Diffusers v0.39.0

New Pipelines

Cosmos 3

Cosmos 3 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.

• PR: https://github.com/huggingface/diffusers/pull/13818
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/cosmos3

Thanks to @atharvajoshi10, @yzhautouskay, and @MaciejBalaNV for the contributions.

Ideogram 4

Ideogram 4 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.

• PR: https://github.com/huggingface/diffusers/pull/13859
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/ideogram4

Thanks to @JinLiIdeogram for the contribution.

Krea 2

Krea 2 (K2) 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.

• PR: https://github.com/huggingface/diffusers/pull/14045
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/krea2

Thanks to @EleaZhong and @Abhinay1997 for the contribution.

DreamLite

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.

• PR: https://github.com/huggingface/diffusers/pull/13815
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/dreamlite

Thanks to @Carlofkl for the contribution.

PRX Pixel

PRXPixel 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).

• PR: https://github.com/huggingface/diffusers/pull/13928
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/prx_pixel

Thanks to @DavidBert for the contribution.

Motif-Video

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.

• PR: https://github.com/huggingface/diffusers/pull/13551
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/motif_video

Thanks to @waitingcheung for the contribution.

AnyFlow

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.

• PR: https://github.com/huggingface/diffusers/pull/13745
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/anyflow

Thanks to @Enderfga for the contribution.

JoyAI-Image-Edit

JoyAI-Image 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.

• PR: https://github.com/huggingface/diffusers/pull/13444
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/joyimage_edit

Thanks to @Moran232 for the contribution.

DiffusionGemma

DiffusionGemma 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.

• PR: https://github.com/huggingface/diffusers/pull/13986
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/diffusion_gemma

Anima

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.

It reuses the CosmosTransformer3DModel with a Qwen3 text encoder, a T5-token text conditioner, and the AutoencoderKLQwenImage VAE.

• PR: https://github.com/huggingface/diffusers/pull/13732
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/anima

Thanks to @rmatif for the contribution.

LTX-2.X IC LoRA and HDR Pipelines

New LTX2InContextPipeline (in-context LoRA) and LTX2HDRPipeline extend the LTX-2 family with in-context conditioning and HDR video generation.

• PR: https://github.com/huggingface/diffusers/pull/13572
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/ltx2

Modular Pipeline Support

• We added a modular pipeline for Stable Diffusion 3 (SD3) in https://github.com/huggingface/diffusers/pull/13324 (thanks to @AlanPonnachan).
• We added a modular pipeline for Anima in https://github.com/huggingface/diffusers/pull/13732 (thanks to @rmatif).
• LoRA loading is now enabled on ErnieImageModularPipeline (#13948) and Ideogram4ModularPipeline (#13980), thanks to @SamuelTallet.

Core Library

• AutoRound quantization integration
• safetensors support in the TorchAO backend and _dequantize for the TorchAO quantizer
• BitsAndBytes quantization on MPS
• AutoPipelineForText2Audio
• AWS Neuron (Trainium/Inferentia) as an officially supported device with torch.compile compatibility
• Bump safetensors to 0.8.0
• Minimum supported torch version is now 2.6
• Eliminate GPU sync overhead and CPU→GPU transfers across the LTX-2 pipeline

All commits

• [CI] Update all workflows with permissions by @DN6 in #13672
• [agents docs] update models.md with class attributes and attention mask by @yiyixuxu in #13665
• Fix ignored generator in FlowMatchEulerDiscreteScheduler by @RobbinMarcus in #13678
• [core] remove txt_seq_lens from qwen transformer. by @sayakpaul in #13674
• [tests] fix lora tests involving clip. by @sayakpaul in #13675
• post release 0.38.0 by @sayakpaul in #13670
• Fix NameError in ZImageOmniPipeline when guidance_scale=0 by @Ricardo-M-L in #13527
• Enable TorchAO int4wo quantization tests on XPU by @jiqing-feng in #13537
• [CI] QOL improvement for PR size labeler by @DN6 in #13554
• Fix BucketBatchSampler cache alignment in DreamBooth scripts by @azolotenkov in #13353
• chore: update pr_labeler.yml by @hf-security-analysis[bot] in #13685
• Address ernie-image review findings #13577 by @akshan-main in #13663
• feat: Add Modular Pipeline for Stable Diffusion 3 (SD3) by @AlanPonnachan in #13324
• Update attention_backends.md to update FA3 minimum support to Ampere by @sayakpaul in #13283
• [CI] Bump style-bot SHA + switch to GitHub App by @paulinebm in #13690
• [feat] JoyAI-JoyImage-Edit support by @Moran232 in #13444
• Add LoRA support for Cosmos Predict 2.5 and fix pipeline to match official Cosmos repo by @terarachang in #13664
• Eliminate GPU sync overhead and CPU→GPU transfers across LTX2 pipeline by @ViktoriiaRomanova in #13564
• Gate deep imports from torch.distributed by @hlky in #13673
• Bump diffusers from 0.20.1 to 0.38.0 in /examples/research_projects/realfill by @dependabot[bot] in #13692
• Reduce WanAnimate TorchAO test input sizes to prevent OOM by @jiqing-feng in #13541
• add SP support for flash_varlen_hub backend by @zhtmike in #13479
• [ci] allow claude to open PRs for certain instructions. by @sayakpaul in #13536
• [ci] remove compel. by @sayakpaul in #13715
• styling fix. by @sayakpaul (direct commit on v0.39.0-release)
• better usage of UV_PRERELEASE=allow by @sayakpaul in #13716
• [docs] add magcache to caching api listing by @sayakpaul in #13714
• [tests] refactor autoencoderkl tests by @sayakpaul in #13368
• [docs] add docs for JoyAI-Image-Edit by @feice-huang in #13726
• [tests] add attention backend tests. by @sayakpaul in #13174
• Install transformers from main for doc and staging by @sayakpaul in #13723
• Update Flax removal version by @DN6 in #13729
• examples/dreambooth: fix LR scheduler step count for multi-GPU in train_dreambooth_lora_sd3.py by @Dev-X25874 in #13731
• Serge reviewer by @sayakpaul in #13735
• [ci] switch to a more unique name by @sayakpaul in #13738
• fix autoencoder memory tests by @sayakpaul in #13734
• Fix GGUF to Work Better with modules_to_not_convert / keep_in_fp32_modules by @dg845 in #13697
• [tests] refactor ltx2 autoencoder tests to use latest mixins by @sayakpaul in #13739
• feat: Add Motif-Video model and pipelines by @waitingcheung in #13551
• Update contribution guidelines by @DN6 in #13753
• [agents] add a section on tests in the ai skill and integration guides. by @sayakpaul in #13752
• Add LTX-2.X IC LoRA and HDR Pipelines by @dg845 in #13572
• [tests] Fix controlnet tests by @sayakpaul in #13736
• [tests] fix bitsandbytes compile tests for flux. by @sayakpaul in #13750
• [core] minimum torch version is 2.6 by @sayakpaul in #13725
• [tests] fix lora checkpoint serialization issues by @sayakpaul in #13676
• fix(randn_tensor): compare device.type, not torch.device, when suppressing MPS info log by @Ricardo-M-L in #13508
• [LLADA2] Fix llada2 review #13598 by @kashif in #13698
• fix lfs pointer rejection problems for hub tests by @sayakpaul in #13733
• Fix training gradient underflow in quantization tests by @jiqing-feng in #13539
• examples/dreambooth: fix missing weighting chunk when using prior preservation in Flux and SD3 LoRA training by @Dev-X25874 in #13743
• Implement _dequantize for TorchAO quantizer by @jiqing-feng in #13538
• fix device mismatch issue for HiDreamTransformerTests by @kaixuanliu in #13766
• [docs] remove pipeline examples section by @stevhliu in #13771
• [CI] Replace print_env step in CI with diffusers-cli env by @DN6 in #13662
• update safetensors.torch._tobytes to safetensors.torch._to_ndarray by @sywangyi in #13770
• [agents docs] update pipelines.md: by @yiyixuxu in #13570
• fix(gguf): correct mismatched-shape error message in check_quantized_param_shape by @Ricardo-M-L in #13504
• [CI] claude_review: target source PR's branch for follow-up PRs by @yiyixuxu in #13774
• [WIP] chore: add utilities to check if call/forward methods are documented. by @sayakpaul in #13758
• Fix OOM in WanAnimate BitsAndBytes Training Test by @jiqing-feng in #13777
• ci: use uv overrides to make sure tokenizers install from <=0.23.0 under subs by @sayakpaul in #13767
• [LTX 2.3] update docs by @linoytsaban in #13788
• [docs] fix ace step checkpoint id. by @sayakpaul in #13787
• Add AnyFlow Any-Step Video Diffusion Pipelines (Bidirectional + FAR Causal) by @Enderfga in #13745
• Initialize ZImage pad tokens deterministically by @sywangyi in #13805
• note: torch.zeros -> torch.empty by @sayakpaul in #13807
• chore: enable Dependabot weekly GitHub Actions bumps by @hf-dependantbot-rollout[bot] in #13812
• [ci] shorten serge name. by @sayakpaul in #13795
• Adding Cosmos 3 to Diffusers by @atharvajoshi10 in #13818
• This PR updates the Stable Diffusion IP-Adapter integration by @sywangyi in #13810
• [AnyFlow] FAR: standalone causal-mask builder + torch.compile follow-up by @Enderfga in #13792
• Update repo_id for FLASH_4_HUB in attention_dispatch by @WaterKnight1998 in #13822
• Pin torchvision, torch, and torchaudio versions by @sayakpaul in #13757
• [docs] Follow ups for consistent forward docstrings by @sayakpaul in #13779
• refactor sana transformer tests by @akshan-main in #13826
• Fix redundant Z-Image terminal timestep by @rootonchair in #13730
• override torch stuff to prevent them from getting updated by @sayakpaul in #13831
• Add Anima modular pipeline by @rmatif in #13732
• [Feat] support AutoPipelineForText2Audio by @RuixiangMa in #13511
• moved to a webhook by @tarekziade in #13836
• refactor autoencoder tests (asymmetric_kl, ltx_video) by @akshan-main in #13845
• Fix duplicate safetensors.load_file call in _onload_from_disk when st… by @gagandhakrey in #13851
• Fix AttributeError in onnxruntime train_unconditional (args.report_to → args.logger) by @Ricardo-M-L in #13524
• [fix] CLIPTextModel with transformers >= 5.6 and from_single_file by @asomoza in #13843
• [tests] migrate group offloading tests to pytest by @sayakpaul in #13234
• [tests] refactor caching tests. by @sayakpaul in #13235
• Allow bucket reshuffling with DreamBooth caches by @azolotenkov in #13712
• [Neuron] Add AWS Neuron (Trainium/Inferentia) as an officially supported device by @JingyaHuang in #13289
• refactor autoencoder_magvit tests by @akshan-main in #13834
• refactor autoencoder_hunyuan_video tests by @akshan-main in #13835
• refactor autoencoder_kl_cogvideox tests by @akshan-main in #13840
• refactor autoencoder tests (vq, kvae_video, oobleck, consistency_decoder, tiny, vidtok) by @akshan-main in #13849
• updatge the test marigold to make it pass in xpu by @sywangyi in #13856
• [CI] Fix torch_device import in AutoencoderTesterMixin by @DN6 in #13852
• Add Ideogram 4 by @apolinario in #13859
• Add structured prompt upsampling to Ideogram4 by @apolinario in #13860
• [ci] add hook tests to our CI. by @sayakpaul in #13848
• fix kvae gradient checkpointing tests by @sayakpaul (direct commit on v0.39.0-release)
• Revert "fix kvae gradient checkpointing tests" by @sayakpaul (direct commit on v0.39.0-release)
• [tests] fix anyflow tests by @sayakpaul in #13855
• [CI] Refactor LTX Transformer Tests by @DN6 in #13254
• [CI] Refactor Bria Transformer Tests by @DN6 in #13341
• [CI] Refactor Chronoedit, PRX, EasyAnimate, Ovis transformer tests by @DN6 in #13347
• Add Cosmos3 action generation support by @yzhautouskay in #13823
• [docs] update philosophy.md (finally) by @yiyixuxu in #13808
• fix kvae gradient checkpointing tests by @sayakpaul in #13865
• [tests] Improve ideogram4 tests by @sayakpaul in #13862
• [tests] migrate test_hooks.py to pytest by @sayakpaul in #13242
• fix chronoedit tests on PRs by @sayakpaul in #13870
• Fix the QwenImage Attention mask under Ulysses SP by @zhtmike in #13756
• Add from_single_file support to ErnieImageTransformer2DModel by @akshan-main in #13727
• switch to a webhook by @tarekziade in #13884
• [chore] fix styling by @sayakpaul in #13885
• [cli] report all quant backends in diffusers-cli env. by @sayakpaul in #13728
• fix marigold depth failure in xpu and A100 by @sywangyi in #13886
• refactor autoencoder tests (temporal decoder, cosmos, kvae, mochi) by @akshan-main in #13832
• refactor controlnet_cosmos tests by @akshan-main in #13847
• refactor unet_spatiotemporal tests by @akshan-main in #13891
• Fix fp16 LoRA unscale crash after validation in train_dreambooth_lora.py by @HaozheZhang6 in #13895
• [CI] Refactor Chroma , LongCat and HiDream Transformer Tests by @DN6 in #13345
• [CI] Refactor Skyreels, Lumina, Ominigen, Mochi transformer tests by @DN6 in #13348
• [CI] Refactor SD3 Transformer Test by @DN6 in #13340
• refactor unet tests (3d_condition, motion, controlnetxs) by @akshan-main in #13897
• refactor unet_1d tests by @akshan-main in #13898
• refactor unet_2d tests by @akshan-main in #13901
• [chore] log quant config to the user_agent by @sayakpaul in #13850
• Integrate AutoRound into Diffusers by @xin3he in #13552
• [tests] refactor UNet model tests to align with the new pattern by @sayakpaul in #13153
• [tests] fix vidtok tests by @sayakpaul in #13894
• quant config logging by @sayakpaul in #13906
• Use device_map="auto" in single file tests to support large models on limited GPU memory by @jiqing-feng in #13816
• Fix incorrect batch temporal IDs for cond_model_input in Flux2 Klein img2img training by @HaozheZhang6 in #13923
• Incorporate safetensors support to TorchAO by @hlky in #13719
• [Pipelines] Add DreamLite text-to-image and image-edit pipelines by @Carlofkl in #13815
• [.ai] add self-review skill by @yiyixuxu in #13917
• update PR template and highlight AI-agent setup for contributors by @yiyixuxu in #13913
• [CI] implement a bot to remind prs to link issues if not. by @sayakpaul in #13744
• Point "Coding with AI agents" links at the rendered docs site by @yiyixuxu in #13952
• [tests] fix consistency decoder tests by @sayakpaul in #13905
• Add tutorial translations in Chinese by @liwd190019 in #13932
• Make root PHILOSOPHY.md a symlink to the docs philosophy page by @yiyixuxu in #13954
• fix(flux): enable true CFG with precomputed negative embeds by @akshan-main in #13957
• Enable LoRA loading on ErnieImageModularPipeline by @SamuelTallet in #13948
• Fix typo in AutoModel by @neo in #13889
• keep the agent symlinks by @yiyixuxu in #13968
• [CI] allow running tests as PR comments through a bot by @sayakpaul in #13873
• Add Cosmos3 video2video generation support by @yzhautouskay in #13896
• [CI] Refactor Z Image Transformer Tests by @DN6 in #13253
• fix untrusted fork secret mixing by @sayakpaul in #13970
• start by @sayakpaul (direct commit on v0.39.0-release)
• Revert "start" by @sayakpaul (direct commit on v0.39.0-release)
• Add Sound Encoder to Cosmos3 by @MaciejBalaNV in #13911
• Add PRXPixelPipeline: pixel-space PRX text-to-image pipeline by @DavidBert in #13928
• [tests] port final set of model tests and others by @sayakpaul in #13974
• Add Ideogram4LoraLoaderMixin (LoRA loading for Ideogram4) by @linoytsaban in #13921
• Enable LoRA loading on Ideogram4ModularPipeline by @SamuelTallet in #13980
• [Neuron] Enable torch.compile compatibility with Neuron device by @JingyaHuang in #13485
• ci: don't remind on prs from admins, etc. by @sayakpaul in #13965
• ci: use hosted runners by @tarekziade in #13987
• Fix LTX2 connector token/register layout (regression from #13564) by @Boffee in #13931
• Fix Ideogram4MRoPE collapsing under torch.autocast (compute rotary in float32) by @HaozheZhang6 in #13922
• [Fix] Fix three final_layer LoRA conversion bugs in _convert_sd_scripts_to_ai_toolkit by @lcheng321 in #14001
• Add Krea 2 (K2) text-to-image pipeline and transformer by @yiyixuxu in #14045
• [.ai doc] Refine .ai attention-mask and component-mutation guidance by @yiyixuxu in #13982
• Enable BitsAndBytes quantization in MPS by @LucasSte in #13915
• fix(flux): tighten check_inputs validation by @akshan-main in #13955
• Krea 2 LoRA DreamBooth trainer by @apolinario in #14046
• Fix model cuda tests by @sayakpaul in #13975
• [.ai] document single-file model layout and "don't reimplement Diffus… by @yiyixuxu in #14048
• fix claude code review fix in PRs. by @sayakpaul in #14058
• fix(bria_fibo): fix guidance_embeds, prompt_embeds, tensor-image and multi-image crashes by @akshan-main in #13981
• [tests] implement base model output caching in model-level tests by @sayakpaul in #14059
• [discrete diffusion] Add DiffusionGemma pipeline and schedulers by @kashif in #13986
• Add from_single_file support for SkyReelsV2 and ChronoEdit transformers by @HaozheZhang6 in #13946
• multi-GPU VAE Fix for Cosmos 3 by @atharvajoshi10 in #13924
• docs: fix repeated word typo in set_timesteps docstring by @ramkumar27072006 in #13876
• feat: bump safetensors to 0.8.0 by @porunov in #13971
• Fix DreamLite legacy block type aliases by @ElectricGoal in #14066
• Fix Kohya UNet LoRA key conversion for conv_in/conv_out/time_embedding by @dxqb in #14006
• [Tests] Skip layerwise casting tests on devices without float8_e4m3fn support by @GiGiKoneti in #14073
• [lora] add non-diffusers LoRA loading support for Krea 2 LoRAs by @linoytsaban in #14074
• Add doc pages for the DiffusionGemma schedulers by @kashif in #14092
• [chore] update to 2026 finally. by @sayakpaul in #14079
• fix #14063 for Kandinsky5 pipeline load with device_map=balanced by @kaixuanliu in #14050
• Complete Kohya LoRA conversion for Qwen and Z-Image by @dxqb in #14080
• Ideogram4 lora training by @apolinario in #13861
• ovis_image: fix guidance_scale / max_sequence_length / batched CFG / precomputed embeds + add pipeline test by @HaozheZhang6 in #13944
• [docs] fix qwen tokenizer in docstrings. by @sayakpaul in #14098
• Bump transformers from 4.47.0 to 5.3.0 in /examples/cogview4-control by @dependabot[bot] in #14109
• Fix mutable default args in lora_base.py by @PrakshaaleJain in #14064
• Fix FA3 varlen wrapper when hub kernel returns single tensor by @ in #14102
• support loading pipeline from transformer style (flat) repo by @yiyixuxu in #14096
• diffusers test installation package by @sayakpaul in #14078
• [tests] fix test_from_save_pretrained_dtype_inference by @sayakpaul in #13872
• Release: v0.39.0-release by @sayakpaul (direct commit on v0.39.0-release)

Significant community contributions

The following contributors have made significant changes to the library over the last release:

• @DN6
  • [CI] Update all workflows with permissions (#13672)
  • [CI] QOL improvement for PR size labeler (#13554)
  • Update Flax removal version (#13729)
  • Update contribution guidelines (#13753)
  • [CI] Replace print_env step in CI with diffusers-cli env (#13662)
  • [CI] Fix torch_device import in AutoencoderTesterMixin (#13852)
  • [CI] Refactor LTX Transformer Tests (#13254)
  • [CI] Refactor Bria Transformer Tests (#13341)
  • [CI] Refactor Chronoedit, PRX, EasyAnimate, Ovis transformer tests (#13347)
  • [CI] Refactor Chroma , LongCat and HiDream Transformer Tests (#13345)
  • [CI] Refactor Skyreels, Lumina, Ominigen, Mochi transformer tests (#13348)
  • [CI] Refactor SD3 Transformer Test (#13340)
  • [CI] Refactor Z Image Transformer Tests (#13253)
• @yiyixuxu
  • [agents docs] update models.md with class attributes and attention mask (#13665)
  • [agents docs] update pipelines.md: (#13570)
  • [CI] claude_review: target source PR's branch for follow-up PRs (#13774)
  • [docs] update philosophy.md (finally) (#13808)
  • [.ai] add self-review skill (#13917)
  • update PR template and highlight AI-agent setup for contributors (#13913)
  • Point "Coding with AI agents" links at the rendered docs site (#13952)
  • Make root PHILOSOPHY.md a symlink to the docs philosophy page (#13954)
  • keep the agent symlinks (#13968)
  • Add Krea 2 (K2) text-to-image pipeline and transformer (#14045)
  • [.ai doc] Refine .ai attention-mask and component-mutation guidance (#13982)
  • [.ai] document single-file model layout and "don't reimplement Diffus… (#14048)
  • support loading pipeline from transformer style (flat) repo (#14096)
• @akshan-main
  • Address ernie-image review findings #13577 (#13663)
  • refactor sana transformer tests (#13826)
  • refactor autoencoder tests (asymmetric_kl, ltx_video) (#13845)
  • refactor autoencoder_magvit tests (#13834)
  • refactor autoencoder_hunyuan_video tests (#13835)
  • refactor autoencoder_kl_cogvideox tests (#13840)
  • refactor autoencoder tests (vq, kvae_video, oobleck, consistency_decoder, tiny, vidtok) (#13849)
  • Add from_single_file support to ErnieImageTransformer2DModel (#13727)
  • refactor autoencoder tests (temporal decoder, cosmos, kvae, mochi) (#13832)
  • refactor controlnet_cosmos tests (#13847)
  • refactor unet_spatiotemporal tests (#13891)
  • refactor unet tests (3d_condition, motion, controlnetxs) (#13897)
  • refactor unet_1d tests (#13898)
  • refactor unet_2d tests (#13901)
  • fix(flux): enable true CFG with precomputed negative embeds (#13957)
  • fix(flux): tighten check_inputs validation (#13955)
  • fix(bria_fibo): fix guidance_embeds, prompt_embeds, tensor-image and multi-image crashes (#13981)
• @AlanPonnachan
  • feat: Add Modular Pipeline for Stable Diffusion 3 (SD3) (#13324)
• @Moran232
  • [feat] JoyAI-JoyImage-Edit support (#13444)
• @terarachang
  • Add LoRA support for Cosmos Predict 2.5 and fix pipeline to match official Cosmos repo (#13664)
• @dg845
  • Fix GGUF to Work Better with modules_to_not_convert / keep_in_fp32_modules (#13697)
  • Add LTX-2.X IC LoRA and HDR Pipelines (#13572)
• @waitingcheung
  • feat: Add Motif-Video model and pipelines (#13551)
• @kashif
  • [LLADA2] Fix llada2 review #13598 (#13698)
  • [discrete diffusion] Add DiffusionGemma pipeline and schedulers (#13986)
  • Add doc pages for the DiffusionGemma schedulers (#14092)
• @linoytsaban
  • [LTX 2.3] update docs (#13788)
  • Add Ideogram4LoraLoaderMixin (LoRA loading for Ideogram4) (#13921)
  • [lora] add non-diffusers LoRA loading support for Krea 2 LoRAs (#14074)
• @Enderfga
  • Add AnyFlow Any-Step Video Diffusion Pipelines (Bidirectional + FAR Causal) (#13745)
  • [AnyFlow] FAR: standalone causal-mask builder + torch.compile follow-up (#13792)
• @atharvajoshi10
  • Adding Cosmos 3 to Diffusers (#13818)
  • multi-GPU VAE Fix for Cosmos 3 (#13924)
• @rmatif
  • Add Anima modular pipeline (#13732)
• @JingyaHuang
  • [Neuron] Add AWS Neuron (Trainium/Inferentia) as an officially supported device (#13289)
  • [Neuron] Enable torch.compile compatibility with Neuron device (#13485)
• @apolinario
  • Add Ideogram 4 (#13859)
  • Add structured prompt upsampling to Ideogram4 (#13860)
  • Krea 2 LoRA DreamBooth trainer (#14046)
  • Ideogram4 lora training (#13861)
• @yzhautouskay
  • Add Cosmos3 action generation support (#13823)
  • Add Cosmos3 video2video generation support (#13896)
• @xin3he
  • Integrate AutoRound into Diffusers (#13552)
• @Carlofkl
  • [Pipelines] Add DreamLite text-to-image and image-edit pipelines (#13815)
• @liwd190019
  • Add tutorial translations in Chinese (#13932)
• @MaciejBalaNV
  • Add Sound Encoder to Cosmos3 (#13911)
• @DavidBert
  • Add PRXPixelPipeline: pixel-space PRX text-to-image pipeline (#13928)