94 Pull requests merged by 39 people

• [docs] Model cards

  #11112 merged Jun 2, 2025

• [docs] Caching methods

  #11625 merged Jun 2, 2025

• [tests] chore: rename lora model-level tests.

  #11481 merged Jun 2, 2025

• [chore] misc changes in the bnb tests for consistency.

  #11355 merged Jun 2, 2025

• Use float32 RoPE freqs in Wan with MPS backends

  #11643 merged Jun 2, 2025

• [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

• Update Intel Gaudi doc

  #11479 merged May 23, 2025

• [LoRA] minor fix for load_lora_weights() for Flux and a test

  #11595 merged May 22, 2025

• Type annotation fix

  #11597 merged May 21, 2025

• [chore] allow string device to be passed to randn_tensor.

  #11559 merged May 21, 2025

• RegionalPrompting: Inherit from Stable Diffusion

  #11525 merged May 20, 2025

• [Modular diffusers] more refactors

  #11484 merged May 20, 2025

• [docs] Remove fast diffusion tutorial

  #11583 merged May 20, 2025

• docs: fix invalid links

  #11505 merged May 20, 2025

• [LoRA] kijai wan lora support for I2V

  #11588 merged May 20, 2025

• [WIP] Modular Diffusers support custom code/pipeline blocks

  #11539 merged May 20, 2025

• LTX 0.9.7-distilled; documentation improvements

  #11571 merged May 19, 2025

• Use HF Papers

  #11567 merged May 19, 2025

• [Single File] Fix loading for LTX 0.9.7 transformer

  #11578 merged May 19, 2025

• [WIP][LoRA] start supporting kijai wan lora.

  #11579 merged May 19, 2025

• [LoRA] support non-diffusers LTX-Video loras

  #11572 merged May 19, 2025

• [docs] tip for group offloding + quantization

  #11576 merged May 19, 2025

• Revert error to warning when loading LoRA from repo with multiple weights

  #11568 merged May 19, 2025

• Doc update

  #11531 merged May 19, 2025

• enhance value guard of _device_agnostic_dispatch

  #11553 merged May 19, 2025

• [docs] Regional compilation docs

  #11556 merged May 15, 2025

• [tests] add tests for combining layerwise upcasting and groupoffloading.

  #11558 merged May 15, 2025

• [gguf] Refactor __torch_function__ to avoid unnecessary computation

  #11551 merged May 15, 2025

• [Single File] GGUF/Single File Support for HiDream

  #11550 merged May 15, 2025

• [tests] Add torch.compile test for UNet2DConditionModel

  #11537 merged May 14, 2025

• Fix deprecation warnings in test_ltx_image2video.py

  #11538 merged May 13, 2025

• Update pipeline_flux_img2img.py to add missing vae_slicing and vae_tiling calls.

  #11545 merged May 13, 2025

• [tests] Enable testing for HiDream transformer

  #11478 merged May 13, 2025

• LTX Video 0.9.7

  #11516 merged May 13, 2025

• [LoRA] small change to support Hunyuan LoRA Loading for FramePack

  #11546 merged May 13, 2025

• [train_dreambooth.py] Fix the LR Schedulers when num_train_epochs is passed in a distributed training env

  #11239 merged May 13, 2025

• fix: remove torch_dtype="auto" option from docstrings

  #11513 merged May 13, 2025

• Fix typo in train_diffusion_orpo_sdxl_lora_wds.py

  #11541 merged May 13, 2025

• Add VisualCloze

  #11377 merged May 12, 2025

• [test_models_transformer_ltx.py] help us test torch.compile() for impactful models

  #11512 merged May 12, 2025

• enable several pipeline integration tests on XPU

  #11526 merged May 12, 2025

• Hunyuan Video Framepack F1

  #11534 merged May 12, 2025

• [tests] add tests for framepack transformer model.

  #11520 merged May 11, 2025

• Change Framepack transformer layer initialization order

  #11535 merged May 9, 2025

• enable print_env on xpu

  #11507 merged May 9, 2025

• enable dit integration cases on xpu

  #11523 merged May 9, 2025

• [LTXPipeline] Update latents dtype to match VAE dtype

  #11533 merged May 9, 2025

• enable 7 cases on XPU

  #11503 merged May 9, 2025

• [LoRA] support non-diffusers hidream loras

  #11532 merged May 9, 2025

• [Tests] Enable more general testing for torch.compile() with LoRA hotswapping

  #11322 merged May 9, 2025

• feat: pipeline-level quantization config

  #11130 merged May 9, 2025

• [tests] fix audioldm2 for transformers main.

  #11522 merged May 8, 2025

• Conditionally import torchvision in Cosmos transformer

  #11524 merged May 8, 2025

• Add cross attention type for Sana-Sprint training in diffusers.

  #11514 merged May 8, 2025

• [LoRA] make lora alpha and dropout configurable

  #11467 merged May 8, 2025

• clean up the __Init__ for stable_diffusion

  #11500 merged May 7, 2025

• Cosmos

  #10660 merged May 7, 2025

• [docs] minor updates to bitsandbytes docs.

  #11509 merged May 6, 2025

• [lora_conversion] Enhance key handling for OneTrainer components in LORA conversion utility (#11441)

  #11487 merged May 6, 2025

• enable lora cases on XPU

  #11506 merged May 6, 2025

• Hunyuan Video Framepack

  #11428 merged May 6, 2025

• [LoRA] use removeprefix to preserve sanity.

  #11493 merged May 6, 2025

• update dep table.

  #11504 merged May 6, 2025

• Update setup.py to pin min version of peft

  #11502 merged May 6, 2025

• Fix torchao docs typo for fp8 granular quantization

  #11473 merged May 6, 2025

• Update training script for txt to img sdxl with lora supp with new interpolation.

  #11496 merged May 5, 2025

• Set LANCZOS as the default interpolation method for image resizing.

  #11492 merged May 5, 2025

• [training] feat: enable quantization for hidream lora training.

  #11494 merged May 5, 2025

• [train_dreambooth_lora_lumina2] Add LANCZOS as the default interpolation mode for image resizing

  #11491 merged May 5, 2025

• [train_dreambooth_lora_sdxl] Add --image_interpolation_mode option for image resizing (default to lanczos)

  #11490 merged May 5, 2025

• [train_text_to_image_sdxl]Add LANCZOS as default interpolation mode for image resizing

  #11455 merged May 5, 2025

• [Feature] Implement tiled VAE encoding/decoding for Wan model.

  #11414 merged May 5, 2025

• enable semantic diffusion and stable diffusion panorama cases on XPU

  #11459 merged May 5, 2025

28 Pull requests opened by 19 people

• Fix huggingface-hub package name.

  #11498 opened May 5, 2025

• Change timestep device to cpu for xla

  #11501 opened May 5, 2025

• Add FluxPAGPipeline with support for PAG

  #11510 opened May 6, 2025

• [tests] add test for group_offloading with training.

  #11515 opened May 7, 2025

• Feat/multispectral dataloader 5ch

  #11517 opened May 7, 2025

• Add SkyReels V2: Infinite-Length Film Generative Model

  #11518 opened May 7, 2025

• [Chore] add rule to ignore checking black line whitespace.

  #11544 opened May 13, 2025

• Apply Occam's Razor in position embedding calculation

  #11562 opened May 15, 2025

• add prodigy deps

  #11564 opened May 16, 2025

• [benchmarks] overhaul benchmarks

  #11565 opened May 16, 2025

• Chroma as a FLUX.1 variant

  #11566 opened May 17, 2025

• [Research] Latent Perceptual Loss (LPL) for Stable Diffusion XL

  #11573 opened May 18, 2025

• Wan VACE

  #11582 opened May 19, 2025

• Torchao int4 serialization

  #11591 opened May 20, 2025

• First Block Cache refactor

  #11594 opened May 20, 2025

• Introduce DeprecatedPipelineMixin to simplify pipeline deprecation process

  #11596 opened May 21, 2025

• save_pretrained for serializing config.

  #11603 opened May 22, 2025

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

  #11610 opened May 25, 2025

• Added PhotoDoodle Pipeline

  #11621 opened May 28, 2025

• Update pipeline_flux_fill.py

  #11622 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

• Set _torch_version to N/A if torch is disabled.

  #11645 opened Jun 2, 2025

• Add Finegrained FP8

  #11647 opened Jun 3, 2025

• Use real-valued instead of complex tensors in Wan2.1 RoPE

  #11649 opened Jun 3, 2025

• Allow remote code repo names to contain "."

  #11652 opened Jun 3, 2025

44 Issues closed by 21 people

• Diffusers Transformer Pipeline Produces ComplexDouble Tensors on MPS, Causing Conversion Error

  #10986 closed Jun 3, 2025

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

  #11460 closed Jun 3, 2025

• import error

  #11560 closed Jun 3, 2025

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

  #11628 closed Jun 2, 2025

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

  #11627 closed Jun 2, 2025

• 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

• with a custom attention processor for Flux.dev, inference time changes when manually load and inject the transformer model into a flux pipeline versus let the flux pipeline constructor load the transformer internally.

  #11607 closed May 26, 2025

• Flux FP8 with optimum.quanto TypeError: WeightQBytesTensor.__new__() missing 6 required positional arguments: 'axis', 'size', 'stride', 'data', 'scale', and 'activation_qtype'

  #10526 closed May 23, 2025

• 0.33.X FluxLoraLoaderMixin `delete_adapters` Regression

  #11592 closed May 22, 2025

• BlipDiffusionPipeline example breaks in v0.33.1, but works in v0.32.2

  #11563 closed May 22, 2025

• .to() cast in .load_lora_weights breaks on bitsandbytes quantized text_encoder's for SD/SDXL

  #11570 closed May 21, 2025

• Infinite (not literally) length video creation using LTX-Video?

  #11590 closed May 20, 2025

• KeyError: 'vae.encoder.conv_out.conv.weight'

  #11574 closed May 20, 2025

• Flux fill dev with controlnet support

  #11547 closed May 19, 2025

• [Feature request] Please provide diffusers repo for ltxv-13b-0.9.7-distilled

  #11569 closed May 18, 2025

• HiDream support for safetensors and gguf loading

  #11344 closed May 16, 2025

• hello i cant generate beautiful anime women

  #11345 closed May 15, 2025

• AttributeError: 'list' object has no attribute '__module__' :hunyuan dit cannot load multiple controlnets

  #9142 closed May 15, 2025

• `.from_pretrained` `torch_dtype="auto"` argument not working a expected

  #11432 closed May 13, 2025

• wan2.1 transformer gguf load error

  #11088 closed May 13, 2025

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

  #11295 closed May 12, 2025

• Prompt adherence for FluxPipeline is broken

  #11536 closed May 10, 2025

• [Tracker] fix training resuming problem when using FP16 in the examples

  #6552 closed May 10, 2025

• [Feature request] LTX-Video v0.9.6 15x faster inference than non-distilled model.

  #11359 closed May 9, 2025

• HiDream LoRA support

  #11383 closed May 9, 2025

• Apply applicable `quantization_config` to model components when loading a model

  #10327 closed May 9, 2025

• Stable Virtual Camera

  #11151 closed May 8, 2025

• partial models spec in model_index.json

  #10413 closed May 8, 2025

• Question about non-convergence of training autoencoderkl.

  #11221 closed May 7, 2025

• ImportError: cannot import name 'CogView4LoraLoaderMixin' from 'diffusers.loaders'

  #11218 closed May 7, 2025

• Crash when loading Flux Schnell 1 model with train_dreambooth_lora_flux

  #11045 closed May 7, 2025

• Unable to load Flux LoRA trained with OneTrainer – NotImplementedError in `_convert_mixture_state_dict_to_diffusers`

  #11441 closed May 6, 2025

• Unable to load FLUX.1-Canny-dev-lora into FluxControlPipeline

  #11464 closed May 6, 2025

• TypeError: BnB4BitDiffusersQuantizer.create_quantized_param() got an unexpected keyword argument 'dtype'

  #11149 closed May 6, 2025

• [quant] about float8_e4m3_tensor

  #11468 closed May 6, 2025

• Failed to import diffusers.schedulers.scheduling_ddim because of the following error (look up to see its traceback): numpy.dtype size changed, may indicate binary incompatibility. Expected 96 from C header, got 88 from PyObject

  #11169 closed May 5, 2025

• Better image interpolation in training scripts follow up

  #11390 closed May 5, 2025

• The module 'HunyuanVideoTransformer3DModel' has been loaded in `bitsandbytes` 8bit and moving it to cpu via `.to()` is not supported. Module is still on cuda:0

  #10653 closed May 4, 2025

27 Issues opened by 24 people

• Can't load flux-fill-lora with FluxControl

  #11651 opened Jun 3, 2025

• max_shard_size

  #11650 opened Jun 3, 2025

• how to load lora weight with fp8 transfomer model?

  #11648 opened Jun 3, 2025

• Error in init from pretrained for LTXConditionPipeline

  #11644 opened Jun 2, 2025

• 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

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

  #11615 opened May 27, 2025

• Scheduling LORA

  #11599 opened May 22, 2025

• Not getting the desired result as Stable Diffusion Web UI

  #11585 opened May 20, 2025

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

  #11584 opened May 20, 2025

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

  #11581 opened May 19, 2025

• Can diffusers support loading and running FLUX with fp8 ?

  #11580 opened May 19, 2025

• Hidream Model loading takes too long — any way to speed it up?

  #11575 opened May 19, 2025

• FluxFillPipeline Support load IP Adapter.

  #11561 opened May 15, 2025

• `device_map="auto"` supported for diffusers pipelines?

  #11555 opened May 14, 2025

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

  #11542 opened May 13, 2025

• FluxPipeline produces noise when .enable_vae_slicing is used, and FluxImage2ImagePipeline does not support .enable_vae_slicing.

  #11540 opened May 12, 2025

• [Docs Update] AutoPipelineForInpainting.from_pretrained fails to load runwayml/stable-diffusion-inpainting without variant="fp16"

  #11528 opened May 9, 2025

• Request support for MAGI-1

  #11519 opened May 8, 2025

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

  #11499 opened May 5, 2025

• SD3 ControlNet Script (and others?): dataset preprocessing cache depends on unrelated arguments

  #11497 opened May 5, 2025

• Error when I'm trying to train a Flux lora with train_dreambooth_lora_flux_advanced

  #11489 opened May 4, 2025

• Sincerely Request The Support for Flux PAG Pipeline

  #11488 opened May 4, 2025

100 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.

• [LoRA] parse metadata from LoRA and save metadata

  #11324 commented on Jun 2, 2025 • 34 new comments

• First Block Cache

  #11180 commented on May 20, 2025 • 12 new comments

• [Quantization] Add TRT-ModelOpt as a Backend

  #11173 commented on May 29, 2025 • 11 new comments

• Attention Dispatcher

  #11368 commented on May 30, 2025 • 7 new comments

• Fixes #11068 Add extended support for SD3 ControlNet (Stability AI)

  #11084 commented on May 11, 2025 • 0 new comments

• Improve `textual inversion` compatibility

  #10949 commented on May 9, 2025 • 0 new comments

• Support for control-lora

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

• model_cpu_offload failed in unidiffusers pipeline

  #11443 commented on Jun 3, 2025 • 0 new comments

• onnx export failure - timestep parameter with static value

  #11456 commented on Jun 3, 2025 • 0 new comments

• enable_xformers_memory_efficient_attention in the training script

  #11486 commented on Jun 3, 2025 • 0 new comments

• InstructPix2Pix training script for SD3

  #9101 commented on Jun 3, 2025 • 0 new comments

• [Quantization] Support TRT as a backend

  #11032 commented on Jun 2, 2025 • 0 new comments

• FlaxUNet2DConditionModel is not initialized with correct dtypes

  #11144 commented on Jun 2, 2025 • 0 new comments

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

  #11279 commented on Jun 2, 2025 • 0 new comments

• Hotswapping multiple LoRAs throws a peft key error.

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

• Train_controlnet_sdxl.py and tensorboard log images

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

• Finetuning of flux or scratch training

  #11466 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

• PixArt Sigma PEFT LoRA loader support

  #11216 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

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

  #11374 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

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

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

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

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

• Lora Hotswap no clear documentation

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

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

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

• attributeerror: 'distributeddataparallel' object has no attribute 'dtype'. did you mean: 'type'?

  #11417 commented on May 25, 2025 • 0 new comments

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

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

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

  #11477 commented on May 17, 2025 • 0 new comments

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

  #11452 commented on Jun 2, 2025 • 0 new comments

• [Refactor] Initialize class members inside init method

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

• [NewModel] Adds SEVA ( Stable Virtual Camera) model

  #11440 commented on Jun 2, 2025 • 0 new comments

• [LoRA training] add aspect ratio bucketing

  #11438 commented on May 29, 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

• Bump h11 from 0.14.0 to 0.16.0 in /examples/server

  #11415 commented on May 25, 2025 • 0 new comments

• Add fluxfill train code

  #11393 commented on May 23, 2025 • 0 new comments

• Bump torch from 2.2.0 to 2.6.0 in /examples/research_projects/realfill

  #11364 commented on May 19, 2025 • 0 new comments

• Update License year; Add missing license for HiDream implementation

  #11358 commented on May 20, 2025 • 0 new comments

• Add basic implementation of AuraFlowImg2ImgPipeline

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

• [loaders] make the `loaders` folder structure cleaner

  #11335 commented on Jun 2, 2025 • 0 new comments

• Laplace Scheduler for DDPM

  #11320 commented on May 24, 2025 • 0 new comments

• Fix the documentation of stable_diffusion_3.md

  #11287 commented on May 11, 2025 • 0 new comments

• Add VidTok AutoEncoders

  #11261 commented on May 23, 2025 • 0 new comments

• test new token for STYLE BOT

  #11257 commented on May 9, 2025 • 0 new comments

• [Feature] MultiControlNet support for SD3Impainting

  #11251 commented on May 22, 2025 • 0 new comments

• [modular diffusers] more refactor

  #11235 commented on May 22, 2025 • 0 new comments

• Bump jinja2 from 3.1.4 to 3.1.6 in /examples/server

  #11234 commented on May 8, 2025 • 0 new comments

• Add SDXL implementation for PyTorch/XLA training

  #11204 commented on May 4, 2025 • 0 new comments

• Added unload_lora_weights to StableDiffusionPipeline

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

• [CI] Some improvements to Nightly reports summaries

  #11166 commented on Jun 3, 2025 • 0 new comments

• Since last update of transformers I can't import diffusers modules

  #11343 commented on May 16, 2025 • 0 new comments

• `prepare_ip_adapter_image_embeds` Bug Causes Feature Mixing During Batch Processing in IP-Adapter

  #9813 commented on May 15, 2025 • 0 new comments

• Potential incorrect reshaping in 2D positional embedding

  #11309 commented on May 14, 2025 • 0 new comments

• [tests] help us test `torch.compile()` for impactful models

  #11430 commented on May 14, 2025 • 0 new comments

• [Community] Help us fix the LR schedulers when `num_train_epochs` is passed in a distributed training env

  #8384 commented on May 13, 2025 • 0 new comments

• value errors in convert to/from diffusers from original stable diffusion

  #11285 commented on May 12, 2025 • 0 new comments

• HiDream auxiliary loss for MoE experts not tied to computation graph

  #11301 commented on May 12, 2025 • 0 new comments

• MultiControlNetModel is not supported for SD3ControlNetInpaintingPipeline

  #11208 commented on May 11, 2025 • 0 new comments

• Error while loading Lora

  #11286 commented on May 11, 2025 • 0 new comments

• [Flux ControlNet] Add support for de-distilled models with CFG

  #9635 commented on May 11, 2025 • 0 new comments

• [New Pipeline]: SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers

  #11135 commented on May 10, 2025 • 0 new comments

• Full support for Flux attention masking

  #10194 commented on May 10, 2025 • 0 new comments

• Finetuned models aren't saved or loaded properly in train_custom_diffusion.py

  #9320 commented on May 10, 2025 • 0 new comments

• Support wan2.1 video model?

  #11008 commented on May 9, 2025 • 0 new comments

• Output of randn_tensor changes based on dtype, making seeds non-reproducible if the model precision is changed

  #11056 commented on May 9, 2025 • 0 new comments

• Error distributing FluxTransformer2DModel to multiple GPUs using controlnet

  #11247 commented on May 9, 2025 • 0 new comments

• Add ReNeg: An end-toend method designed to learn improved Negative embeddings (CVPR 2025 Highlight)

  #11256 commented on May 9, 2025 • 0 new comments

• [core] refactor `attention_processor.py` the easy way

  #10022 commented on May 8, 2025 • 0 new comments

• [Tests] fast tests single file checkpoints

  #6515 commented on May 8, 2025 • 0 new comments

• Expanded init fields in StableDiffusionPipeline cause incompatibilities with many/most inherited pipelines

  #6969 commented on May 7, 2025 • 0 new comments

• TypeError: UVit2DModel.forward.<locals>.layer_() got an unexpected keyword argument 'encoder_hidden_states'

  #11214 commented on May 6, 2025 • 0 new comments

• AttributeError: _hf_hook caused by delattr in hooks.remove_hook_from_module()

  #10729 commented on May 6, 2025 • 0 new comments

• Getting CUDA out of memory error even with Colab A100 high RAM

  #11014 commented on May 5, 2025 • 0 new comments

• Error in loading Lora

  #11209 commented on May 5, 2025 • 0 new comments

• controlnet pipeline and training script for sana model

  #11019 commented on May 4, 2025 • 0 new comments

• scheduler UniPCMultistepScheduler get_velocity()

  #11213 commented on May 24, 2025 • 0 new comments

• diffusers中的cogvideo image2video中建议的分辨率尺寸与cogvideo原项目中建议的尺寸不一致？

  #11336 commented on May 24, 2025 • 0 new comments

• Controlnet Inference example, CUDA OOM

  #11363 commented on May 24, 2025 • 0 new comments

• How to convert the hidream lora trained by diffusers to a format that comfyui can load?

  #11396 commented on May 24, 2025 • 0 new comments

• FluxTransformer2DModel does not have config and cannot set_default_attn_processor

  #11398 commented on May 24, 2025 • 0 new comments

• set_adapters not support for compiled model

  #11408 commented on May 24, 2025 • 0 new comments

• File "/usr/local/python/lib/python3.8/site-packages/diffusers/models/attention_processor.py", line 3074, in __call__ [rank0]: batch_size, key_tokens, _ = ( [rank0]: ValueError: too many values to unpack (expected 3)

  #11410 commented on May 24, 2025 • 0 new comments

• RuntimeError: The size of tensor a (4608) must match the size of tensor b (5120) at non-singleton dimension 2 during DreamBooth Training with Prior Preservation

  #10722 commented on May 24, 2025 • 0 new comments

• Dreambooth finetune FLUX dev CLIPTextModel

  #10925 commented on May 23, 2025 • 0 new comments

• scheduler refactor to support different `set_timesteps` and `step` method

  #11389 commented on May 23, 2025 • 0 new comments

• FluxFillPipeline quality deteriorates over multiple iterations of inpainting

  #10204 commented on May 22, 2025 • 0 new comments

• torch.compile errors on vae.encode

  #10937 commented on May 22, 2025 • 0 new comments

• Run FLUX-controlnet zero3 training failed: 'weight' must be 2-D

  #10969 commented on May 22, 2025 • 0 new comments

• flux controlnet train ReadMe have a bug

  #11321 commented on May 22, 2025 • 0 new comments

• _get_checkpoint_shard_files not work when HF_HUB_OFFLINE=1

  #11447 commented on May 21, 2025 • 0 new comments

• Wan Video Vae RemoteVae

  #11326 commented on May 21, 2025 • 0 new comments

• convert_hunyuan_video_to_diffusers.py not working - invalid load key, '\xd8'.

  #11370 commented on May 20, 2025 • 0 new comments

• Mochi OutOfMemory

  #11454 commented on May 18, 2025 • 0 new comments

• Flux FIll lora / dreambooth finetune support

  #11145 commented on May 17, 2025 • 0 new comments

• Error in loading Lora

  #11224 commented on May 17, 2025 • 0 new comments

• Standardization of additional token identifiers across pipelines

  #11334 commented on May 17, 2025 • 0 new comments

• DDIM previous timestep issue

  #11347 commented on May 17, 2025 • 0 new comments

• Support Chroma - Flux based model with architecture changes

  #11010 commented on May 17, 2025 • 0 new comments

• Civit AI flux model razor-8step-rapid-real not working with diffusers single file

  #11127 commented on May 16, 2025 • 0 new comments

• How to multi-GPU WAN inference

  #11339 commented on May 16, 2025 • 0 new comments