22 Pull requests merged by 13 people

• [docs] update torchao doc link

  #11634 merged May 30, 2025

• Fix typos in strings and comments

  #11476 merged May 30, 2025

• typo fix in pipeline_flux.py

  #11623 merged May 30, 2025

• Bug: Fixed Image 2 Image example

  #11619 merged May 30, 2025

• enable group_offloading and PipelineDeviceAndDtypeStabilityTests on XPU, all passed

  #11620 merged May 30, 2025

• removing unnecessary else statement

  #11624 merged May 30, 2025

• Fix wrong indent for examples of controlnet script

  #11632 merged May 29, 2025

• [textual_inversion_sdxl.py] fix lr scheduler steps count

  #11557 merged May 29, 2025

• [docs] PyTorch 2.0

  #11618 merged May 28, 2025

• [CI] fix the filename for displaying failures in lora ci.

  #11600 merged May 28, 2025

• [Sana Sprint] add image-to-image pipeline

  #11602 merged May 27, 2025

• [LoRA] improve LoRA fusion tests

  #11274 merged May 27, 2025

• Adding NPU for get device function

  #11617 merged May 27, 2025

• [training docs] smol update to README files

  #11616 merged May 27, 2025

• Make group offloading compatible with torch.compile()

  #11605 merged May 27, 2025

• fix security issue in build docker ci

  #11614 merged May 26, 2025

• Fix mixed variant downloading

  #11611 merged May 26, 2025

• [tests] Changes to the torch.compile() CI and tests

  #11508 merged May 26, 2025

• Fix bug when variant and safetensor file does not match

  #11587 merged May 26, 2025

• [docs] Pipeline-level quantization

  #11604 merged May 26, 2025

• [Feature] AutoModel can load components using model_index.json

  #11401 merged May 26, 2025

• enable pipeline test cases on xpu

  #11527 merged May 26, 2025

7 Pull requests opened by 6 people

• Added PhotoDoodle Pipeline

  #11621 opened May 28, 2025

• Update pipeline_flux_fill.py

  #11622 opened May 28, 2025

• [docs] Caching methods

  #11625 opened May 28, 2025

• Add community class StableDiffusionXL_T5Pipeline

  #11626 opened May 29, 2025

• [bugfix] Fix the issue that will save the model card if push to hub is not applied in HiDream

  #11629 opened May 29, 2025

• Pipeline doc pr

  #11636 opened May 30, 2025

• [`Wan`] Fix VAE sampling mode in `WanVideoToVideoPipeline`

  #11639 opened May 30, 2025

7 Issues closed by 5 people

• RuntimeError: group_norm in VAE decode for SDXL Masked Img2Img (even with ControlNets disabled & FP32 VAE/Latents)

  #11424 closed May 30, 2025

• TorchAO+diffusers

  #10555 closed May 29, 2025

• [SD3] pipe.enable_xformers_memory_efficient_attention

  #8535 closed May 28, 2025

• How to know that "Textual inversion" file I have loaded and not turn it on?

  #11419 closed May 27, 2025

• `use_safetensors` is not passed to `load_sub_model`

  #11601 closed May 27, 2025

• extend AutoModel to be able to load transformer models & custom diffusers models

  #11388 closed May 26, 2025

• RuntimeError: Failed to import diffusers.pipelines.cogvideo.pipeline_cogvideox because of the following error (look up to see its traceback):

  #11413 closed May 26, 2025

9 Issues opened by 9 people

• prompt_embeds_scale in FluxPriorReduxPipeline seems to have no effect.

  #11642 opened Jun 1, 2025

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

  #11641 opened May 31, 2025

• How to load lora weight in distribution applications?

  #11637 opened May 30, 2025

• When I use deepspeed_zero3 to train the controlnet on flux, an error occured "RuntimeError: tensor does not have a device".

  #11633 opened May 29, 2025

• OMI Format Compatibility

  #11631 opened May 29, 2025

• [FR] Please support WanVACETransformer3DModel.from_single_file

  #11630 opened May 29, 2025

• DreamO/Flux group offload: Expected all tensors to be on the same device, but found at least two devices

  #11628 opened May 29, 2025

• StableDiffusion3Pipeline with InstantX/SD3.5-Large-IP-Adapter

  #11627 opened May 29, 2025

• AnimateDiffPipeline: Tensor Mismatch with num_frames > motion_max_seq_length (chunking failure)

  #11615 opened May 27, 2025

39 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.

• Any chance class members like self._interrupt could be defined in __init__ across pipelines?

  #11002 commented on May 26, 2025 • 0 new comments

• Lora Hotswap no clear documentation

  #11423 commented on May 26, 2025 • 0 new comments

• Unable to load IP Adapter into FLUX ( TypeError: CLIPVisionModelWithProjection.__init__() got an unexpected keyword argument 'dtype' )

  #11581 commented on May 26, 2025 • 0 new comments

• fusing/stable-unclip-2-1-h-img2img cannot found

  #11448 commented on May 27, 2025 • 0 new comments

• [New Project] Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

  #11480 commented on May 27, 2025 • 0 new comments

• [performance] investigating FluxPipeline for recompilations on resolution changes

  #11360 commented on May 27, 2025 • 0 new comments

• FluxFillPipeline Support load IP Adapter.

  #11561 commented on May 27, 2025 • 0 new comments

• [Feature request] Integrate SkyReels-V2 support in diffusers

  #11374 commented on May 27, 2025 • 0 new comments

• Scheduling LORA

  #11599 commented on May 28, 2025 • 0 new comments

• enable_attention_slicing give NaN results for SDXL on MPS

  #11229 commented on May 28, 2025 • 0 new comments

• PixArt Sigma PEFT LoRA loader support

  #11216 commented on May 28, 2025 • 0 new comments

• Can diffusers support loading and running FLUX with fp8 ?

  #11580 commented on May 29, 2025 • 0 new comments

• model_cpu_offload failed in unidiffusers pipeline

  #11443 commented on May 29, 2025 • 0 new comments

• CompVis/stable-diffusion-v1-4 is missing fp16 files

  #11460 commented on May 30, 2025 • 0 new comments

• How to finetune Flux-dev full params, 80G OOM ...

  #10196 commented on May 30, 2025 • 0 new comments

• Finetuning of flux or scratch training

  #11466 commented on May 30, 2025 • 0 new comments

• Train_controlnet_sdxl.py and tensorboard log images

  #11470 commented on May 31, 2025 • 0 new comments

• Hotswapping multiple LoRAs throws a peft key error.

  #11298 commented on May 31, 2025 • 0 new comments

• [Models] handle initialization of new layers in a partially pre-trained model better

  #11279 commented on Jun 1, 2025 • 0 new comments

• [Quantization] Support TRT as a backend

  #11032 commented on Jun 1, 2025 • 0 new comments

• Support for control-lora

  #10686 commented on May 29, 2025 • 0 new comments

• [docs] Model cards

  #11112 commented on May 28, 2025 • 0 new comments

• Added unload_lora_weights to StableDiffusionPipeline

  #11172 commented on May 30, 2025 • 0 new comments

• [Quantization] Add TRT-ModelOpt as a Backend

  #11173 commented on May 29, 2025 • 0 new comments

• [LoRA] parse metadata from LoRA and save metadata

  #11324 commented on May 27, 2025 • 0 new comments

• Add basic implementation of AuraFlowImg2ImgPipeline

  #11340 commented on May 27, 2025 • 0 new comments

• Pipeline deprecations

  #11354 commented on May 31, 2025 • 0 new comments

• Attention Dispatcher

  #11368 commented on May 30, 2025 • 0 new comments

• Bump torch from 2.4.1 to 2.7.0 in /examples/server

  #11429 commented on May 28, 2025 • 0 new comments

• [LoRA training] add aspect ratio bucketing

  #11438 commented on May 29, 2025 • 0 new comments

• [Refactor] Initialize class members inside init method

  #11450 commented on May 26, 2025 • 0 new comments

• [feat] Add ostris / Flex.2-preview pipeline

  #11485 commented on May 28, 2025 • 0 new comments

• Add FluxPAGPipeline with support for PAG

  #11510 commented on May 26, 2025 • 0 new comments

• Add SkyReels V2: Infinite-Length Film Generative Model

  #11518 commented on Jun 1, 2025 • 0 new comments

• Apply Occam's Razor in position embedding calculation

  #11562 commented on May 27, 2025 • 0 new comments

• add prodigy deps

  #11564 commented on May 26, 2025 • 0 new comments

• [benchmarks] overhaul benchmarks

  #11565 commented on May 31, 2025 • 0 new comments

• Wan VACE

  #11582 commented on May 30, 2025 • 0 new comments

• Make SDXL treat the "optional" components as really optional

  #11610 commented on May 29, 2025 • 0 new comments