\r\n* fix check_inputs func in LuminaText2ImgPipeline  by @victolee0 in #10651\r\n* SDXL ControlNet Union pipelines, make control_image argument immutible  by @Teriks in #10663\r\n* Revert RePaint scheduler 'fix'  by @GiusCat in #10644\r\n* [core] Pyramid Attention Broadcast  by @a-r-r-o-w in #9562\r\n* [fix] refer use_framewise_encoding on AutoencoderKLHunyuanVideo._encode  by @hanchchch in #10600\r\n* Refactor gradient checkpointing  by @a-r-r-o-w in #10611\r\n* [Tests] conditionally check `fp8_e4m3_bf16_max_memory < fp8_e4m3_fp32_max_memory`   by @sayakpaul in #10669\r\n* Fix pipeline dtype unexpected change when using SDXL reference community pipelines in float16 mode  by @dimitribarbot in #10670\r\n* [tests] update llamatokenizer in hunyuanvideo tests  by @sayakpaul in #10681\r\n* support StableDiffusionAdapterPipeline.from_single_file  by @Teriks in #10552\r\n* fix(hunyuan-video): typo in height and width input check  by @badayvedat in #10684\r\n* [FIX] check_inputs function in Auraflow Pipeline  by @SahilCarterr in #10678\r\n* Fix enable memory efficient attention on ROCm  by @tenpercent in #10564\r\n* Fix inconsistent random transform in instruct pix2pix  by @Luvata in #10698\r\n* feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling  by @badayvedat in #10699\r\n* Fixed grammar in \"write_own_pipeline\" readme  by @N0-Flux-given in #10706\r\n* Fix Documentation about Image-to-Image Pipeline  by @ParagEkbote in #10704\r\n* [bitsandbytes] Simplify bnb int8 dequant  by @sayakpaul in #10401\r\n* Fix train_text_to_image.py --help  by @nkthiebaut in #10711\r\n* Notebooks for Community Scripts-6  by @ParagEkbote in #10713\r\n* [Fix] Type Hint in from_pretrained() to Ensure Correct Type Inference  by @SahilCarterr in #10714\r\n* add provider_options in from_pretrained  by @xieofxie in #10719\r\n* [Community] Enhanced `Model Search`  by @suzukimain in #10417\r\n* [bugfix] NPU Adaption for Sana  by @leisuzz in #10724\r\n* Quantized Flux with IP-Adapter  by @hlky in #10728\r\n* EDMEulerScheduler accept sigmas, add final_sigmas_type  by @hlky in #10734\r\n* [LoRA] fix peft state dict parsing  by @sayakpaul in #10532\r\n* Add `Self` type hint to `ModelMixin`'s `from_pretrained`  by @hlky in #10742\r\n* [Tests] Test layerwise casting with training  by @sayakpaul in #10765\r\n* speedup hunyuan encoder causal mask generation  by @dabeschte in #10764\r\n* [CI] Fix Truffle Hog failure  by @DN6 in #10769\r\n* Add OmniGen  by @staoxiao in #10148\r\n* feat: new community mixture_tiling_sdxl pipeline for SDXL  by @elismasilva in #10759\r\n* Add support for lumina2  by @zhuole1025 in #10642\r\n* Refactor OmniGen  by @a-r-r-o-w in #10771\r\n* Faster set_adapters  by @Luvata in #10777\r\n* [Single File] Add Single File support for Lumina Image 2.0 Transformer  by @DN6 in #10781\r\n* Fix `use_lu_lambdas` and `use_karras_sigmas` with `beta_schedule=squaredcos_cap_v2` in `DPMSolverMultistepScheduler`  by @hlky in #10740\r\n* `MultiControlNetUnionModel` on SDXL  by @guiyrt in #10747\r\n* fix: [Community pipeline] Fix flattened elements on image   by @elismasilva in #10774\r\n* make tensors contiguous before passing to safetensors  by @faaany in #10761\r\n* Disable PEFT input autocast when using fp8 layerwise casting  by @a-r-r-o-w in #10685\r\n* Update FlowMatch docstrings to mention correct output classes  by @a-r-r-o-w in #10788\r\n* Refactor CogVideoX transformer forward  by @a-r-r-o-w in #10789\r\n* Module Group Offloading  by @a-r-r-o-w in #10503\r\n* Update Custom Diffusion Documentation for Multiple Concept Inference to resolve issue #10791  by @puhuk in #10792\r\n* [FIX] check_inputs function in lumina2  by @SahilCarterr in #10784\r\n* follow-up refactor on lumina2  by @yiyixuxu in #10776\r\n* CogView4 (supports different length c and uc)  by @zRzRzRzRzRzRzR in #10649\r\n* typo fix  by @YanivDorGalron in #10802\r\n* Extend Support for callback_on_step_end for AuraFlow and LuminaText2Img Pipelines  by @ParagEkbote in #10746\r\n* [chore] update notes generation spaces  by @sayakpaul in #10592\r\n* [LoRA] improve lora support for flux.  by @sayakpaul in #10810\r\n* Fix max_shift value in flux and related functions to 1.15 (issue #10675)  by @puhuk in #10807\r\n* [docs] add missing entries to the lora docs.  by @sayakpaul in #10819\r\n* DiffusionPipeline mixin `to`+FromOriginalModelMixin/FromSingleFileMixin `from_single_file` type hint  by @hlky in #10811\r\n* [LoRA] make `set_adapters()` robust on silent failures.  by @sayakpaul in #9618\r\n* [FEAT] Model loading refactor  by @SunMarc in #10604\r\n* [misc] feat: introduce a style bot.  by @sayakpaul in #10274\r\n* Remove print statements  by @a-r-r-o-w in #10836\r\n* [tests] use proper gemma class and config in lumina2 tests.  by @sayakpaul in #10828\r\n* [LoRA] add LoRA support to Lumina2 and fine-tuning script  by @sayakpaul in #10818\r\n* [Utils] add utilities for checking if certain utilities are properly documented  by @sayakpaul in #7763\r\n* Add missing `isinstance` for arg checks in GGUFParameter  by @AstraliteHeart in #10834\r\n* [tests] test `encode_prompt()` in isolation  by @sayakpaul in #10438\r\n* store activation cls instead of function  by @SunMarc in #10832\r\n* fix: support transformer models' `generation_config` in pipeline  by @JeffersonQin in #10779\r\n* Notebooks for Community Scripts-7  by @ParagEkbote in #10846\r\n* [CI] install accelerate transformers from `main`  by @sayakpaul in #10289\r\n* [CI] run fast gpu tests conditionally on pull requests.  by @sayakpaul in #10310\r\n* SD3 IP-Adapter runtime checkpoint conversion  by @guiyrt in #10718\r\n* Some consistency-related fixes for HunyuanVideo  by @a-r-r-o-w in #10835\r\n* SkyReels Hunyuan T2V & I2V  by @a-r-r-o-w in #10837\r\n* fix: run tests from a pr workflow.  by @sayakpaul in #9696\r\n* [chore] template for remote vae.  by @sayakpaul in #10849\r\n* fix remote vae template  by @sayakpaul in #10852\r\n* [CI] Fix incorrectly named test module for Hunyuan DiT  by @DN6 in #10854\r\n* [CI] Update always test Pipelines list in Pipeline fetcher  by @DN6 in #10856\r\n* `device_map` in `load_model_dict_into_meta`  by @hlky in #10851\r\n* [Fix] Docs overview.md  by @SahilCarterr in #10858\r\n* remove format check for safetensors file  by @SunMarc in #10864\r\n* [docs] LoRA support  by @stevhliu in #10844\r\n* Comprehensive type checking for `from_pretrained` kwargs  by @guiyrt in #10758\r\n* Fix `torch_dtype` in Kolors text encoder with `transformers` v4.49  by @hlky in #10816\r\n* [LoRA] restrict certain keys to be checked for peft config update.  by @sayakpaul in #10808\r\n* Add SD3 ControlNet to AutoPipeline  by @hlky in #10888\r\n* [docs] Update prompt weighting docs  by @stevhliu in #10843\r\n* [docs] Flux group offload  by @stevhliu in #10847\r\n* [Fix] fp16 unscaling in train_dreambooth_lora_sdxl  by @SahilCarterr in #10889\r\n* [docs] Add CogVideoX Schedulers  by @a-r-r-o-w in #10885\r\n* [chore] correct qk norm list.  by @sayakpaul in #10876\r\n* [Docs] Fix toctree sorting   by @DN6 in #10894\r\n* [refactor] SD3 docs & remove additional code  by @a-r-r-o-w in #10882\r\n* [refactor] Remove additional Flux code  by @a-r-r-o-w in #10881\r\n* [CI] Improvements to conditional GPU PR tests  by @DN6 in #10859\r\n* Multi IP-Adapter for Flux pipelines  by @guiyrt in #10867\r\n* Fix Callback Tensor Inputs of the SDXL Controlnet Inpaint and Img2img Pipelines are missing \"controlnet_image\".  by @CyberVy in #10880\r\n* Security fix  by @ydshieh in #10905\r\n* Marigold Update: v1-1 models, Intrinsic Image Decomposition pipeline, documentation  by @toshas in #10884\r\n* [Tests] fix: lumina2 lora fuse_nan test  by @sayakpaul in #10911\r\n* Fix Callback Tensor Inputs of the SD Controlnet Pipelines are missing some elements.  by @CyberVy in #10907\r\n* [CI] Fix Fast GPU tests on PR  by @DN6 in #10912\r\n* [CI] Fix for failing IP Adapter test in Fast GPU PR tests  by @DN6 in #10915\r\n* Experimental per control type scale for ControlNet Union  by @hlky in #10723\r\n* [style bot] improve security for the stylebot.  by @sayakpaul in #10908\r\n* [CI] Update Stylebot Permissions  by @DN6 in #10931\r\n* [Alibaba Wan Team] continue on #10921 Wan2.1  by @yiyixuxu in #10922\r\n* Support IPAdapter for more Flux pipelines  by @hlky in #10708\r\n* Add `remote_decode` to `remote_utils`  by @hlky in #10898\r\n* Update VAE Decode endpoints  by @hlky in #10939\r\n* [chore] fix-copies to flux pipelines  by @sayakpaul in #10941\r\n* [Tests] Remove more encode prompts tests  by @sayakpaul in #10942\r\n* Add EasyAnimateV5.1 text-to-video, image-to-video, control-to-video generation model   by @bubbliiiing in #10626\r\n* Fix SD2.X clip single file load projection_dim  by @Teriks in #10770\r\n* add from_single_file to animatediff   by @<NOT FOUND> in #10924\r\n* Add Example of IPAdapterScaleCutoffCallback to Docs  by @ParagEkbote in #10934\r\n* Update pipeline_cogview4.py  by @zRzRzRzRzRzRzR in #10944\r\n* Fix redundant prev_output_channel assignment in UNet2DModel  by @ahmedbelgacem in #10945\r\n* Improve load_ip_adapter RAM Usage  by @CyberVy in #10948\r\n* [tests] make tests device-agnostic (part 4)  by @faaany in #10508\r\n* Update evaluation.md  by @sayakpaul in #10938\r\n* [LoRA] feat: support non-diffusers lumina2 LoRAs.  by @sayakpaul in #10909\r\n* [Quantization]  support pass MappingType for TorchAoConfig  by @a120092009 in #10927\r\n* Fix the missing parentheses when calling is_torchao_available in quantization_config.py.  by @CyberVy in #10961\r\n* [LoRA] Support Wan  by @a-r-r-o-w in #10943\r\n* Fix incorrect seed initialization when args.seed is 0  by @azolotenkov in #10964\r\n* feat: add Mixture-of-Diffusers ControlNet Tile upscaler Pipeline for SDXL  by @elismasilva in #10951\r\n* [Docs] CogView4 comment fix  by @zRzRzRzRzRzRzR in #10957\r\n* update check_input for cogview4  by @yiyixuxu in #10966\r\n* Add VAE Decode endpoint slow test  by @hlky in #10946\r\n* [flux lora training] fix t5 training bug  by @linoytsaban in #10845\r\n* use style bot GH Action from `huggingface_hub`  by @hanouticelina in #10970\r\n* [train_dreambooth_lora.py] Fix the LR Schedulers when `num_train_epochs` is passed in a distributed training env  by @flyxiv in #10973\r\n* [tests] fix tests for save load components  by @sayakpaul in #10977\r\n* Fix loading OneTrainer Flux LoRA  by @hlky in #10978\r\n* fix default values of Flux guidance_scale in docstrings  by @catwell in #10982\r\n* [CI] remove synchornized.  by @sayakpaul in #10980\r\n* Bump jinja2 from 3.1.5 to 3.1.6 in /examples/research_projects/realfill  by @dependabot[bot] in #10984\r\n* Fix Flux Controlnet Pipeline _callback_tensor_inputs Missing Some Elements  by @CyberVy in #10974\r\n* [Single File] Add user agent to SF download requests.   by @DN6 in #10979\r\n* Add CogVideoX DDIM Inversion to Community Pipelines  by @LittleNyima in #10956\r\n* fix wan i2v pipeline bugs  by @yupeng1111 in #10975\r\n* Hunyuan I2V  by @a-r-r-o-w in #10983\r\n* Fix Graph Breaks When Compiling CogView4  by @chengzeyi in #10959\r\n* Wan VAE move scaling to pipeline  by @hlky in #10998\r\n* [LoRA] remove full key prefix from peft.  by @sayakpaul in #11004\r\n* [Single File] Add single file support for Wan T2V/I2V  by @DN6 in #10991\r\n* Add STG to community pipelines  by @kinam0252 in #10960\r\n* [LoRA] Improve copied from comments in the LoRA loader classes  by @sayakpaul in #10995\r\n* Fix for fetching variants only  by @DN6 in #10646\r\n* [Quantization] Add Quanto backend  by @DN6 in #10756\r\n* [Single File] Add single file loading for SANA Transformer  by @ishan-modi in #10947\r\n* [LoRA] Improve warning messages when LoRA loading becomes a no-op  by @sayakpaul in #10187\r\n* [LoRA] CogView4  by @a-r-r-o-w in #10981\r\n* [Tests] improve quantization tests by additionally measuring the inference memory savings  by @sayakpaul in #11021\r\n* [`Research Project`] Add AnyText: Multilingual Visual Text Generation And Editing  by @tolgacangoz in #8998\r\n* [Quantization] Allow loading TorchAO serialized Tensor objects with torch>=2.6   by @DN6 in #11018\r\n* fix: mixture tiling sdxl pipeline - adjust gerating time_ids & embeddings   by @elismasilva in #11012\r\n* [LoRA] support wan i2v loras from the world.  by @sayakpaul in #11025\r\n* Fix SD3 IPAdapter feature extractor  by @hlky in #11027\r\n* chore: fix help messages in advanced diffusion examples  by @wonderfan in #10923\r\n* Fix missing **kwargs in lora_pipeline.py  by @CyberVy in #11011\r\n* Fix for multi-GPU WAN inference  by @AmericanPresidentJimmyCarter in #10997\r\n* [Refactor] Clean up import utils boilerplate  by @DN6 in #11026\r\n* Use `output_size` in `repeat_interleave`  by @hlky in #11030\r\n* [hybrid inference 🍯🐝] Add VAE encode  by @hlky in #11017\r\n* Wan Pipeline scaling fix, type hint warning, multi generator fix  by @hlky in #11007\r\n* [LoRA] change to warning from info when notifying the users about a LoRA no-op  by @sayakpaul in #11044\r\n* Rename Lumina(2)Text2ImgPipeline -> Lumina(2)Pipeline  by @hlky in #10827\r\n* making ```formatted_images``` initialization compact  by @YanivDorGalron in #10801\r\n* Fix aclnnRepeatInterleaveIntWithDim error on NPU for get_1d_rotary_pos_embed  by @ZhengKai91 in #10820\r\n* [Tests] restrict memory tests for quanto for certain schemes.  by @sayakpaul in #11052\r\n* [LoRA] feat: support non-diffusers wan t2v loras.  by @sayakpaul in #11059\r\n* [examples/controlnet/train_controlnet_sd3.py] Fixes #11050 - Cast prompt_embeds and pooled_prompt_embeds to weight_dtype to prevent dtype mismatch  by @andjoer in #11051\r\n* reverts accidental change that removes attn_mask in attn. Improves fl…  by @entrpn in #11065\r\n* Fix deterministic issue when getting pipeline dtype and device  by @dimitribarbot in #10696\r\n* [Tests] add requires peft decorator.  by @sayakpaul in #11037\r\n* CogView4 Control Block  by @zRzRzRzRzRzRzR in #10809\r\n* [CI] pin transformers version for benchmarking.  by @sayakpaul in #11067\r\n* Fix Wan I2V Quality  by @chengzeyi in #11087\r\n* LTX 0.9.5  by @a-r-r-o-w in #10968\r\n* make PR GPU tests conditioned on styling.  by @sayakpaul in #11099\r\n* Group offloading improvements  by @a-r-r-o-w in #11094\r\n* Fix pipeline_flux_controlnet.py  by @co63oc in #11095\r\n* update readme instructions.  by @entrpn in #11096\r\n* Resolve stride mismatch in UNet's ResNet to support Torch DDP  by @jinc7461 in #11098\r\n* Fix Group offloading behaviour when using streams  by @a-r-r-o-w in #11097\r\n* Quality options in `export_to_video`  by @hlky in #11090\r\n* [CI] uninstall deps properly from pr gpu tests.  by @sayakpaul in #11102\r\n* [BUG] Fix Autoencoderkl train script  by @lavinal712 in #11113\r\n* [Wan LoRAs] make T2V LoRAs compatible with Wan I2V  by @linoytsaban in #11107\r\n* [tests] enable bnb tests on xpu  by @faaany in #11001\r\n* [fix bug] PixArt inference_steps=1  by @lawrence-cj in #11079\r\n* Flux with Remote Encode  by @hlky in #11091\r\n* [tests] make cuda only tests device-agnostic   by @faaany in #11058\r\n* Provide option to reduce CPU RAM usage in Group Offload  by @DN6 in #11106\r\n* remove F.rms_norm for now  by @yiyixuxu in #11126\r\n* Notebooks for Community Scripts-8  by @ParagEkbote in #11128\r\n* fix _callback_tensor_inputs of sd controlnet inpaint pipeline missing some elements  by @CyberVy in #11073\r\n* [core] FasterCache  by @a-r-r-o-w in #10163\r\n* add sana-sprint  by @yiyixuxu in #11074\r\n* Don't override `torch_dtype` and don't use when `quantization_config` is set  by @hlky in #11039\r\n* Update README and example code for AnyText usage  by @tolgacangoz in #11028\r\n* Modify the implementation of retrieve_timesteps in CogView4-Control.  by @zRzRzRzRzRzRzR in #11125\r\n* [fix SANA-Sprint]  by @lawrence-cj in #11142\r\n* New HunyuanVideo-I2V  by @a-r-r-o-w in #11066\r\n* [doc] Fix Korean Controlnet Train doc  by @flyxiv in #11141\r\n* Improve information about group offloading and layerwise casting  by @a-r-r-o-w in #11101\r\n* add a timestep scale for sana-sprint teacher model  by @lawrence-cj in #11150\r\n* [Quantization] dtype fix for GGUF + fix BnB tests  by @DN6 in #11159\r\n* Set self._hf_peft_config_loaded to True when LoRA is loaded using `load_lora_adapter` in PeftAdapterMixin class  by @kentdan3msu in #11155\r\n* WanI2V encode_image  by @hlky in #11164\r\n* [Docs] Update Wan Docs with memory optimizations  by @DN6 in #11089\r\n* Fix LatteTransformer3DModel dtype mismatch with enable_temporal_attentions  by @hlky in #11139\r\n* Raise warning and round down if Wan num_frames is not 4k + 1  by @a-r-r-o-w in #11167\r\n* [Docs] Fix environment variables in `installation.md`  by @remarkablemark in #11179\r\n* Add `latents_mean` and `latents_std` to `SDXLLongPromptWeightingPipeline`  by @hlky in #11034\r\n* Bug fix in LTXImageToVideoPipeline.prepare_latents() when latents is already set  by @kakukakujirori in #10918\r\n* [tests] no hard-coded cuda   by @faaany in #11186\r\n* [WIP] Add Wan Video2Video  by @DN6 in #11053\r\n* map BACKEND_RESET_MAX_MEMORY_ALLOCATED to reset_peak_memory_stats on XPU  by @yao-matrix in #11191\r\n* fix autocast  by @jiqing-feng in #11190\r\n* fix: for checking mandatory and optional pipeline components  by @elismasilva in #11189\r\n* remove unnecessary call to `F.pad`  by @bm-synth in #10620\r\n* allow models to run with a user-provided dtype map instead of a single dtype  by @hlky in #10301\r\n* [tests] HunyuanDiTControlNetPipeline inference precision issue on XPU  by @faaany in #11197\r\n* Revert `save_model` in ModelMixin save_pretrained and use safe_serialization=False in test  by @hlky in #11196\r\n* [docs] `torch_dtype` map  by @hlky in #11194\r\n* Fix enable_sequential_cpu_offload in CogView4Pipeline  by @hlky in #11195\r\n* SchedulerMixin from_pretrained and ConfigMixin Self type annotation  by @hlky in #11192\r\n* Update import_utils.py  by @Lakshaysharma048 in #10329\r\n* Add CacheMixin to Wan and LTX Transformers  by @DN6 in #11187\r\n* feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline  by @elismasilva in #11188\r\n* [Model Card] standardize advanced diffusion training sdxl lora  by @chiral-carbon in #7615\r\n* Change KolorsPipeline LoRA Loader to StableDiffusion  by @BasileLewan in #11198\r\n* Update Style Bot workflow  by @hanouticelina in #11202\r\n* Fixed requests.get function call by adding timeout parameter.  by @kghamilton89 in #11156\r\n* Fix Single File loading for LTX VAE   by @DN6 in #11200\r\n* [feat]Add strength in flux_fill pipeline (denoising strength for fluxfill)  by @Suprhimp in #10603\r\n* [LTX0.9.5] Refactor `LTXConditionPipeline` for text-only conditioning  by @tolgacangoz in #11174\r\n* Add Wan with STG as a community pipeline  by @Ednaordinary in #11184\r\n* Add missing MochiEncoder3D.gradient_checkpointing attribute  by @mjkvaak-amd in #11146\r\n* enable 1 case on XPU  by @yao-matrix in #11219\r\n* ensure dtype match between diffused latents and vae weights  by @heyalexchoi in #8391\r\n* [docs] MPS update  by @stevhliu in #11212\r\n* Add support to pass image embeddings to the WAN I2V pipeline.  by @goiri in #11175\r\n* [train_controlnet.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env  by @Bhavay-2001 in #8461\r\n* [Training] Better image interpolation in training scripts  by @asomoza in #11206\r\n* [LoRA] Implement hot-swapping of LoRA  by @BenjaminBossan in #9453\r\n* introduce compute arch specific expectations and fix test_sd3_img2img_inference failure  by @yao-matrix in #11227\r\n* [Flux LoRA] fix issues in flux lora scripts  by @linoytsaban in #11111\r\n* Flux quantized with lora  by @hlky in #10990\r\n* [feat] implement `record_stream` when using CUDA streams during group offloading  by @sayakpaul in #11081\r\n* [bistandbytes] improve replacement warnings for bnb  by @sayakpaul in #11132\r\n* minor update to sana sprint docs.  by @sayakpaul in #11236\r\n* [docs] minor updates to dtype map docs.  by @sayakpaul in #11237\r\n* [LoRA] support more comyui loras for Flux 🚨  by @sayakpaul in #10985\r\n* fix: SD3 ControlNet validation so that it runs on a A100.  by @sayakpaul in #11238\r\n* AudioLDM2 Fixes  by @hlky in #11244\r\n* AutoModel  by @hlky in #11115\r\n* fix FluxReduxSlowTests::test_flux_redux_inference case failure on XPU  by @yao-matrix in #11245\r\n* [docs] AutoModel  by @hlky in #11250\r\n* Update Ruff to latest Version  by @DN6 in #10919\r\n* fix flux controlnet bug  by @free001style in #11152\r\n* fix timeout constant  by @sayakpaul in #11252\r\n* fix consisid imports  by @sayakpaul in #11254\r\n* Release: v0.33.0 by @sayakpaul (direct commit on v0.33.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @guiyrt\r\n    * IP-Adapter for `StableDiffusion3Img2ImgPipeline` (#10589)\r\n    * [Docs] Update SD3 ip_adapter model_id to diffusers checkpoint (#10597)\r\n    * `MultiControlNetUnionModel` on SDXL (#10747)\r\n    * SD3 IP-Adapter runtime checkpoint conversion (#10718)\r\n    * Comprehensive type checking for `from_pretrained` kwargs (#10758)\r\n    * Multi IP-Adapter for Flux pipelines (#10867)\r\n* @chengzeyi\r\n    * [Docs] Add documentation about using ParaAttention to optimize FLUX and HunyuanVideo (#10544)\r\n    * Fix Graph Breaks When Compiling CogView4 (#10959)\r\n    * Fix Wan I2V Quality (#11087)\r\n* @entrpn\r\n    * implementing flux on TPUs with ptxla (#10515)\r\n    * reverts accidental change that removes attn_mask in attn. Improves fl… (#11065)\r\n    * update readme instructions. (#11096)\r\n* @SHYuanBest\r\n    * [core] ConsisID (#10140)\r\n* @faaany\r\n    * [tests] make tests device-agnostic (part 3)  (#10437)\r\n    * make tensors contiguous before passing to safetensors (#10761)\r\n    * [tests] make tests device-agnostic (part 4) (#10508)\r\n    * [tests] enable bnb tests on xpu (#11001)\r\n    * [tests] make cuda only tests device-agnostic  (#11058)\r\n    * [tests] no hard-coded cuda  (#11186)\r\n    * [tests] HunyuanDiTControlNetPipeline inference precision issue on XPU (#11197)\r\n* @yiyixuxu\r\n    * fix offload gpu tests etc (#10366)\r\n    * follow-up refactor on lumina2 (#10776)\r\n    * [Alibaba Wan Team] continue on #10921 Wan2.1 (#10922)\r\n    * update check_input for cogview4 (#10966)\r\n    * remove F.rms_norm for now (#11126)\r\n    * add sana-sprint (#11074)\r\n* @DN6\r\n    * [CI] Update HF_TOKEN in all workflows (#10613)\r\n    * [CI] Fix Truffle Hog failure (#10769)\r\n    * [Single File] Add Single File support for Lumina Image 2.0 Transformer (#10781)\r\n    * [CI] Fix incorrectly named test module for Hunyuan DiT (#10854)\r\n    * [CI] Update always test Pipelines list in Pipeline fetcher (#10856)\r\n    * [Docs] Fix toctree sorting  (#10894)\r\n    * [CI] Improvements to conditional GPU PR tests (#10859)\r\n    * [CI] Fix Fast GPU tests on PR (#10912)\r\n    * [CI] Fix for failing IP Adapter test in Fast GPU PR tests (#10915)\r\n    * [CI] Update Stylebot Permissions (#10931)\r\n    * [Single File] Add user agent to SF download requests.  (#10979)\r\n    * [Single File] Add single file support for Wan T2V/I2V (#10991)\r\n    * Fix for fetching variants only (#10646)\r\n    * [Quantization] Add Quanto backend (#10756)\r\n    * [Quantization] Allow loading TorchAO serialized Tensor objects with torch>=2.6  (#11018)\r\n    * [Refactor] Clean up import utils boilerplate (#11026)\r\n    * Provide option to reduce CPU RAM usage in Group Offload (#11106)\r\n    * [Quantization] dtype fix for GGUF + fix BnB tests (#11159)\r\n    * [Docs] Update Wan Docs with memory optimizations (#11089)\r\n    * [WIP] Add Wan Video2Video (#11053)\r\n    * Add CacheMixin to Wan and LTX Transformers (#11187)\r\n    * Fix Single File loading for LTX VAE  (#11200)\r\n    * Update Ruff to latest Version (#10919)\r\n* @Anonym0u3\r\n    * Add pipeline_stable_diffusion_xl_attentive_eraser (#10579)\r\n* @lavinal712\r\n    * create a script to train autoencoderkl (#10605)\r\n    * [BUG] Fix Autoencoderkl train script (#11113)\r\n* @Marlon154\r\n    * Add community pipeline for semantic guidance for FLUX (#10610)\r\n* @ParagEkbote\r\n    * Fix Documentation about Image-to-Image Pipeline (#10704)\r\n    * Notebooks for Community Scripts-6 (#10713)\r\n    * Extend Support for callback_on_step_end for AuraFlow and LuminaText2Img Pipelines (#10746)\r\n    * Notebooks for Community Scripts-7 (#10846)\r\n    * Add Example of IPAdapterScaleCutoffCallback to Docs (#10934)\r\n    * Notebooks for Community Scripts-8 (#11128)\r\n* @suzukimain\r\n    * [Community] Enhanced `Model Search` (#10417)\r\n* @staoxiao\r\n    * Add OmniGen (#10148)\r\n* @elismasilva\r\n    * feat: new community mixture_tiling_sdxl pipeline for SDXL (#10759)\r\n    * fix: [Community pipeline] Fix flattened elements on image  (#10774)\r\n    * feat: add Mixture-of-Diffusers ControlNet Tile upscaler Pipeline for SDXL (#10951)\r\n    * fix: mixture tiling sdxl pipeline - adjust gerating time_ids & embeddings  (#11012)\r\n    * fix: for checking mandatory and optional pipeline components (#11189)\r\n    * feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline (#11188)\r\n* @zhuole1025\r\n    * Add support for lumina2 (#10642)\r\n* @zRzRzRzRzRzRzR\r\n    * CogView4 (supports different length c and uc) (#10649)\r\n    * Update pipeline_cogview4.py (#10944)\r\n    * [Docs] CogView4 comment fix (#10957)\r\n    * CogView4 Control Block (#10809)\r\n    * Modify the implementation of retrieve_timesteps in CogView4-Control. (#11125)\r\n* @toshas\r\n    * Marigold Update: v1-1 models, Intrinsic Image Decomposition pipeline, documentation (#10884)\r\n* @bubbliiiing\r\n    * Add EasyAnimateV5.1 text-to-video, image-to-video, control-to-video generation model  (#10626)\r\n* @LittleNyima\r\n    * Add CogVideoX DDIM Inversion to Community Pipelines (#10956)\r\n* @kinam0252\r\n    * Add STG to community pipelines (#10960)\r\n* @tolgacangoz\r\n    * [`Research Project`] Add AnyText: Multilingual Visual Text Generation And Editing (#8998)\r\n    * Update README and example code for AnyText usage (#11028)\r\n    * [LTX0.9.5] Refactor `LTXConditionPipeline` for text-only conditioning (#11174)\r\n* @Ednaordinary\r\n    * Add Wan with STG as a community pipeline (#11184)","publishedAt":"2025-04-09T13:37:21.000Z","fetchedAt":"2026-04-07T17:27:25.723Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.33.0","media":[],"coverageCount":0},{"id":"rel_h6fVteyB5dOgeakqsDTLb","version":"v0.32.2","type":"feature","title":"v0.32.2","summary":"# Fixes for Flux Single File loading, LoRA loading for 4bit BnB Flux, Hunyuan Video \r\n\r\nThis patch release\r\n\r\n- Fixes a regression in loading Comfy UI...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"# Fixes for Flux Single File loading, LoRA loading for 4bit BnB Flux, Hunyuan Video \r\n\r\nThis patch release\r\n\r\n- Fixes a regression in loading Comfy UI format single file checkpoints for Flux\r\n- Fixes a regression in loading LoRAs with bitsandbytes 4bit quantized Flux models\r\n- Adds `unload_lora_weights` for Flux Control\r\n- Fixes a bug that prevents Hunyuan Video from running with batch size > 1\r\n- Allow Hunyuan Video to load LoRAs created from the original repository code \r\n\r\n## All commits\r\n* [Single File] Fix loading Flux Dev finetunes with Comfy Prefix  by @DN6 in #10545\r\n* [CI] Update HF Token on Fast GPU Model Tests by @DN6  #10570\r\n* [CI] Update HF Token in Fast GPU Tests by @DN6 #10568\r\n* Fix batch > 1 in HunyuanVideo  by @hlky in #10548\r\n* Fix HunyuanVideo produces NaN on PyTorch<2.5  by @hlky in #10482\r\n* Fix hunyuan video attention mask dim  by @a-r-r-o-w in #10454\r\n* [LoRA] Support original format loras for HunyuanVideo  by @a-r-r-o-w in #10376\r\n* [LoRA] feat: support loading loras into 4bit quantized Flux models.  by @sayakpaul in #10578\r\n* [LoRA] clean up `load_lora_into_text_encoder()` and `fuse_lora()` copied from  by @sayakpaul in #10495 \r\n* [LoRA] feat: support `unload_lora_weights()` for Flux Control.  by @sayakpaul in #10206\r\n* Fix Flux multiple Lora loading bug  by @maxs-kan in #10388\r\n* [LoRA] fix: lora unloading when using expanded Flux LoRAs.  by @sayakpaul in #10397\r\n\r\n\r\n\r\n\r\n ","publishedAt":"2025-01-15T16:46:08.000Z","fetchedAt":"2026-04-07T17:27:25.723Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.32.2","media":[],"coverageCount":0},{"id":"rel_XbfqQqPIMzvPSUut9peIP","version":"v0.32.1","type":"feature","title":"v0.32.1","summary":"# TorchAO Quantizer fixes\r\n\r\nThis patch release fixes a few bugs related to the TorchAO Quantizer introduced in [v0.32.0]().\r\n\r\n- Importing Diffusers ...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"# TorchAO Quantizer fixes\r\n\r\nThis patch release fixes a few bugs related to the TorchAO Quantizer introduced in [v0.32.0]().\r\n\r\n- Importing Diffusers would raise an error in PyTorch versions lower than 2.3.0. This should no longer be a problem.\r\n- Device Map does not work as expected when using the quantizer. We now raise an error if it is used. Support for using device maps with different quantization backends will be added in the near future.\r\n- Quantization was not performed due to faulty logic. This is now fixed and better tested.\r\n\r\nRefer to our [documentation](https://huggingface.co/docs/diffusers/) to learn more about how to use different quantization backends.\r\n\r\n## All commits\r\n\r\n* make style for https://github.com/huggingface/diffusers/pull/10368  by @yiyixuxu in #10370\r\n* fix test pypi installation in the release workflow  by @sayakpaul in #10360\r\n* Fix TorchAO related bugs; revert device_map changes  by @a-r-r-o-w in #10371","publishedAt":"2024-12-25T12:34:54.000Z","fetchedAt":"2026-04-07T17:27:25.622Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.32.1","media":[],"coverageCount":0},{"id":"rel_D_iX4wMgv0tc2RG_OOLMv","version":"v0.32.0","type":"feature","title":"Diffusers 0.32.0: New video pipelines, new image pipelines, new quantization backends, new training scripts, and more","summary":"https://github.com/user-attachments/assets/34d5f7ca-8e33-4401-8109-5c245ce7595f\r\n\r\nThis release took a while, but it has many exciting updates. It con...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"https://github.com/user-attachments/assets/34d5f7ca-8e33-4401-8109-5c245ce7595f\r\n\r\nThis release took a while, but it has many exciting updates. It contains several new pipelines for image and video generation, new quantization backends, and more. \r\n\r\nGoing forward, to provide more transparency to the community about ongoing developments and releases in Diffusers, we will be making use of a [roadmap tracker](https://github.com/orgs/huggingface/projects/61/views/1). \r\n\r\n## New Video Generation Pipelines 📹\r\n\r\nOpen video generation models are on the rise, and we’re pleased to provide comprehensive integration support for all of them. The following video pipelines are bundled in this release:\r\n\r\n- [Mochi-1](https://huggingface.co/docs/diffusers/main/en/api/pipelines/mochi)\r\n- [Allegro](https://huggingface.co/docs/diffusers/main/en/api/pipelines/allegro)\r\n- [LTXVideo](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video)\r\n- [HunyuanVideo](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video)\r\n\r\nCheck out [this section](https://www.notion.so/Diffusers-0-32-0-release-15f1384ebcac8091ac5bf18c128639ab?pvs=21) to learn more about the fine-tuning options available for these new video models. \r\n\r\n## New Image Generation Pipelines\r\n\r\n- SANA\r\n    - [Text-to-image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana#diffusers.SanaPipeline)\r\n    - [PAG](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana#diffusers.SanaPAGPipeline)\r\n- Flux Control (including Control LoRA)\r\n    - [Depth Control](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#depth-control)\r\n    - [Canny Control](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#canny-control)\r\n- [Flux Redux](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#redux)\r\n- [Flux Fill Inpainting / Outpainting](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#fill-inpaintingoutpainting)\r\n- [Flux RF-Inversion](https://github.com/huggingface/diffusers/pull/9816)\r\n- [SD3.5 ControlNet](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_3#image-prompting-with-ip-adapters)\r\n- [ControlNet Union XL](https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_union)\r\n- [SD3.5 IP Adapter](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_3#image-prompting-with-ip-adapters)\r\n- [Flux IP adapter](https://github.com/huggingface/diffusers/pull/10261)\r\n\r\n**Important Note about the new Flux Models**\r\n\r\nWe can combine the regular Flux.1 Dev LoRAs with Flux Control LoRAs, Flux Control, and Flux Fill. For example, you can enable few-steps inference with Flux Fill using:\r\n\r\n```python\r\nfrom diffusers import FluxFillPipeline\r\nfrom diffusers.utils import load_image\r\nimport torch\r\n\r\npipe = FluxFillPipeline.from_pretrained(\r\n    \"black-forest-labs/FLUX.1-Fill-dev\", torch_dtype=torch.bfloat16\r\n).to(\"cuda\")\r\n\r\nadapter_id = \"alimama-creative/FLUX.1-Turbo-Alpha\"\r\npipe.load_lora_weights(adapter_id)\r\n\r\nimage = load_image(\"https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/cup.png\")\r\nmask = load_image(\"https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/cup_mask.png\")\r\n\r\nimage = pipe(\r\n    prompt=\"a white paper cup\",\r\n    image=image,\r\n    mask_image=mask,\r\n    height=1632,\r\n    width=1232,\r\n    guidance_scale=30,\r\n    num_inference_steps=8,\r\n    max_sequence_length=512,\r\n    generator=torch.Generator(\"cpu\").manual_seed(0)\r\n).images[0]\r\nimage.save(\"flux-fill-dev.png\")\r\n```\r\n\r\nTo learn more, check out the [documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#combining-flux-turbo-loras-with-flux-control-fill-and-redux). \r\n\r\n> [!NOTE]  \r\n> SANA is a small model compared to other models like Flux and Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image.  We support LoRA fine-tuning of SANA. Check out [this section](https://www.notion.so/Diffusers-0-32-0-release-15f1384ebcac8091ac5bf18c128639ab?pvs=21) for more details.\r\n\r\n### Acknowledgements\r\n\r\n- Shoutout to @lawrence-cj and @chenjy2003 for contributing SANA in [this PR](https://github.com/huggingface/diffusers/pull/9982). SANA also features a Deep Compression Autoencoder, which was contributed by @lawrence-cj in [this PR](https://github.com/huggingface/diffusers/pull/9708). \r\n- Shoutout to @guiyrt for contributing SD3.5 IP Adapter in [this PR](https://github.com/huggingface/diffusers/pull/9987).\r\n\r\n## New Quantization Backends\r\n\r\n- [TorchAO](https://huggingface.co/docs/diffusers/main/en/quantization/torchao)\r\n- [GGUF](https://huggingface.co/docs/diffusers/main/en/quantization/gguf)\r\n\r\nPlease be aware of the following caveats:\r\n\r\n- TorchAO quantized checkpoints cannot be serialized in `safetensors` currently. This may change in the future.\r\n- GGUF currently only supports loading pre-quantized checkpoints into models in this release. Support for saving models with GGUF quantization will be added in the future.\r\n\r\n## New training scripts\r\n\r\nThis release features many new training scripts for the community to play:\r\n\r\n- [Flux Control](https://github.com/huggingface/diffusers/tree/main/examples/flux-control)\r\n- [Mochi-1](https://github.com/a-r-r-o-w/finetrainers)\r\n- [LTXVideo](https://github.com/a-r-r-o-w/finetrainers?tab=readme-ov-file#quickstart)\r\n- [SANA](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sana.md)\r\n- [Hunyuan Video](https://github.com/a-r-r-o-w/finetrainers?tab=readme-ov-file#quickstart)\r\n\r\n## All commits\r\n\r\n* post-release 0.31.0  by @sayakpaul in #9742\r\n* fix bug in `require_accelerate_version_greater`  by @faaany in #9746\r\n* [Official callbacks] SDXL Controlnet CFG Cutoff  by @asomoza in #9311\r\n* [SD3-5 dreambooth lora] update model cards  by @linoytsaban in #9749\r\n* config attribute not foud error for FluxImagetoImage Pipeline for multi controlnet solved  by @rshah240 in #9586\r\n* Some minor updates to the nightly and push workflows  by @sayakpaul in #9759\r\n* [Docs] fix docstring typo in SD3 pipeline  by @shenzhiy21 in #9765\r\n* [bugfix] bugfix for npu free memory  by @leisuzz in #9640\r\n* [research_projects] add flux training script with quantization  by @sayakpaul in #9754\r\n* Add a doc for AWS Neuron in Diffusers  by @JingyaHuang in #9766\r\n* [refactor] enhance readability of flux related pipelines  by @Luciennnnnnn in #9711\r\n* Added Support of Xlabs controlnet to FluxControlNetInpaintPipeline  by @SahilCarterr in #9770\r\n* [research_projects] Update README.md to include a note about NF5 T5-xxl  by @sayakpaul in #9775\r\n* [Fix] train_dreambooth_lora_flux_advanced ValueError: unexpected save model: <class 'transformers.models.t5.modeling_t5.T5EncoderModel'>  by @rootonchair in #9777\r\n* [Fix] remove setting lr for T5 text encoder when using prodigy in flux dreambooth lora script  by @biswaroop1547 in #9473\r\n* [SD 3.5 Dreambooth LoRA] support configurable training block & layers  by @linoytsaban in #9762\r\n* [flux dreambooth lora training] make LoRA target modules configurable + small bug fix  by @linoytsaban in #9646\r\n* adds the pipeline for pixart alpha controlnet  by @raulc0399 in #8857\r\n* [core] Allegro T2V  by @a-r-r-o-w in #9736\r\n* Allegro VAE fix  by @a-r-r-o-w in #9811\r\n* [CI] add new runner for testing  by @sayakpaul in #9699\r\n* [training] fixes to the quantization training script and add AdEMAMix optimizer as an option  by @sayakpaul in #9806\r\n* [training] use the lr when using 8bit adam.  by @sayakpaul in #9796\r\n* [Tests] clean up and refactor gradient checkpointing tests  by @sayakpaul in #9494\r\n* [CI] add a big GPU marker to run memory-intensive tests separately on CI  by @sayakpaul in #9691\r\n* [LoRA] fix: lora loading when using with a device_mapped model.  by @sayakpaul in #9449\r\n* Revert \"[LoRA] fix: lora loading when using with a device_mapped mode…  by @yiyixuxu in #9823\r\n* [Model Card] standardize advanced diffusion training sd15 lora  by @chiral-carbon in #7613\r\n* NPU Adaption for FLUX  by @leisuzz in #9751\r\n* Fixes EMAModel \"from_pretrained\" method  by @SahilCarterr in #9779\r\n* Update train_controlnet_flux.py,Fix size mismatch issue in validation  by @ScilenceForest in #9679\r\n* Handling mixed precision for dreambooth flux lora training  by @icsl-Jeon in #9565\r\n* Reduce Memory Cost in Flux Training  by @leisuzz in #9829\r\n* Add Diffusion Policy for Reinforcement Learning  by @DorsaRoh in #9824\r\n* [feat] add `load_lora_adapter()` for compatible models  by @sayakpaul in #9712\r\n* Refac training utils.py  by @RogerSinghChugh in #9815\r\n* [core] Mochi T2V   by @a-r-r-o-w in #9769\r\n* [Fix] Test of sd3 lora  by @SahilCarterr in #9843\r\n* Fix: Remove duplicated comma in distributed_inference.md  by @vahidaskari in #9868\r\n* Add new community pipeline for 'Adaptive Mask Inpainting', introduced in [ECCV2024] ComA  by @jellyheadandrew in #9228\r\n* Updated _encode_prompt_with_clip and encode_prompt in train_dreamboth_sd3  by @SahilCarterr in #9800\r\n* [Core] introduce `controlnet` module  by @sayakpaul in #8768\r\n* [Flux] reduce explicit device transfers and typecasting in flux.  by @sayakpaul in #9817\r\n* Improve downloads of sharded variants  by @DN6 in #9869\r\n* [fix] Replaced shutil.copy with shutil.copyfile  by @SahilCarterr in #9885\r\n* Enabling gradient checkpointing in eval() mode  by @MikeTkachuk in #9878\r\n* [FIX] Fix TypeError in DreamBooth SDXL when use_dora is False  by @SahilCarterr in #9879\r\n* [Advanced LoRA v1.5] fix: gradient unscaling problem  by @sayakpaul in #7018\r\n* Revert \"[Flux] reduce explicit device transfers and typecasting in flux.\"  by @sayakpaul in #9896\r\n* Feature IP Adapter Xformers Attention Processor  by @elismasilva in #9881\r\n*  Notebooks for Community Scripts Examples  by @ParagEkbote in #9905\r\n* Fix Progress Bar Updates in SD 1.5 PAG Img2Img pipeline  by @painebenjamin in #9925\r\n* Update pipeline_flux_img2img.py  by @example-git in #9928\r\n* add depth controlnet sd3 pre-trained checkpoints to docs  by @pureexe in #9937\r\n* Move Wuerstchen Dreambooth to research_projects  by @ParagEkbote in #9935\r\n* Update ip_adapter.py  by @mkknightr in #8882\r\n* Modify apply_overlay for inpainting with padding_mask_crop (Inpainting area: \"Only Masked\")  by @clarkkent0618 in #8793\r\n* Correct pipeline_output.py to the type Mochi  by @twobob in #9945\r\n* Add all AttnProcessor classes in `AttentionProcessor` type  by @Prgckwb in #9909\r\n* Fixed Nits in Docs and Example Script  by @ParagEkbote in #9940\r\n* Add server example  by @thealmightygrant in #9918\r\n* CogVideoX 1.5  by @zRzRzRzRzRzRzR in #9877\r\n* Notebooks for Community Scripts-2  by @ParagEkbote in #9952\r\n* [advanced flux training] bug fix + reduce memory cost as in #9829  by @linoytsaban in #9838\r\n* [LoRA] feat: `save_lora_adapter()`  by @sayakpaul in #9862\r\n* Make CogVideoX RoPE implementation consistent  by @a-r-r-o-w in #9963\r\n* [CI] Unpin torch<2.5 in CI  by @DN6 in #9961\r\n* Move IP Adapter Scripts to research project  by @ParagEkbote in #9960\r\n* add skip_layers argument to SD3 transformer model class  by @bghira in #9880\r\n* Fix beta and exponential sigmas + add tests  by @hlky in #9954\r\n* Flux latents fix  by @DN6 in #9929\r\n* [LoRA] enable LoRA for Mochi-1  by @sayakpaul in #9943\r\n* Improve control net block index for sd3  by @linjiapro in #9758\r\n* Update handle single blocks on _convert_xlabs_flux_lora_to_diffusers  by @raulmosa in #9915\r\n* fix controlnet module refactor   by @yiyixuxu in #9968\r\n* Fix prepare latent image ids and vae sample generators for flux  by @a-r-r-o-w in #9981\r\n* [Tests] skip nan lora tests on PyTorch 2.5.1 CPU.  by @sayakpaul in #9975\r\n* make `pipelines` tests device-agnostic (part1)  by @faaany in #9399\r\n* ControlNet from_single_file when already converted  by @hlky in #9978\r\n* Flux Fill, Canny, Depth, Redux  by @a-r-r-o-w in #9985\r\n* [SD3 dreambooth lora] smol fix to checkpoint saving  by @linoytsaban in #9993\r\n* [Docs] add: missing pipelines from the spec.  by @sayakpaul in #10005\r\n* Add prompt about wandb in examples/dreambooth/readme.  by @SkyCol in #10014\r\n* [docs] Fix CogVideoX table  by @a-r-r-o-w in #10008\r\n* Notebooks for Community Scripts-3  by @ParagEkbote in #10032\r\n* Sd35 controlnet  by @yiyixuxu in #10020\r\n* Add `beta`, `exponential` and `karras` sigmas to `FlowMatchEulerDiscreteScheduler`  by @hlky in #10001\r\n* Update sdxl reference pipeline to latest sdxl pipeline  by @dimitribarbot in #9938\r\n* [Community Pipeline] Add some feature for regional prompting pipeline  by @cjkangme in #9874\r\n* Add sdxl controlnet reference community pipeline  by @dimitribarbot in #9893\r\n* Change image_gen_aux repository URL  by @asomoza in #10048\r\n* make `pipelines` tests device-agnostic (part2)  by @faaany in #9400\r\n* [Mochi-1] ensuring to compute the fourier features in FP32 in Mochi encoder  by @sayakpaul in #10031\r\n* [Fix] Syntax error  by @SahilCarterr in #10068\r\n* [CI] Add quantization  by @sayakpaul in #9832\r\n* Add `sigmas` to Flux pipelines  by @hlky in #10081\r\n* Fixed Nits in Evaluation Docs   by @ParagEkbote in #10063\r\n* fix link in the docs  by @coding-famer in #10058\r\n* fix offloading for sd3.5 controlnets  by @yiyixuxu in #10072\r\n* [Single File] Fix SD3.5 single file loading  by @DN6 in #10077\r\n* Fix `num_images_per_prompt>1` with Skip Guidance Layers in `StableDiffusion3Pipeline`  by @hlky in #10086\r\n* [Single File] Pass token when fetching interpreted config  by @DN6 in #10082\r\n* Interpolate fix on cuda for large output tensors  by @pcuenca in #10067\r\n* Convert `sigmas` to `np.array` in FlowMatch set_timesteps  by @hlky in #10088\r\n* fix: missing AutoencoderKL lora adapter  by @beniz in #9807\r\n* Let server decide default repo visibility  by @Wauplin in #10047\r\n* Fix some documentation in ./src/diffusers/models/embeddings.py for demo  by @DTG2005 in #9579\r\n* Don't stale close-to-merge  by @pcuenca in #10096\r\n* Add StableDiffusion3PAGImg2Img Pipeline + Fix SD3 Unconditional PAG  by @painebenjamin in #9932\r\n* Notebooks for Community Scripts-4  by @ParagEkbote in #10094\r\n* Fix Broken Link in Optimization Docs  by @ParagEkbote in #10105\r\n* DPM++ third order fixes  by @StAlKeR7779 in #9104\r\n* update  by @aihao2000 in #7067\r\n* Avoid compiling a progress bar.  by @lsb in #10098\r\n* [Bug fix] \"previous_timestep()\" in DDPM scheduling compatible with \"trailing\" and \"linspace\" options  by @AnandK27 in #9384\r\n* Fix multi-prompt inference  by @hlky in #10103\r\n* Test `skip_guidance_layers` in SD3 pipeline  by @hlky in #10102\r\n* Use parameters + buffers when deciding upscale_dtype  by @universome in #9882\r\n* [tests] refactor vae tests  by @sayakpaul in #9808\r\n* add torch_xla support in pipeline_stable_audio.py  by @<NOT FOUND> in #10109\r\n* Fix `pipeline_stable_audio` formating  by @hlky in #10114\r\n* [bitsandbytes] allow directly CUDA placements of pipelines loaded with bnb components  by @sayakpaul in #9840\r\n* Fix Broken Links in ReadMe  by @ParagEkbote in #10117\r\n* Add `sigmas` to pipelines using FlowMatch  by @hlky in #10116\r\n* [Flux Redux] add prompt & multiple image input   by @linoytsaban in #10056\r\n* Fix a bug in the state dict judgment in ip_adapter.py.  by @zhangp365 in #10095\r\n* Fix a bug for SD35 control net training and improve control net block index  by @linjiapro in #10065\r\n* pass attn mask arg for flux  by @yiyixuxu in #10122\r\n* [docs] load_lora_adapter  by @stevhliu in #10119\r\n* Use torch.device instead of current device index for BnB quantizer  by @a-r-r-o-w in #10069\r\n* [Tests] fix condition argument in xfail.  by @sayakpaul in #10099\r\n* [Tests] xfail incompatible SD configs.  by @sayakpaul in #10127\r\n* [FIX] Bug in FluxPosEmbed  by @SahilCarterr in #10115\r\n* [Guide] Quantize your Diffusion Models with `bnb`  by @ariG23498 in #10012\r\n* Remove duplicate checks for len(generator) != batch_size when generator is a list  by @a-r-r-o-w in #10134\r\n* [community] Load Models from Sources like `Civitai` into Existing Pipelines  by @suzukimain in #9986\r\n* [DC-AE] Add the official Deep Compression Autoencoder code(32x,64x,128x compression ratio);  by @lawrence-cj in #9708\r\n* fixed a dtype bfloat16 bug in torch_utils.py  by @zhangp365 in #10125\r\n* [LoRA] depcrecate save_attn_procs().  by @sayakpaul in #10126\r\n* Update ptxla training  by @entrpn in #9864\r\n* support sd3.5 for controlnet example  by @DavyMorgan in #9860\r\n* [Single file] Support `revision` argument when loading single file config  by @a-r-r-o-w in #10168\r\n* [community pipeline] Add RF-inversion Flux pipeline  by @linoytsaban in #9816\r\n* Improve post-processing performance  by @soof-golan in #10170\r\n* Use `torch` in `get_3d_rotary_pos_embed`/`_allegro`  by @hlky in #10161\r\n* Flux Control LoRA  by @a-r-r-o-w in #9999\r\n* Add PAG Support for Stable Diffusion Inpaint Pipeline  by @darshil0805 in #9386\r\n* [community pipeline rf-inversion] - fix example in doc  by @linoytsaban in #10179\r\n* Fix Nonetype attribute error when loading multiple Flux loras  by @jonathanyin12 in #10182\r\n* Added Error when len(gligen_images ) is not equal to len(gligen_phrases) in StableDiffusionGLIGENTextImagePipeline  by @SahilCarterr in #10176\r\n* [Single File] Add single file support for AutoencoderDC  by @DN6 in #10183\r\n* Add ControlNetUnion  by @hlky in #10131\r\n* fix min-snr implementation  by @ethansmith2000 in #8466\r\n* Add support for XFormers in SD3  by @CanvaChen in #8583\r\n* [LoRA] add a test to ensure `set_adapters()` and attn kwargs outs match  by @sayakpaul in #10110\r\n* [CI] merge peft pr workflow into the main pr workflow.  by @sayakpaul in #10042\r\n* [WIP][Training] Flux Control LoRA training script  by @sayakpaul in #10130\r\n* [core] LTX Video  by @a-r-r-o-w in #10021\r\n* Ci update tpu  by @paulinebm in #10197\r\n* Remove `negative_*` from SDXL callback  by @hlky in #10203\r\n* refactor  StableDiffusionXLControlNetUnion  by @hlky in #10200\r\n* update StableDiffusion3Img2ImgPipeline.add image size validation  by @ZHJ19970917 in #10166\r\n* Remove mps workaround for fp16 GELU, which is now supported natively  by @skotapati in #10133\r\n* [RF inversion community pipeline] add eta_decay   by @linoytsaban in #10199\r\n* Allow image resolutions multiple of 8 instead of 64 in SVD pipeline  by @mlfarinha in #6646\r\n* Use `torch` in `get_2d_sincos_pos_embed` and `get_3d_sincos_pos_embed`  by @hlky in #10156\r\n* add reshape to fix use_memory_efficient_attention in flax  by @entrpn in #7918\r\n* Add offload option in flux-control training  by @Adenialzz in #10225\r\n* Test error raised when loading normal and expanding loras together in Flux  by @a-r-r-o-w in #10188\r\n* [Sana] Add Sana, including `SanaPipeline`, `SanaPAGPipeline`, `LinearAttentionProcessor`, `Flow-based DPM-sovler` and so on.  by @lawrence-cj in #9982\r\n* [Tests] update always test pipelines list.  by @sayakpaul in #10143\r\n* Update sana.md with minor corrections  by @sayakpaul in #10232\r\n* [docs] minor stuff to ltx video docs.  by @sayakpaul in #10229\r\n* Fix format issue in push_test yml  by @DN6 in #10235\r\n* [core] Hunyuan Video  by @a-r-r-o-w in #10136\r\n* Update pipeline_controlnet.py add support for pytorch_xla  by @<NOT FOUND> in #10222\r\n* [Docs] add rest of the lora loader mixins to the docs.  by @sayakpaul in #10230\r\n* Use `t` instead of `timestep` in `_apply_perturbed_attention_guidance`  by @hlky in #10243\r\n* Add `dynamic_shifting` to SD3  by @hlky in #10236\r\n* Fix `use_flow_sigmas`  by @hlky in #10242\r\n* Fix ControlNetUnion _callback_tensor_inputs  by @hlky in #10218\r\n* Use non-human subject in StableDiffusion3ControlNetPipeline example  by @hlky in #10214\r\n* Add enable_vae_tiling to AllegroPipeline, fix example  by @hlky in #10212\r\n* Fix checkpoint in CogView3PlusPipeline example  by @hlky in #10211\r\n* Fix RePaint Scheduler  by @hlky in #10185\r\n* Add ControlNetUnion to AutoPipeline from_pretrained  by @hlky in #10219\r\n* fix downsample bug in MidResTemporalBlock1D  by @holmosaint in #10250\r\n* [core] TorchAO Quantizer  by @a-r-r-o-w in #10009\r\n* [docs] Add missing AttnProcessors  by @stevhliu in #10246\r\n* [chore] add contribution note for lawrence.  by @sayakpaul in #10253\r\n* Fix copied from comment in Mochi lora loader  by @a-r-r-o-w in #10255\r\n* [LoRA] Support LTX Video  by @a-r-r-o-w in #10228\r\n* [docs] Clarify dtypes for Sana  by @a-r-r-o-w in #10248\r\n* [Single File] Add GGUF support  by @DN6 in #9964\r\n* Fix Mochi Quality Issues  by @DN6 in #10033\r\n* [tests] Remove/rename unsupported quantization torchao type  by @a-r-r-o-w in #10263\r\n* [docs] delete_adapters()  by @stevhliu in #10245\r\n* [Community Pipeline] Fix typo that cause error on regional prompting pipeline  by @cjkangme in #10251\r\n* Add `set_shift` to FlowMatchEulerDiscreteScheduler  by @hlky in #10269\r\n* [LoRA] feat: lora support for SANA.  by @sayakpaul in #10234\r\n* [chore] fix: licensing headers in mochi and ltx  by @sayakpaul in #10275\r\n* Use `torch` in `get_2d_rotary_pos_embed`  by @hlky in #10155\r\n* [chore] fix: reamde -> readme  by @sayakpaul in #10276\r\n* Make `time_embed_dim` of `UNet2DModel` changeable  by @Bichidian in #10262\r\n* Support pass kwargs to sd3 custom attention processor  by @Matrix53 in #9818\r\n* Flux Control(Depth/Canny) + Inpaint  by @affromero in #10192\r\n* Fix sigma_last with use_flow_sigmas  by @hlky in #10267\r\n* Fix Doc links in GGUF and Quantization overview docs   by @DN6 in #10279\r\n* Make zeroing prompt embeds for Mochi Pipeline configurable  by @DN6 in #10284\r\n* [Single File] Add single file support for Flux Canny, Depth and Fill  by @DN6 in #10288\r\n* [tests] Fix broken cuda, nightly and lora tests on main for CogVideoX  by @a-r-r-o-w in #10270\r\n* Rename Mochi integration test correctly  by @a-r-r-o-w in #10220\r\n* [tests] remove nullop import checks from lora tests  by @a-r-r-o-w in #10273\r\n* [chore] Update README_sana.md to update the default model  by @sayakpaul in #10285\r\n* Hunyuan VAE tiling fixes and transformer docs  by @a-r-r-o-w in #10295\r\n* Add Flux Control to AutoPipeline  by @hlky in #10292\r\n* Update lora_conversion_utils.py  by @zhaowendao30 in #9980\r\n* Check correct model type is passed to `from_pretrained`  by @hlky in #10189\r\n* [LoRA] Support HunyuanVideo  by @SHYuanBest in #10254\r\n* [Single File] Add single file support for Mochi Transformer  by @DN6 in #10268\r\n* Allow Mochi Transformer to be split across multiple GPUs  by @DN6 in #10300\r\n* Fix `local_files_only` for checkpoints with shards  by @hlky in #10294\r\n* Fix failing lora tests after HunyuanVideo lora  by @a-r-r-o-w in #10307\r\n* unet's `sample_size` attribute is to accept tuple(h, w) in `StableDiffusionPipeline`  by @Foundsheep in #10181\r\n* Enable Gradient Checkpointing for UNet2DModel (New)  by @dg845 in #7201\r\n* [WIP] SD3.5 IP-Adapter Pipeline Integration  by @guiyrt in #9987\r\n* Add support for sharded models when TorchAO quantization is enabled  by @a-r-r-o-w in #10256\r\n* Make tensors in ResNet contiguous for Hunyuan VAE  by @a-r-r-o-w in #10309\r\n* [Single File] Add GGUF support for LTX  by @DN6 in #10298\r\n* [LoRA] feat: support loading regular Flux LoRAs into Flux Control, and Fill  by @sayakpaul in #10259\r\n* [Tests] add integration tests for lora expansion stuff in Flux.  by @sayakpaul in #10318\r\n* Mochi docs  by @DN6 in #9934\r\n* [Docs] Update ltx_video.md to remove generator from `from_pretrained()`  by @sayakpaul in #10316\r\n* docs: fix a mistake in docstring  by @Leojc in #10319\r\n* [BUG FIX] [Stable Audio Pipeline] Resolve torch.Tensor.new_zeros() TypeError in function prepare_latents caused by audio_vae_length  by @syntaxticsugr in #10306\r\n* [docs] Fix quantization links  by @stevhliu in #10323\r\n* [Sana]add 2K related model for Sana  by @lawrence-cj in #10322\r\n* [Docs] Update gguf.md to remove generator from the pipeline from_pretrained  by @sayakpaul in #10299\r\n* Fix push_tests_mps.yml  by @hlky in #10326\r\n* Fix EMAModel test_from_pretrained  by @hlky in #10325\r\n* Support Flux IP Adapter  by @hlky in #10261\r\n* flux controlnet inpaint config bug  by @yigitozgenc in #10291\r\n* Community hosted weights for diffusers format HunyuanVideo weights  by @a-r-r-o-w in #10344\r\n* Fix enable_sequential_cpu_offload in test_kandinsky_combined  by @hlky in #10324\r\n* update `get_parameter_dtype`  by @yiyixuxu in #10342\r\n* [Single File] Add Single File support for HunYuan video  by @DN6 in #10320\r\n* [Sana bug] bug fix for 2K model config  by @lawrence-cj in #10340\r\n* `.from_single_file()` - Add missing `.shape`  by @gau-nernst in #10332\r\n* Bump minimum TorchAO version to 0.7.0  by @a-r-r-o-w in #10293\r\n* [docs] fix: torchao example.  by @sayakpaul in #10278\r\n* [tests] Refactor TorchAO serialization fast tests  by @a-r-r-o-w in #10271\r\n* [SANA LoRA] sana lora training tests and misc.  by @sayakpaul in #10296\r\n* [Single File] Fix loading  by @DN6 in #10349\r\n* [Tests] QoL improvements to the LoRA test suite  by @sayakpaul in #10304\r\n* Fix FluxIPAdapterTesterMixin  by @hlky in #10354\r\n* Fix failing CogVideoX LoRA fuse test  by @a-r-r-o-w in #10352\r\n* Rename LTX blocks and docs title  by @a-r-r-o-w in #10213\r\n* [LoRA] test fix  by @sayakpaul in #10351\r\n* [Tests] Fix more tests sayak  by @sayakpaul in #10359\r\n* [core] LTX Video 0.9.1  by @a-r-r-o-w in #10330\r\n* Release: v0.32.0 by @sayakpaul (direct commit on v0.32.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @faaany\r\n    * fix bug in `require_accelerate_version_greater` (#9746)\r\n    * make `pipelines` tests device-agnostic (part1) (#9399)\r\n    * make `pipelines` tests device-agnostic (part2) (#9400)\r\n* @linoytsaban\r\n    * [SD3-5 dreambooth lora] update model cards (#9749)\r\n    * [SD 3.5 Dreambooth LoRA] support configurable training block & layers (#9762)\r\n    * [flux dreambooth lora training] make LoRA target modules configurable + small bug fix (#9646)\r\n    * [advanced flux training] bug fix + reduce memory cost as in #9829 (#9838)\r\n    * [SD3 dreambooth lora] smol fix to checkpoint saving (#9993)\r\n    * [Flux Redux] add prompt & multiple image input  (#10056)\r\n    * [community pipeline] Add RF-inversion Flux pipeline (#9816)\r\n    * [community pipeline rf-inversion] - fix example in doc (#10179)\r\n    * [RF inversion community pipeline] add eta_decay  (#10199)\r\n* @raulc0399\r\n    * adds the pipeline for pixart alpha controlnet (#8857)\r\n* @yiyixuxu\r\n    * Revert \"[LoRA] fix: lora loading when using with a device_mapped mode… (#9823)\r\n    * fix controlnet module refactor  (#9968)\r\n    * Sd35 controlnet (#10020)\r\n    * fix offloading for sd3.5 controlnets (#10072)\r\n    * pass attn mask arg for flux (#10122)\r\n    * update `get_parameter_dtype` (#10342)\r\n* @jellyheadandrew\r\n    * Add new community pipeline for 'Adaptive Mask Inpainting', introduced in [ECCV2024] ComA (#9228)\r\n* @DN6\r\n    * Improve downloads of sharded variants (#9869)\r\n    * [CI] Unpin torch<2.5 in CI (#9961)\r\n    * Flux latents fix (#9929)\r\n    * [Single File] Fix SD3.5 single file loading (#10077)\r\n    * [Single File] Pass token when fetching interpreted config (#10082)\r\n    * [Single File] Add single file support for AutoencoderDC (#10183)\r\n    * Fix format issue in push_test yml (#10235)\r\n    * [Single File] Add GGUF support (#9964)\r\n    * Fix Mochi Quality Issues (#10033)\r\n    * Fix Doc links in GGUF and Quantization overview docs  (#10279)\r\n    * Make zeroing prompt embeds for Mochi Pipeline configurable (#10284)\r\n    * [Single File] Add single file support for Flux Canny, Depth and Fill (#10288)\r\n    * [Single File] Add single file support for Mochi Transformer (#10268)\r\n    * Allow Mochi Transformer to be split across multiple GPUs (#10300)\r\n    * [Single File] Add GGUF support for LTX (#10298)\r\n    * Mochi docs (#9934)\r\n    * [Single File] Add Single File support for HunYuan video (#10320)\r\n    * [Single File] Fix loading (#10349)\r\n* @ParagEkbote\r\n    *  Notebooks for Community Scripts Examples (#9905)\r\n    * Move Wuerstchen Dreambooth to research_projects (#9935)\r\n    * Fixed Nits in Docs and Example Script (#9940)\r\n    * Notebooks for Community Scripts-2 (#9952)\r\n    * Move IP Adapter Scripts to research project (#9960)\r\n    * Notebooks for Community Scripts-3 (#10032)\r\n    * Fixed Nits in Evaluation Docs  (#10063)\r\n    * Notebooks for Community Scripts-4 (#10094)\r\n    * Fix Broken Link in Optimization Docs (#10105)\r\n    * Fix Broken Links in ReadMe (#10117)\r\n* @painebenjamin\r\n    * Fix Progress Bar Updates in SD 1.5 PAG Img2Img pipeline (#9925)\r\n    * Add StableDiffusion3PAGImg2Img Pipeline + Fix SD3 Unconditional PAG (#9932)\r\n* @hlky\r\n    * Fix beta and exponential sigmas + add tests (#9954)\r\n    * ControlNet from_single_file when already converted (#9978)\r\n    * Add `beta`, `exponential` and `karras` sigmas to `FlowMatchEulerDiscreteScheduler` (#10001)\r\n    * Add `sigmas` to Flux pipelines (#10081)\r\n    * Fix `num_images_per_prompt>1` with Skip Guidance Layers in `StableDiffusion3Pipeline` (#10086)\r\n    * Convert `sigmas` to `np.array` in FlowMatch set_timesteps (#10088)\r\n    * Fix multi-prompt inference (#10103)\r\n    * Test `skip_guidance_layers` in SD3 pipeline (#10102)\r\n    * Fix `pipeline_stable_audio` formating (#10114)\r\n    * Add `sigmas` to pipelines using FlowMatch (#10116)\r\n    * Use `torch` in `get_3d_rotary_pos_embed`/`_allegro` (#10161)\r\n    * Add ControlNetUnion (#10131)\r\n    * Remove `negative_*` from SDXL callback (#10203)\r\n    * refactor  StableDiffusionXLControlNetUnion (#10200)\r\n    * Use `torch` in `get_2d_sincos_pos_embed` and `get_3d_sincos_pos_embed` (#10156)\r\n    * Use `t` instead of `timestep` in `_apply_perturbed_attention_guidance` (#10243)\r\n    * Add `dynamic_shifting` to SD3 (#10236)\r\n    * Fix `use_flow_sigmas` (#10242)\r\n    * Fix ControlNetUnion _callback_tensor_inputs (#10218)\r\n    * Use non-human subject in StableDiffusion3ControlNetPipeline example (#10214)\r\n    * Add enable_vae_tiling to AllegroPipeline, fix example (#10212)\r\n    * Fix checkpoint in CogView3PlusPipeline example (#10211)\r\n    * Fix RePaint Scheduler (#10185)\r\n    * Add ControlNetUnion to AutoPipeline from_pretrained (#10219)\r\n    * Add `set_shift` to FlowMatchEulerDiscreteScheduler (#10269)\r\n    * Use `torch` in `get_2d_rotary_pos_embed` (#10155)\r\n    * Fix sigma_last with use_flow_sigmas (#10267)\r\n    * Add Flux Control to AutoPipeline (#10292)\r\n    * Check correct model type is passed to `from_pretrained` (#10189)\r\n    * Fix `local_files_only` for checkpoints with shards (#10294)\r\n    * Fix push_tests_mps.yml (#10326)\r\n    * Fix EMAModel test_from_pretrained (#10325)\r\n    * Support Flux IP Adapter (#10261)\r\n    * Fix enable_sequential_cpu_offload in test_kandinsky_combined (#10324)\r\n    * Fix FluxIPAdapterTesterMixin (#10354)\r\n* @dimitribarbot\r\n    * Update sdxl reference pipeline to latest sdxl pipeline (#9938)\r\n    * Add sdxl controlnet reference community pipeline (#9893)\r\n* @suzukimain\r\n    * [community] Load Models from Sources like `Civitai` into Existing Pipelines (#9986)\r\n* @lawrence-cj\r\n    * [DC-AE] Add the official Deep Compression Autoencoder code(32x,64x,128x compression ratio); (#9708)\r\n    * [Sana] Add Sana, including `SanaPipeline`, `SanaPAGPipeline`, `LinearAttentionProcessor`, `Flow-based DPM-sovler` and so on. (#9982)\r\n    * [Sana]add 2K related model for Sana (#10322)\r\n    * [Sana bug] bug fix for 2K model config (#10340)\r\n* @darshil0805\r\n    * Add PAG Support for Stable Diffusion Inpaint Pipeline (#9386)\r\n* @affromero\r\n    * Flux Control(Depth/Canny) + Inpaint (#10192)\r\n* @SHYuanBest\r\n    * [LoRA] Support HunyuanVideo (#10254)\r\n* @guiyrt\r\n    * [WIP] SD3.5 IP-Adapter Pipeline Integration (#9987)\r\n","publishedAt":"2024-12-23T16:00:11.000Z","fetchedAt":"2026-04-07T17:27:25.622Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.32.0","media":[],"coverageCount":0},{"id":"rel_N3kbPB7f8qERPuT-bbHI5","version":"v0.31.0","type":"feature","title":"v0.31.0","summary":"# v0.31.0: Stable Diffusion 3.5 Large, CogView3, Quantization, Training Scripts, and more\r\n\r\n## Stable Diffusion 3.5 Large\r\n\r\nStability AI’s latest te...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"# v0.31.0: Stable Diffusion 3.5 Large, CogView3, Quantization, Training Scripts, and more\r\n\r\n## Stable Diffusion 3.5 Large\r\n\r\nStability AI’s latest text-to-image generation model is Stable Diffusion 3.5 Large. SD3.5 Large is the next iteration of Stable Diffusion 3. It comes with two checkpoints (both of which have 8B params):\r\n\r\n- A regular one\r\n- A timestep-distilled one enabling few-step inference\r\n\r\nMake sure to fill up the form by going to the [model page](https://huggingface.co/stabilityai/stable-diffusion-3.5-large), and then run `huggingface-cli login` before running the code below. \r\n\r\n```python\r\n# make sure to update diffusers\r\n# pip install -U diffusers\r\nimport torch\r\nfrom diffusers import StableDiffusion3Pipeline\r\n\r\npipe = StableDiffusion3Pipeline.from_pretrained(\r\n\t\"stabilityai/stable-diffusion-3.5-large\", torch_dtype=torch.bfloat16\r\n).to(\"cuda\")\r\n\r\nimage = pipe(\r\n    prompt=\"a photo of a cat holding a sign that says hello world\",\r\n    negative_prompt=\"\",\r\n    num_inference_steps=40,\r\n    height=1024,\r\n    width=1024,\r\n    guidance_scale=4.5,\r\n).images[0]\r\n\r\nimage.save(\"sd3_hello_world.png\")\r\n```\r\n\r\nFollow the [documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_3) to know more. \r\n\r\n## Cogview3-plus\r\n\r\nWe added a new text-to-image model, Cogview3-plus, from the THUDM team! The model is DiT-based and supports image generation from 512 to 2048px. Thanks to @zRzRzRzRzRzRzR for contributing it! \r\n\r\n```python\r\nfrom diffusers import CogView3PlusPipeline\r\nimport torch\r\n\r\npipe = CogView3PlusPipeline.from_pretrained(\"THUDM/CogView3-Plus-3B\", torch_dtype=torch.float16).to(\"cuda\")\r\n\r\n# Enable it to reduce GPU memory usage\r\npipe.enable_model_cpu_offload()\r\npipe.vae.enable_slicing()\r\npipe.vae.enable_tiling()\r\n\r\nprompt = \"A vibrant cherry red sports car sits proudly under the gleaming sun, its polished exterior smooth and flawless, casting a mirror-like reflection. The car features a low, aerodynamic body, angular headlights that gaze forward like predatory eyes, and a set of black, high-gloss racing rims that contrast starkly with the red. A subtle hint of chrome embellishes the grille and exhaust, while the tinted windows suggest a luxurious and private interior. The scene conveys a sense of speed and elegance, the car appearing as if it's about to burst into a sprint along a coastal road, with the ocean's azure waves crashing in the background.\"\r\n\r\nimage = pipe(\r\n    prompt=prompt,\r\n    guidance_scale=7.0,\r\n    num_images_per_prompt=1,\r\n    num_inference_steps=50,\r\n    width=1024,\r\n    height=1024,\r\n).images[0]\r\n\r\nimage.save(\"cogview3.png\")\r\n```\r\n\r\nRefer to the [documentation](https://huggingface.co/docs/diffusers/en/api/pipelines/cogview3) to know more. \r\n\r\n## Quantization\r\n\r\nWe have landed native quantization support in Diffusers, starting with `bitsandbytes` as its first quantization backend. With this, we hope to see large diffusion models becoming much more accessible to run on consumer hardware. \r\n\r\nThe example below shows how to run Flux.1 Dev with the NF4 data-type. Make sure you install the libraries:\r\n\r\n```bash\r\npip install -Uq git+https://github.com/huggingface/transformers@main\r\npip install -Uq bitsandbytes\r\npip install -Uq diffusers\r\n```\r\n\r\n```python\r\nfrom diffusers import BitsAndBytesConfig, FluxTransformer2DModel\r\nimport torch\r\n\r\nckpt_id = \"black-forest-labs/FLUX.1-dev\"\r\nnf4_config = BitsAndBytesConfig(\r\n    load_in_4bit=True,\r\n    bnb_4bit_quant_type=\"nf4\",\r\n    bnb_4bit_compute_dtype=torch.bfloat16\r\n)\r\nmodel_nf4 = FluxTransformer2DModel.from_pretrained(\r\n    ckpt_id,\r\n    subfolder=\"transformer\",\r\n    quantization_config=nf4_config,\r\n    torch_dtype=torch.bfloat16\r\n)\r\n```\r\n\r\nThen, we use `model_nf4` to instantiate the `FluxPipeline`:\r\n\r\n```python\r\n\r\nfrom diffusers import FluxPipeline\r\n\r\npipeline = StableDiffusion3Pipeline.from_pretrained(\r\n    ckpt_id, \r\n    transformer=model_nf4,\r\n    torch_dtype=torch.bfloat16\r\n)\r\npipeline.enable_model_cpu_offload()\r\n\r\nprompt = \"A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature's body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight\"\r\n\r\nimage = pipeline(\r\n    prompt=prompt,\r\n    negative_prompt=\"\",\r\n    num_inference_steps=50,\r\n    guidance_scale=4.5,\r\n    max_sequence_length=512,\r\n).images[0]\r\nimage.save(\"whimsical.png\")\r\n```\r\n\r\nFollow the documentation [here](https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes) to know more. Additionally, check out this [Colab Notebook](https://colab.research.google.com/gist/sayakpaul/c76bd845b48759e11687ac550b99d8b4/potato-flux-dev.ipynb) that runs Flux.1 Dev in an end-to-end manner with NF4 quantization. \r\n\r\n## Training scripts\r\n\r\nWe have a fresh bucket of training scripts with this release:\r\n\r\n- [Advanced Flux.1 trainer](https://huggingface.co/blog/linoyts/new-advanced-flux-dreambooth-lora)\r\n- [CogVideoX trainer](https://github.com/huggingface/diffusers/tree/main/examples/cogvideo)\r\n\r\nVideo model fine-tuning can be quite expensive. So, we have worked on a repository, [cogvideox-factory](https://github.com/a-r-r-o-w/cogvideox-factory), which provides memory-optimized scripts to fine-tune the Cog family of models. \r\n\r\n## Misc\r\n\r\n- We now support the loading of different kinds of Flux LoRAs, including Kohya, TheLastBen, and Xlabs.\r\n- Loading of Xlabs Flux ControlNets is also now supported. Thanks to @Anghellia for contributing it! \r\n\r\n## All commits\r\n\r\n* Feature flux controlnet img2img and inpaint pipeline  by @ighoshsubho in #9408\r\n* Remove CogVideoX mentions from single file docs; Test updates  by @a-r-r-o-w in #9444\r\n* set max_shard_size to None for pipeline save_pretrained  by @a-r-r-o-w in #9447\r\n* adapt masked im2im pipeline for SDXL  by @noskill in #7790\r\n* [Flux] add lora integration tests.  by @sayakpaul in #9353\r\n* [training] CogVideoX Lora  by @a-r-r-o-w in #9302\r\n* Several fixes to Flux ControlNet pipelines  by @vladmandic in #9472\r\n* [refactor] LoRA tests  by @a-r-r-o-w in #9481\r\n* [CI] fix nightly model tests  by @sayakpaul in #9483\r\n* [Cog] some minor fixes and nits  by @sayakpaul in #9466\r\n* [Tests] Reduce the model size in the lumina test   by @saqlain2204 in #8985\r\n* Fix the bug of sd3 controlnet training when using gradient checkpointing.  by @pibbo88 in #9498\r\n* [Schedulers] Add exponential sigmas / exponential noise schedule  by @hlky in #9499\r\n* Allow DDPMPipeline half precision  by @sbinnee in #9222\r\n* Add Noise Schedule/Schedule Type to Schedulers Overview documentation  by @hlky in #9504\r\n* fix bugs for sd3 controlnet training  by @xduzhangjiayu in #9489\r\n* [Doc] Fix path and and also import imageio  by @LukeLIN-web in #9506\r\n* [CI] allow faster downloads from the Hub in CI.  by @sayakpaul in #9478\r\n* a few fix for SingleFile tests  by @yiyixuxu in #9522\r\n* Add exponential sigmas to other schedulers and update docs  by @hlky in #9518\r\n* [Community Pipeline] Batched implementation of Flux with CFG  by @sayakpaul in #9513\r\n* Update community_projects.md  by @lee101 in #9266\r\n* [docs] Model sharding  by @stevhliu in #9521\r\n* update get_parameter_dtype  by @yiyixuxu in #9526\r\n* [Doc] Improved level of clarity for latents_to_rgb.  by @LagPixelLOL in #9529\r\n* [Schedulers] Add beta sigmas / beta noise schedule  by @hlky in #9509\r\n* flux controlnet fix (control_modes batch & others)  by @yiyixuxu in #9507\r\n* [Tests] Fix ChatGLMTokenizer  by @asomoza in #9536\r\n* [bug] Precedence of operations in VAE should be slicing -> tiling  by @a-r-r-o-w in #9342\r\n* [LoRA] make set_adapters() method more robust.  by @sayakpaul in #9535\r\n* [examples] add train flux-controlnet scripts in example.  by @PromeAIpro in #9324\r\n* [Tests] [LoRA] clean up the serialization stuff.  by @sayakpaul in #9512\r\n* [Core] fix variant-identification.  by @sayakpaul in #9253\r\n* [refactor] remove conv_cache from CogVideoX VAE  by @a-r-r-o-w in #9524\r\n* [train_instruct_pix2pix.py]Fix the LR schedulers when `num_train_epochs` is passed in a distributed training env  by @AnandK27 in #9316\r\n* [chore] fix: retain memory utility.  by @sayakpaul in #9543\r\n* [LoRA] support Kohya Flux LoRAs that have text encoders as well  by @sayakpaul in #9542\r\n* Add beta sigmas to other schedulers and update docs  by @hlky in #9538\r\n* Add PAG support to StableDiffusionControlNetPAGInpaintPipeline   by @juancopi81 in #8875\r\n* Support bfloat16 for Upsample2D  by @darhsu in #9480\r\n* fix cogvideox autoencoder decode  by @Xiang-cd in #9569\r\n* [sd3] make sure height and size are divisible by `16`  by @yiyixuxu in #9573\r\n* fix xlabs FLUX lora conversion typo  by @Clement-Lelievre in #9581\r\n* [Chore] add a note on the versions in Flux LoRA integration tests  by @sayakpaul in #9598\r\n* fix vae dtype when accelerate config using --mixed_precision=\"fp16\"  by @xduzhangjiayu in #9601\r\n* refac: docstrings in import_utils.py  by @yijun-lee in #9583\r\n* Fix for use_safetensors parameters, allow use of parameter on loading submodels  by @elismasilva in #9576) \r\n* Update distributed_inference.md to include `transformer.device_map`  by @sayakpaul in #9553\r\n* fix: CogVideox train dataset _preprocess_data crop video  by @glide-the in #9574\r\n* [LoRA] Handle DoRA better  by @sayakpaul in #9547\r\n* Fixed noise_pred_text referenced before assignment.  by @LagPixelLOL in #9537\r\n* Fix the bug that `joint_attention_kwargs` is not passed to the FLUX's transformer attention processors  by @HorizonWind2004 in #9517\r\n* refac/pipeline_output  by @yijun-lee in #9582\r\n* [LoRA] allow loras to be loaded with low_cpu_mem_usage.  by @sayakpaul in #9510\r\n* add PAG support for SD Img2Img  by @SahilCarterr in #9463\r\n* make controlnet support interrupt  by @pureexe in #9620\r\n* [LoRA] fix dora test to catch the warning properly.  by @sayakpaul in #9627\r\n* flux controlnet control_guidance_start and control_guidance_end implement  by @ighoshsubho in #9571\r\n* fix IsADirectoryError when running the training code for sd3_dreambooth_lora_16gb.ipynb  by @alaister123 in #9634\r\n* Add Differential Diffusion to Kolors  by @saqlain2204 in #9423\r\n* FluxMultiControlNetModel  by @hlky in #9647\r\n* [CI] replace ubuntu version to 22.04.  by @sayakpaul in #9656\r\n* [docs] Fix xDiT doc image damage  by @Eigensystem in #9655\r\n* [Tests] increase transformers version in `test_low_cpu_mem_usage_with_loading`  by @sayakpaul in #9662\r\n* Flux - soft inpainting via differential diffusion  by @ryanlyn in #9268\r\n* CogView3Plus DiT  by @zRzRzRzRzRzRzR in #9570\r\n* Improve the performance and suitable for NPU computing  by @leisuzz in #9642\r\n* [`Community Pipeline`] Add 🪆Matryoshka Diffusion Models  by @tolgacangoz in #9157\r\n* Added Lora Support to SD3 Img2Img Pipeline  by @SahilCarterr in #9659\r\n* Add pred_original_sample to `if not return_dict` path  by @hlky in #9649\r\n* Convert list/tuple of `SD3ControlNetModel` to `SD3MultiControlNetModel`  by @hlky in #9652\r\n* Convert list/tuple of `HunyuanDiT2DControlNetModel` to `HunyuanDiT2DMultiControlNetModel`  by @hlky in #9651\r\n* Refactor SchedulerOutput and add pred_original_sample in `DPMSolverSDE`, `Heun`, `KDPM2Ancestral` and `KDPM2`  by @hlky in #9650\r\n* Slight performance improvement to `Euler`, `EDMEuler`, `FlowMatchHeun`, `KDPM2Ancestral`  by @hlky in #9616\r\n* [Fix] when run load pretain with local_files_only, local variable 'cached_folder' referenced before assignment  by @RobinXL in #9376\r\n* [Chore] fix import of EntryNotFoundError.  by @sayakpaul in #9676\r\n* Dreambooth lora flux bug 3dtensor to 2dtensor  by @0x-74 in #9653\r\n* refactor image_processor.py file  by @charchit7 in #9608\r\n* [doc] Fix some docstrings in `src/diffusers/training_utils.py`  by @mreraser in #9606\r\n* [docs] refactoring docstrings in `community/hd_painter.py`  by @Jwaminju in #9593\r\n* [docs] refactoring docstrings in `models/embeddings_flax.py`  by @Jwaminju in #9592\r\n* Fix some documentation in ./src/diffusers/models/adapter.py  by @ahnjj in #9591\r\n* [training] CogVideoX-I2V LoRA  by @a-r-r-o-w in #9482\r\n* [authored by @Anghellia) Add support of Xlabs Controlnets #9638  by @yiyixuxu in #9687\r\n* Docs: CogVideoX  by @glide-the in #9578\r\n* Resolves [BUG] 'GatheredParameters' object is not callable  by @charchit7 in #9614\r\n* [LoRA] log a warning when there are missing keys in the LoRA loading.  by @sayakpaul in #9622\r\n* [SD3 dreambooth-lora training] small updates + bug fixes   by @linoytsaban in #9682\r\n* [peft] simple update when unscale   by @sweetcocoa in #9689\r\n* [pipeline] CogVideoX-Fun Control  by @a-r-r-o-w in #9671\r\n* [core] improve VAE encode/decode framewise batching  by @a-r-r-o-w in #9684\r\n* [tests] fix name and unskip CogI2V integration test  by @a-r-r-o-w in #9683\r\n* [Flux] Add advanced training script + support textual inversion inference  by @linoytsaban in #9434\r\n* [refactor] DiffusionPipeline.download  by @a-r-r-o-w in #9557\r\n* [advanced flux lora script] minor updates to readme  by @linoytsaban in #9705\r\n* Fix bug in Textual Inversion Unloading  by @bonlime in #9304\r\n* Add prompt scheduling callback to community scripts  by @hlky in #9718\r\n* [CI] pin max torch version to fix CI errors  by @a-r-r-o-w in #9709\r\n* [Docker] pin torch versions in the dockerfiles.  by @sayakpaul in #9721\r\n* `make  deps_table_update` to fix CI tests  by @a-r-r-o-w in #9720\r\n* [Quantization] Add quantization support for `bitsandbytes`  by @sayakpaul in #9213\r\n* Fix typo in cogvideo pipeline  by @lichenyu20 in #9722\r\n* [Docs] docs to xlabs controlnets.  by @sayakpaul in #9688\r\n* [docs] add docstrings in `pipline_stable_diffusion.py`  by @jeongiin in #9590\r\n* minor doc/test update  by @yiyixuxu in #9734\r\n* [bugfix] reduce float value error when adding noise  by @gameofdimension in #9004\r\n* fix singlestep dpm tests  by @yiyixuxu in #9716\r\n* Fix `schedule_shifted_power` usage in 🪆Matryoshka Diffusion Models  by @tolgacangoz in #9723\r\n* Update sd3 controlnet example  by @DavyMorgan in #9735\r\n* [Fix] Using sharded checkpoints with gated repositories  by @asomoza in #9737\r\n* [bitsandbbytes] follow-ups  by @sayakpaul in #9730\r\n* Fix typos  by @DN6 in #9739\r\n* is_safetensors_compatible fix  by @DN6 in #9741\r\n* Release: v0.31.0 by @sayakpaul (direct commit on v0.31.0-release)\r\n\r\n## Significant community contributions\r\n\r\nThe following contributors have made significant changes to the library over the last release:\r\n\r\n* @ighoshsubho\r\n    * Feature flux controlnet img2img and inpaint pipeline (#9408)\r\n    * flux controlnet control_guidance_start and control_guidance_end implement (#9571)\r\n* @noskill\r\n    * adapt masked im2im pipeline for SDXL (#7790)\r\n* @saqlain2204\r\n    * [Tests] Reduce the model size in the lumina test  (#8985)\r\n    * Add Differential Diffusion to Kolors (#9423)\r\n* @hlky\r\n    * [Schedulers] Add exponential sigmas / exponential noise schedule (#9499)\r\n    * Add Noise Schedule/Schedule Type to Schedulers Overview documentation (#9504)\r\n    * Add exponential sigmas to other schedulers and update docs (#9518)\r\n    * [Schedulers] Add beta sigmas / beta noise schedule (#9509)\r\n    * Add beta sigmas to other schedulers and update docs (#9538)\r\n    * FluxMultiControlNetModel (#9647)\r\n    * Add pred_original_sample to `if not return_dict` path (#9649)\r\n    * Convert list/tuple of `SD3ControlNetModel` to `SD3MultiControlNetModel` (#9652)\r\n    * Convert list/tuple of `HunyuanDiT2DControlNetModel` to `HunyuanDiT2DMultiControlNetModel` (#9651)\r\n    * Refactor SchedulerOutput and add pred_original_sample in `DPMSolverSDE`, `Heun`, `KDPM2Ancestral` and `KDPM2` (#9650)\r\n    * Slight performance improvement to `Euler`, `EDMEuler`, `FlowMatchHeun`, `KDPM2Ancestral` (#9616)\r\n    * Add prompt scheduling callback to community scripts (#9718)\r\n* @yiyixuxu\r\n    * a few fix for SingleFile tests (#9522)\r\n    * update get_parameter_dtype (#9526)\r\n    * flux controlnet fix (control_modes batch & others) (#9507)\r\n    * [sd3] make sure height and size are divisible by `16` (#9573)\r\n    * [authored by @Anghellia) Add support of Xlabs Controlnets #9638 (#9687)\r\n    * minor doc/test update (#9734)\r\n    * fix singlestep dpm tests (#9716)\r\n* @PromeAIpro\r\n    * [examples] add train flux-controlnet scripts in example. (#9324)\r\n* @juancopi81\r\n    * Add PAG support to StableDiffusionControlNetPAGInpaintPipeline  (#8875)\r\n* @glide-the\r\n    * fix: CogVideox train dataset _preprocess_data crop video (#9574)\r\n    * Docs: CogVideoX (#9578)\r\n* @SahilCarterr\r\n    * add PAG support for SD Img2Img (#9463)\r\n    * Added Lora Support to SD3 Img2Img Pipeline (#9659)\r\n* @ryanlyn\r\n    * Flux - soft inpainting via differential diffusion (#9268)\r\n* @zRzRzRzRzRzRzR\r\n    * CogView3Plus DiT (#9570)\r\n* @tolgacangoz\r\n    * [`Community Pipeline`] Add 🪆Matryoshka Diffusion Models (#9157)\r\n    * Fix `schedule_shifted_power` usage in 🪆Matryoshka Diffusion Models (#9723)\r\n* @linoytsaban\r\n    * [SD3 dreambooth-lora training] small updates + bug fixes  (#9682)\r\n    * [Flux] Add advanced training script + support textual inversion inference (#9434)\r\n    * [advanced flux lora script] minor updates to readme (#9705)","publishedAt":"2024-10-22T14:15:27.000Z","fetchedAt":"2026-04-07T17:27:25.622Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.31.0","media":[],"coverageCount":0},{"id":"rel_5oAnnLT_-Sin1jKnBr4Ua","version":"v0.30.3","type":"feature","title":"v0.30.3: CogVideoX Image-to-Video and Video-to-Video","summary":"This patch release adds Diffusers support for the upcoming CogVideoX-5B-I2V release (an Image-to-Video generation model)! The model weights will be av...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"This patch release adds Diffusers support for the upcoming CogVideoX-5B-I2V release (an Image-to-Video generation model)! The model weights will be available by end of the week on the HF Hub at `THUDM/CogVideoX-5b-I2V` ([Link](https://huggingface.co/THUDM/CogVideoX-5b-I2V)). Stay tuned for the release!\r\n\r\nThis release features two new pipelines:\r\n\r\n- CogVideoXImageToVideoPipeline\r\n- CogVideoXVideoToVideoPipeline\r\n\r\nAdditionally, we now have support for tiled encoding in the CogVideoX VAE. This can be enabled by calling the `vae.enable_tiling()` method, and it is used in the new Video-to-Video pipeline to encode sample videos to latents in a memory-efficient manner.\r\n\r\n## CogVideoXImageToVideoPipeline\r\n\r\nThe code below demonstrates how to use the new image-to-video pipeline:\r\n\r\n```python\r\nimport torch\r\nfrom diffusers import CogVideoXImageToVideoPipeline\r\nfrom diffusers.utils import export_to_video, load_image\r\n\r\npipe = CogVideoXImageToVideoPipeline.from_pretrained(\"THUDM/CogVideoX-5b-I2V\", torch_dtype=torch.bfloat16)\r\npipe.to(\"cuda\")\r\n\r\n# Optionally, enable memory optimizations.\r\n# If enabling CPU offloading, remember to remove `pipe.to(\"cuda\")` above\r\npipe.enable_model_cpu_offload()\r\npipe.vae.enable_tiling()\r\n\r\nprompt = \"An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot.\"\r\nimage = load_image(\r\n    \"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg\"\r\n)\r\nvideo = pipe(image, prompt, use_dynamic_cfg=True)\r\nexport_to_video(video.frames[0], \"output.mp4\", fps=8)\r\n```\r\n\r\n<table align=center>\r\n<tr>\r\n  <td align=center colspan=1><img src=\"https://github.com/user-attachments/assets/1c7c1d86-f97e-44dd-9b17-4fec2bbc2b1a\" /></td>\r\n  <td align=center colspan=1><video src=\"https://github.com/user-attachments/assets/a115372e-c539-4ca0-b0d0-770d62862257\"> Your broswer does not support the video tag. </video></td>\r\n</tr>\r\n</table>\r\n\r\n## CogVideoXVideoToVideoPipeline\r\n\r\nThe code below demonstrates how to use the new video-to-video pipeline:\r\n\r\n```python\r\nimport torch\r\nfrom diffusers import CogVideoXDPMScheduler, CogVideoXVideoToVideoPipeline\r\nfrom diffusers.utils import export_to_video, load_video\r\n\r\n# Models: \"THUDM/CogVideoX-2b\" or \"THUDM/CogVideoX-5b\"\r\npipe = CogVideoXVideoToVideoPipeline.from_pretrained(\"THUDM/CogVideoX-5b-trial\", torch_dtype=torch.bfloat16)\r\npipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config)\r\npipe.to(\"cuda\")\r\n\r\ninput_video = load_video(\r\n    \"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4\"\r\n)\r\nprompt = (\r\n    \"An astronaut stands triumphantly at the peak of a towering mountain. Panorama of rugged peaks and \"\r\n    \"valleys. Very futuristic vibe and animated aesthetic. Highlights of purple and golden colors in \"\r\n    \"the scene. The sky is looks like an animated/cartoonish dream of galaxies, nebulae, stars, planets, \"\r\n    \"moons, but the remainder of the scene is mostly realistic.\"\r\n)\r\n\r\nvideo = pipe(\r\n    video=input_video, prompt=prompt, strength=0.8, guidance_scale=6, num_inference_steps=50\r\n).frames[0]\r\nexport_to_video(video, \"output.mp4\", fps=8)\r\n```\r\n\r\n<table align=center>\r\n<tr>\r\n<td align=center><video src=\"https://github.com/user-attachments/assets/bc9273ff-e459-42f9-af1e-c9b084b28f4d\"> Your browser does not support the video tag. </video></td>\r\n</tr>\r\n</table>\r\n\r\nShoutout to @tin2tin for the awesome demonstration!\r\n\r\nRefer to our [documentation](https://huggingface.co/docs/diffusers/api/pipelines/cogvideox) to learn more about it.\r\n\r\n## All commits\r\n\r\n* [core] Support VideoToVideo with CogVideoX  by @a-r-r-o-w in #9333\r\n* [core] CogVideoX memory optimizations in VAE encode  by @a-r-r-o-w in #9340\r\n* [CI] Quick fix for Cog Video Test  by @DN6 in #9373\r\n* [refactor] move positional embeddings to patch embed layer for CogVideoX  by @a-r-r-o-w in #9263\r\n* CogVideoX-5b-I2V support  by @zRzRzRzRzRzRzR in #9418","publishedAt":"2024-09-17T06:22:05.000Z","fetchedAt":"2026-04-07T17:27:25.622Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.30.3","media":[],"coverageCount":0},{"id":"rel_CeQ7MMqzC9UHGMDF7Lb_1","version":"v0.30.2","type":"feature","title":"v0.30.2: Update from single file default repository","summary":"## All commits\r\n\r\n* update runway repo for single_file  by @yiyixuxu in #9323\r\n* Fix Flux CLIP prompt embeds repeat for num_images_per_prompt > 1  by ...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## All commits\r\n\r\n* update runway repo for single_file  by @yiyixuxu in #9323\r\n* Fix Flux CLIP prompt embeds repeat for num_images_per_prompt > 1  by @DN6  in #9280\r\n* [IP Adapter] Fix cache_dir and local_files_only for image encoder by @asomoza in #9272","publishedAt":"2024-08-31T00:23:16.000Z","fetchedAt":"2026-04-07T17:27:25.622Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.30.2","media":[],"coverageCount":0},{"id":"rel_I9lO4y_2gGLZqD85QByl3","version":"v0.30.1","type":"feature","title":"V0.30.1: CogVideoX-5B & Bug fixes","summary":"## CogVideoX-5B\r\n\r\nThis patch release adds diffusers support for the upcoming CogVideoX-5B release! The model weights will be available next week on t...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"## CogVideoX-5B\r\n\r\nThis patch release adds diffusers support for the upcoming CogVideoX-5B release! The model weights will be available next week on the Huggingface Hub at `THUDM/CogVideoX-5b`. Stay tuned for the release!\r\n\r\nAdditionally, we have implemented VAE tiling feature, which reduces the memory requirement for CogVideoX models. With this update, the total memory requirement is now 12GB for CogVideoX-2B and 21GB for CogVideoX-5B (with CPU offloading). To Enable this feature, simply call `enable_tiling()` on the VAE.\r\n\r\nThe code below shows how to generate a video with CogVideoX-5B\r\n\r\n```python\r\nimport torch\r\nfrom diffusers import CogVideoXPipeline\r\nfrom diffusers.utils import export_to_video\r\n\r\nprompt = \"Tracking shot,late afternoon light casting long shadows,a cyclist in athletic gear pedaling down a scenic mountain road,winding path with trees and a lake in the background,invigorating and adventurous atmosphere.\"\r\n\r\npipe = CogVideoXPipeline.from_pretrained(\r\n    \"THUDM/CogVideoX-5b\",\r\n    torch_dtype=torch.bfloat16\r\n)\r\n\r\npipe.enable_model_cpu_offload()\r\npipe.vae.enable_tiling()\r\n\r\nvideo = pipe(\r\n    prompt=prompt,\r\n    num_videos_per_prompt=1,\r\n    num_inference_steps=50,\r\n    num_frames=49,\r\n    guidance_scale=6,\r\n).frames[0]\r\n\r\nexport_to_video(video, \"output.mp4\", fps=8)\r\n```\r\n\r\nhttps://github.com/user-attachments/assets/c2d4f7e8-ef86-4da6-8085-cb9f83f47f34\r\n\r\nRefer to our [documentation](https://huggingface.co/docs/diffusers/api/pipelines/cogvideox) to learn more about it. \r\n\r\n## All commits\r\n\r\n- Update Video Loading/Export to use `imageio` by @DN6 in #9094\r\n- [refactor] CogVideoX followups + tiled decoding support by @a-r-r-o-w in #9150\r\n- Add Learned PE selection for Auraflow by @cloneofsimo in #9182\r\n- [Single File] Fix configuring scheduler via legacy kwargs by @DN6 in #9229\r\n- [Flux LoRA] support parsing alpha from a flux lora state dict. by @sayakpaul in #9236\r\n- [tests] fix broken xformers tests by @a-r-r-o-w in #9206\r\n- Cogvideox-5B Model adapter change by @zRzRzRzRzRzRzR in #9203\r\n- [Single File] Support loading Comfy UI Flux checkpoints by @DN6 in #9243\r\n\r\n","publishedAt":"2024-08-24T07:26:30.000Z","fetchedAt":"2026-04-07T17:27:25.588Z","url":"https://github.com/huggingface/diffusers/releases/tag/v0.30.1","media":[],"coverageCount":0}],"pagination":{"nextCursor":"2024-08-24T07:26:30.000Z|2026-04-07T17:27:25.588Z|rel_I9lO4y_2gGLZqD85QByl3","limit":20},"summaries":{"rolling":{"windowDays":90,"summary":"Diffusers shifted toward compositional pipeline architecture with Modular Diffusers, letting developers build custom workflows by mixing reusable blocks instead of writing monolithic pipelines from scratch. The release added support for new image and video generation models including Z Image Omni Base, while subsequent patches fixed type hint handling in modular pipelines and LoRA loading for Flux Klein.","releaseCount":2,"generatedAt":"2026-04-07T17:27:30.394Z"},"monthly":[{"year":2026,"month":3,"summary":"Modular Diffusers shipped as the month's centerpiece, introducing composable pipeline building blocks as an alternative to monolithic `DiffusionPipeline` implementations. Alongside this architectural addition, the release brought new image and video pipelines including Z Image Omni Base, expanded core library improvements, and follow-up fixes for type hints in modular pipelines and Flux Klein LoRA loading.","releaseCount":2,"generatedAt":"2026-04-07T17:27:33.943Z"}]}}