5 Pull requests merged by 5 people

• Update pipeline_flux_inpaint.py to fix padding_mask_crop returning only the inpainted area

  #11658 merged Jun 10, 2025

• Add community class StableDiffusionXL_T5Pipeline

  #11626 merged Jun 9, 2025

• Introduce DeprecatedPipelineMixin to simplify pipeline deprecation process

  #11596 merged Jun 9, 2025

• [tests] Fix how compiler mixin classes are used

  #11680 merged Jun 9, 2025

• fixed axes_dims_rope init (huggingface#11641)

  #11678 merged Jun 8, 2025

8 Pull requests opened by 6 people

• Fix EDM DPM Solver Test and Enhance Test Coverage

  #11679 opened Jun 8, 2025

• [tests] model-level `device_map` clarifications

  #11681 opened Jun 9, 2025

• [wip][poc] make group offloading work with disk/nvme transfers

  #11682 opened Jun 9, 2025

• [WIP] device_map rework and direct weights loading

  #11683 opened Jun 10, 2025

• [GGUF] feat: support loading diffusers format gguf checkpoints.

  #11684 opened Jun 10, 2025

• [WIP] Refactor Attention Modules

  #11685 opened Jun 10, 2025

• Bump requests from 2.32.3 to 2.32.4 in /examples/server

  #11686 opened Jun 10, 2025

• Add Pruna optimization framework documentation

  #11688 opened Jun 10, 2025

2 Issues closed by 1 person

• What's the difference between 'example/train_text_to_image_lora.py' and 'example/research_projects/lora/train_text_to_image_lora.py' ?

  #11542 closed Jun 10, 2025

• [BUG] [CleanCode] Tuple[int] = (16, 56, 56) in FluxTransformer2DModel

  #11641 closed Jun 8, 2025

1 Issue opened by 1 person

• [DOCS] Add `pruna` as optimization framework

  #11687 opened Jun 10, 2025

27 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.

• Attention Dispatcher

  #11368 commented on Jun 8, 2025 • 8 new comments

• [benchmarks] overhaul benchmarks

  #11565 commented on Jun 10, 2025 • 5 new comments

• Add FluxPAGPipeline with support for PAG

  #11510 commented on Jun 9, 2025 • 2 new comments

• [tests] tests for compilation + quantization (bnb)

  #11672 commented on Jun 10, 2025 • 0 new comments

• enable cpu offloading of new pipelines on XPU & use device agnostic empty to make pipelines work on XPU

  #11671 commented on Jun 8, 2025 • 0 new comments

• ⚡️ Speed up method `AutoencoderKLWan.clear_cache` by 886%

  #11665 commented on Jun 9, 2025 • 0 new comments

• [WIP] [LoRA] support omi hidream lora.

  #11660 commented on Jun 10, 2025 • 0 new comments

• [LoRA] support Flux Control LoRA with bnb 8bit.

  #11655 commented on Jun 10, 2025 • 0 new comments

• enable torchao test cases on XPU and switch to device agnostic APIs for test cases

  #11654 commented on Jun 10, 2025 • 0 new comments

• Allow remote code repo names to contain "."

  #11652 commented on Jun 10, 2025 • 0 new comments

• Chroma as a FLUX.1 variant

  #11566 commented on Jun 10, 2025 • 0 new comments

• Add SkyReels V2: Infinite-Length Film Generative Model

  #11518 commented on Jun 10, 2025 • 0 new comments

• [torch.compile] Make HiDream torch.compile ready

  #11477 commented on Jun 10, 2025 • 0 new comments

• [quant] add __repr__ for better printing of configs.

  #11452 commented on Jun 10, 2025 • 0 new comments

• [LoRA] parse metadata from LoRA and save metadata

  #11324 commented on Jun 10, 2025 • 0 new comments

• Error in init from pretrained for LTXConditionPipeline

  #11644 commented on Jun 10, 2025 • 0 new comments

• HunyuanVideoImageToVideoPipeline memory leak

  #11676 commented on Jun 10, 2025 • 0 new comments

• [performance] investigating FluxPipeline for recompilations on resolution changes

  #11360 commented on Jun 10, 2025 • 0 new comments

• [Performance] Issue on *SanaLinearAttnProcessor2_0 family. 1.06X speedup can be reached with a simple change.

  #11499 commented on Jun 10, 2025 • 0 new comments

• OMI Format Compatibility

  #11631 commented on Jun 10, 2025 • 0 new comments

• max_shard_size

  #11650 commented on Jun 10, 2025 • 0 new comments

• The density_for_timestep_sampling and loss_weighting for SD3 Training！！！

  #9056 commented on Jun 10, 2025 • 0 new comments

• Add SUPIR Upscaler

  #7219 commented on Jun 10, 2025 • 0 new comments

• Sage Attention for diffuser library

  #11168 commented on Jun 9, 2025 • 0 new comments

• how to load lora weight with fp8 transfomer model?

  #11648 commented on Jun 9, 2025 • 0 new comments

• torch.compile can't be used with groupoffloading on hunyuanvideo_frampack

  #11584 commented on Jun 9, 2025 • 0 new comments

• Request support for MAGI-1

  #11519 commented on Jun 8, 2025 • 0 new comments