29 Pull requests merged by 13 people

• [docs] Install

  #12026 merged Aug 4, 2025

• fix the rest for all GPUs in CI

  #12064 merged Aug 4, 2025

• enable all gpus when running ci.

  #12062 merged Aug 4, 2025

• CI fixing

  #12059 merged Aug 4, 2025

• fix(qwen-image): update vae license

  #12063 merged Aug 4, 2025

• Cross attention module to Wan Attention

  #12058 merged Aug 4, 2025

• tests + minor refactor for QwenImage

  #12057 merged Aug 4, 2025

• [wan2.2] follow-up

  #12024 merged Aug 4, 2025

• Qwen-Image

  #12055 merged Aug 3, 2025

• Update autoencoder_kl_cosmos.py

  #12045 merged Aug 2, 2025

• Fix type of force_upcast to bool

  #12046 merged Aug 2, 2025

• [LoRA] support lightx2v lora in wan

  #12040 merged Aug 2, 2025

• Allow SD pipeline to use newer schedulers, eg: FlowMatch

  #12015 merged Aug 1, 2025

• [wan2.2] fix vae patches

  #12041 merged Aug 1, 2025

• [training-scripts] Make pytorch examples UV-compatible

  #12000 merged Jul 31, 2025

• [Fix] huggingface-cli to hf missed files

  #12008 merged Jul 30, 2025

• [docs] Update index

  #12020 merged Jul 30, 2025

• [core] support attention backends for LTX

  #12021 merged Jul 30, 2025

• wan2.2 i2v FirstBlockCache fix

  #12013 merged Jul 30, 2025

• [wan2.2] add 5b i2v

  #12006 merged Jul 30, 2025

• [docs] Fix link

  #12018 merged Jul 29, 2025

• [docs] quant_kwargs

  #11712 merged Jul 29, 2025

• [docs] include lora fast post.

  #11993 merged Jul 29, 2025

• [modular] add Modular flux for text-to-image

  #11995 merged Jul 29, 2025

• feat: add flux kontext

  #11985 merged Jul 29, 2025

• Fix huggingface-hub failing tests

  #11994 merged Jul 29, 2025

• [refactor] Wan single file implementation

  #11918 merged Jul 29, 2025

• [refactor] some shared parts between hooks + docs

  #11968 merged Jul 29, 2025

• [WIP] Wan2.2

  #12004 merged Jul 28, 2025

14 Pull requests opened by 9 people

• Bria 3 2 pipeline

  #12010 opened Jul 29, 2025

• Fixed "NameError: name 'ftfy' is not defined" in Wan pipeline by directly importing ftfy.

  #12023 opened Jul 30, 2025

• [lora] factor out the overlaps in `save_lora_weights()`.

  #12027 opened Jul 31, 2025

• [wip][core] parallel loading of shards

  #12028 opened Jul 31, 2025

• Add IP-Adapter

  #12030 opened Jul 31, 2025

• try to use deepseek with an agent to auto i18n to zh

  #12032 opened Jul 31, 2025

• Add Flix Fill ControlNet

  #12035 opened Jul 31, 2025

• Add UV script comment block

  #12036 opened Jul 31, 2025

• support `hf_quantizer` in cache warmup.

  #12043 opened Aug 1, 2025

• Helper functions to return skip-layer compatible layers

  #12048 opened Aug 3, 2025

• gguf new quant type support (with demo)

  #12049 opened Aug 3, 2025

• `UNet2DConditionModel`: add support for QK Normalization by propagating `qk_norm` value from config through to child attention modules

  #12051 opened Aug 3, 2025

• [wip] feat: support lora in qwen image and training script

  #12056 opened Aug 4, 2025

• enable compilation in qwen image.

  #12061 opened Aug 4, 2025

10 Issues closed by 7 people

• Invalid API call in Cosmos VAE Encoder

  #12025 closed Aug 2, 2025

• FLUX.1-Kontext-dev Support for GGUF Quantized Model

  #11962 closed Aug 2, 2025

• Support training variance learning (Improved DDPM) with VLB loss.

  #11998 closed Aug 2, 2025

• Kontext pipeline resizing image even if it is within PREFERRED_KONTEXT_RESOLUTIONS

  #11942 closed Aug 2, 2025

• Wan 2.2 WanTransformer3DModel not compatible with Lightx2v self-forcing guidance distilled loras

  #12037 closed Aug 2, 2025

• Wan 2.2 First vs Second stage

  #12019 closed Aug 1, 2025

• Wan 2.2 5b i2v results poor quality compared to official Wan HF Space

  #12034 closed Aug 1, 2025

• The fuse_lora() func in class PeftAdapterMixin did not take effect.

  #12007 closed Jul 29, 2025

• apply_first_block_cache with Wan 2.2 causes ValueError: No context is set. Please set a context before retrieving the state

  #12012 closed Jul 29, 2025

• The inference image is pure black. This seems to be related to weight, but I have been unable to pinpoint where the problem lies.

  #11989 closed Jul 29, 2025

14 Issues opened by 12 people

• Qwen Image | Image-To-Image + Editing + Inpainting

  #12065 opened Aug 4, 2025

• Is there any DiT block defined in the huggingface/diffusers OR huggingface/transformers project?

  #12060 opened Aug 4, 2025

• Kontext Lora

  #12053 opened Aug 3, 2025

• Wan 2.2 with LightX2V offloading tries to multiply tensors from different devices and fails

  #12052 opened Aug 3, 2025

• `UNet2DConditionModel` : `qk_norm` setting in `config.json` is ignored

  #12050 opened Aug 3, 2025

• Fusing Lightx2v lora on Wan2.2 GGUF fails

  #12047 opened Aug 2, 2025

• AttributeError: 'bool' object has no attribute '__module__'. Did you mean: '__mod__'?

  #12044 opened Aug 2, 2025

• Wan 2.2 VAE forward fails

  #12039 opened Aug 1, 2025

• Dataset structure for train_text_to_image_lora.py

  #12038 opened Jul 31, 2025

• X-Omni-En model won't load

  #12029 opened Jul 30, 2025

• _flash_attention_3 in dispatch_attention_fn is not compatible with the latest flash-atten interface.

  #12022 opened Jul 30, 2025

• Dream 7B

  #12017 opened Jul 29, 2025

• Wan 2.2 a14b i2v OOM

  #12011 opened Jul 29, 2025

• WanTransformer3DModel.from_single_file wont load Wan2.2 GGUF (NotImplementedError: Cannot copy out of meta tensor; no data)

  #12009 opened Jul 29, 2025

25 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [docs] Modular diffusers

  #11931 commented on Jul 31, 2025 • 36 new comments

• Context Parallel w/ Ring & Ulysses & Unified Attention

  #11941 commented on Jul 30, 2025 • 23 new comments

• Implement Frequency-Decoupled Guidance (FDG) as a Guider

  #11976 commented on Aug 2, 2025 • 10 new comments

• [modular diffusers] Wan I2V/FLF2V

  #11997 commented on Aug 1, 2025 • 6 new comments

• [WIP Modular] More Updates for Custom Code Loading

  #11969 commented on Aug 4, 2025 • 6 new comments

• [lora] adapt new LoRA config injection method

  #11999 commented on Aug 4, 2025 • 3 new comments

• [tests] tighten compilation tests for quantization

  #12002 commented on Aug 4, 2025 • 2 new comments

• [core] respect `local_files_only=True` when using sharded checkpoints

  #12005 commented on Aug 1, 2025 • 0 new comments

• [chore] complete the licensing statement.

  #12001 commented on Aug 1, 2025 • 0 new comments

• [refactor] condense group offloading

  #11990 commented on Aug 4, 2025 • 0 new comments

• Add F5 TTS pipeline

  #11958 commented on Aug 3, 2025 • 0 new comments

• [fix] fix for prior preservation and mixed precision sampling

  #11873 commented on Jul 31, 2025 • 0 new comments

• Add cuda kernel support for GGUF inference

  #11869 commented on Aug 4, 2025 • 0 new comments

• [wip] Higgs quantization

  #11797 commented on Aug 1, 2025 • 0 new comments

• Add `--lora_alpha` and metadata handling for `train_dreambooth_lora_hidream`

  #11765 commented on Jul 31, 2025 • 0 new comments

• Update pipeline_flux_fill.py

  #11622 commented on Jul 31, 2025 • 0 new comments

• [Quantization] Add TRT-ModelOpt as a Backend

  #11173 commented on Aug 3, 2025 • 0 new comments

• Support for control-lora

  #10686 commented on Jul 30, 2025 • 0 new comments

• Floating point exception with nightly PyTorch and CUDA

  #11945 commented on Aug 2, 2025 • 0 new comments

• AnimateDiff SparseCtrl RGB does not work as expected

  #9508 commented on Aug 1, 2025 • 0 new comments

• Add pruna integration for loading model through diffusers.from_pretrained / pipeline

  #11700 commented on Jul 29, 2025 • 0 new comments

• Problems with Kontext quantization

  #11992 commented on Jul 29, 2025 • 0 new comments

• Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.

  #12003 commented on Jul 29, 2025 • 0 new comments

• Add Bria 3.2 pipeline - next-generation commercial-ready text-to-image model

  #11978 commented on Jul 29, 2025 • 0 new comments

• Impossible to load WanTransformer3DModel when offline using the 'from_pretrained' function.

  #11948 commented on Jul 29, 2025 • 0 new comments