12 Pull requests merged by 9 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

5 Pull requests opened by 4 people

• 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

6 Issues closed by 3 people

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

  #12065 closed Aug 4, 2025

• 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

7 Issues opened by 6 people

• Qwen Image incorrect device assignment during prompt encode

  #12066 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

16 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.

• [WIP Modular] More Updates for Custom Code Loading

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

• [lora] adapt new LoRA config injection method

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

• Floating point exception with nightly PyTorch and CUDA

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

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

  #12022 commented on Aug 2, 2025 • 0 new comments

• Wan 2.2 VAE forward fails

  #12039 commented on Aug 2, 2025 • 0 new comments

• [Quantization] Add TRT-ModelOpt as a Backend

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

• Add cuda kernel support for GGUF inference

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

• Add F5 TTS pipeline

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

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

  #11976 commented on Aug 2, 2025 • 0 new comments

• [refactor] condense group offloading

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

• [tests] tighten compilation tests for quantization

  #12002 commented on Aug 4, 2025 • 0 new comments

• Bria 3 2 pipeline

  #12010 commented on Aug 3, 2025 • 0 new comments

• [wip][core] parallel loading of shards

  #12028 commented on Aug 4, 2025 • 0 new comments

• Add IP-Adapter

  #12030 commented on Aug 3, 2025 • 0 new comments

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

  #12032 commented on Aug 4, 2025 • 0 new comments

• Add Flix Fill ControlNet

  #12035 commented on Aug 2, 2025 • 0 new comments