87 Pull requests merged by 26 people

• 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

• enable quantcompile test on xpu

  #11988 merged Jul 28, 2025

• [compile] logger statements create unnecessary guards during dynamo tracing

  #11987 merged Jul 25, 2025

• [modular diffusers] Wan

  #11913 merged Jul 23, 2025

• [tests] enforce torch version in the compilation tests.

  #11979 merged Jul 23, 2025

• [docs] update guidance_scale docstring for guidance_distilled models.

  #11935 merged Jul 23, 2025

• [tests] Add test slices for Wan

  #11920 merged Jul 23, 2025

• fix style

  #11975 merged Jul 22, 2025

• [Examples] Uniform notations in train_flux_lora

  #10011 merged Jul 22, 2025

• Remove logger warnings for attention backends and hard error during runtime instead

  #11967 merged Jul 22, 2025

• fix "Expected all tensors to be on the same device, but found at least two devices" error

  #11690 merged Jul 22, 2025

• [Modular] update the collection behavior

  #11963 merged Jul 21, 2025

• [tests] Add fast test slices for HiDream-Image

  #11953 merged Jul 21, 2025

• [tests] Add test slices for Cosmos

  #11955 merged Jul 21, 2025

• [tests] Add test slices for Hunyuan Video

  #11954 merged Jul 21, 2025

• Fix kontext finetune issue when batch size >1

  #11921 merged Jul 18, 2025

• [docs] include bp link.

  #11952 merged Jul 18, 2025

• [docs] Update toctree

  #11936 merged Jul 18, 2025

• [Modular] Updates for Custom Pipeline Blocks

  #11940 merged Jul 18, 2025

• [docs] clarify the mapping between Transformer2DModel and finegrained variants.

  #11947 merged Jul 18, 2025

• [refactor] Flux/Chroma single file implementation + Attention Dispatcher

  #11916 merged Jul 17, 2025

• Add SkyReels V2: Infinite-Length Film Generative Model

  #11518 merged Jul 16, 2025

• [training] add an offload utility that can be used as a context manager.

  #11775 merged Jul 16, 2025

• enable flux pipeline compatible with unipc and dpm-solver

  #11908 merged Jul 16, 2025

• [ControlnetUnion] Propagate #11888 to img2img

  #11929 merged Jul 16, 2025

• Fixed bug: Uncontrolled recursive calls that caused an infinite loop when loading certain pipelines containing Transformer2DModel

  #11923 merged Jul 16, 2025

• Remove forced float64 from onnx stable diffusion pipelines

  #11054 merged Jul 16, 2025

• Remove device synchronization when loading weights

  #11927 merged Jul 15, 2025

• [tests] Improve Flux tests

  #11919 merged Jul 15, 2025

• Bump aiohttp from 3.10.10 to 3.12.14 in /examples/server

  #11924 merged Jul 15, 2025

• Fix: Align VAE processing in ControlNet SD3 training with inference

  #11909 merged Jul 14, 2025

• Flux: pass joint_attention_kwargs when using gradient_checkpointing

  #11814 merged Jul 11, 2025

• [docs] torch.compile blog post

  #11837 merged Jul 11, 2025

• Speedup model loading by 4-5x ⚡

  #11904 merged Jul 11, 2025

• [tests] Unify compilation + offloading tests in quantization

  #11910 merged Jul 11, 2025

• Avoid creating tensor in CosmosAttnProcessor2_0 (#11761)

  #11763 merged Jul 10, 2025

• [ControlnetUnion] Multiple Fixes

  #11888 merged Jul 10, 2025

• [utils] account for MPS when available in get_device().

  #11905 merged Jul 10, 2025

• [LoRA] fix: disabling hooks when loading loras.

  #11896 merged Jul 10, 2025

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

  #11429 merged Jul 10, 2025

• [quant] QoL improvements for pipeline-level quant config

  #11876 merged Jul 10, 2025

• The Modular Diffusers

  #9672 merged Jul 10, 2025

• [SD3] CFG Cutoff fix and official callback

  #11890 merged Jul 9, 2025

• Fix unique memory address when doing group-offloading with disk

  #11767 merged Jul 9, 2025

• feat: add multiple input image support in Flux Kontext

  #11880 merged Jul 9, 2025

• [tests] add compile + offload tests for GGUF.

  #11740 merged Jul 9, 2025

• [tests] mark the wanvace lora tester flaky

  #11883 merged Jul 9, 2025

• [tests] Remove more deprecated tests

  #11895 merged Jul 9, 2025

• [Docker] update doc builder dockerfile to include quant libs.

  #11728 merged Jul 9, 2025

• Pin k-diffusion for CI

  #11894 merged Jul 9, 2025

• [CI] Speed up GPU PR Tests

  #11887 merged Jul 9, 2025

• Merge modular diffusers with main

  #11893 merged Jul 9, 2025

• Update chroma.md

  #11891 merged Jul 9, 2025

• [tests] annotate compilation test classes with bnb

  #11715 merged Jul 9, 2025

• First Block Cache

  #11180 merged Jul 8, 2025

• [CI] Fix big GPU test marker

  #11786 merged Jul 8, 2025

• [training ] add Kontext i2i training

  #11858 merged Jul 8, 2025

• [docs] LoRA metadata

  #11848 merged Jul 8, 2025

• Copied-from implementation of PAG-guider

  #11882 merged Jul 8, 2025

• [tests] remove tests for deprecated pipelines.

  #11879 merged Jul 8, 2025

• [docs] fix references in flux pipelines.

  #11857 merged Jul 7, 2025

• [chore] deprecate blip controlnet pipeline.

  #11877 merged Jul 7, 2025

• Modular custom config object serialization

  #11868 merged Jul 5, 2025

• Modular Guider ConfigMixin

  #11862 merged Jul 5, 2025

• Modular PAG Guider

  #11860 merged Jul 4, 2025

• Fix Wan AccVideo/CausVid fuse_lora

  #11856 merged Jul 4, 2025

• FIX set_lora_device when target layers differ

  #11844 merged Jul 4, 2025

45 Pull requests opened by 27 people

• [fix] Flux Kontext resize method

  #11863 opened Jul 4, 2025

• Add cuda kernel support for GGUF inference

  #11869 opened Jul 5, 2025

• Add STORK scheduler

  #11871 opened Jul 6, 2025

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

  #11873 opened Jul 6, 2025

• add kontext into auto-pipeline

  #11875 opened Jul 7, 2025

• [tests] Create test_pipeline_flux_controlnet_inpaint

  #11906 opened Jul 10, 2025

• Fix: Exclude module handling in LoRA weight loading

  #11911 opened Jul 10, 2025

• [WIP] Speed up PR CI

  #11926 opened Jul 15, 2025

• [docs] Modular diffusers

  #11931 opened Jul 15, 2025

• [Modular] Fast Tests

  #11937 opened Jul 16, 2025

• Context Parallel w/ Ring & Ulysses & Unified Attention

  #11941 opened Jul 16, 2025

• [Modular] support standard repo

  #11944 opened Jul 17, 2025

• [WIP] SVDQuant

  #11950 opened Jul 17, 2025

• Add F5 TTS pipeline

  #11958 opened Jul 19, 2025

• [fix] compile for groupoffloading

  #11960 opened Jul 20, 2025

• [WIP Modular] More Updates for Custom Code Loading

  #11969 opened Jul 21, 2025

• torch.compile compatibility with varlen APIs

  #11970 opened Jul 21, 2025

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

  #11976 opened Jul 23, 2025

• Add comprehensive input validation for training hyperparameters in ControlNet Flux training script

  #11980 opened Jul 23, 2025

• Update installation.md

  #11983 opened Jul 23, 2025

• [Modular] LTX

  #11986 opened Jul 24, 2025

• [refactor] condense group offloading

  #11990 opened Jul 25, 2025

• Fix EDMEulerScheduler training with integer timesteps

  #11991 opened Jul 25, 2025

• [modular diffusers] Wan I2V/FLF2V

  #11997 opened Jul 27, 2025

• [lora] adapt new LoRA config injection method

  #11999 opened Jul 28, 2025

• [chore] complete the licensing statement.

  #12001 opened Jul 28, 2025

• [tests] tighten compilation tests for quantization

  #12002 opened Jul 28, 2025

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

  #12005 opened Jul 28, 2025

• 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

• [wan2.2] follow-up

  #12024 opened Jul 30, 2025

• [docs] Install

  #12026 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

• tests + minor refactor for QwenImage

  #12057 opened Aug 4, 2025

• Cross attention module to Wan Attention

  #12058 opened Aug 4, 2025

46 Issues closed by 16 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

• A compatibility issue when using custom Stable Diffusion with pre-trained ControlNets

  #11984 closed Jul 24, 2025

• closed

  #11946 closed Jul 23, 2025

• Passing enable_gqa flag in attention dispatcher should be version guarded

  #11959 closed Jul 22, 2025

• What is the minimum memory requirement for model training?

  #11971 closed Jul 22, 2025

• Implement caching on LTX and WAN video models

  #11134 closed Jul 18, 2025

• Kontext model loading quantization problem

  #11951 closed Jul 18, 2025

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

  #11374 closed Jul 16, 2025

• flux pipeline not work with DPMSolverMultistepScheduler and UniPCMultistepScheduler

  #11907 closed Jul 16, 2025

• [Docs] Visualizing the codebase for diffusers

  #11866 closed Jul 15, 2025

• Support for Large attn_bias via Sparse Tensors or On‑The‑Fly Construction (seq_len ≈ 12 288)

  #11928 closed Jul 15, 2025

• Loading multiple LoRAs to 1 pipeline in parallel, 1 LoRA to 2-pipelines on 2-GPUs

  #11914 closed Jul 15, 2025

• refactors pipelines inheriting from `StableDiffusionPipeline`

  #6984 closed Jul 15, 2025

• Question about control sd3

  #11867 closed Jul 14, 2025

• SD3ControlNet

  #11917 closed Jul 14, 2025

• WanVACETransformer3DModel with GGUF not working for 1.3B model

  #11878 closed Jul 12, 2025

• Issue with FluxKontextPipeline

  #11886 closed Jul 12, 2025

• AttributeError: type object 'CosmosTransformer3DModel' has no attribute 'from_single_file'

  #11865 closed Jul 11, 2025

• Avoid creating tensor in CosmosAttnProcessor2_0

  #11761 closed Jul 10, 2025

• ControlnetUnion not working correctly

  #11861 closed Jul 10, 2025

• Run FluxKontextPipeline with multi-images input, But An error occurred

  #11824 closed Jul 9, 2025

• stabilityai/stable-diffusion-2 is missing fp16 files

  #11900 closed Jul 9, 2025

• stabilityai/stable-diffusion-2 is missing fp16 files

  #11898 closed Jul 9, 2025

• Error in init from pretrained for LTXConditionPipeline

  #11644 closed Jul 9, 2025

• AutoencoderDC.encode fails with torch.compile(fullgraph=True) - "name 'torch' is not defined"

  #11864 closed Jul 9, 2025

• Support custom_pipeline argument for Diffuser T2V Community Pipelines

  #11183 closed Jul 7, 2025

• Multi-ID customization with CogvideoX 5B

  #10462 closed Jul 5, 2025

• When using gradient accumulation, optimizer.step() runs every single step. Is it as expected？

  #10855 closed Jul 5, 2025

• Time series diffusion

  #10886 closed Jul 5, 2025

• train_dreambooth_lora_flux crash on batch size greater than 1

  #10994 closed Jul 5, 2025

• support SageAttention

  #11121 closed Jul 5, 2025

• How to multi-GPU WAN inference

  #11339 closed Jul 5, 2025

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

  #11370 closed Jul 5, 2025

• Bug: set adapters when model is compiled

  #11766 closed Jul 5, 2025

• support for MeanFlow

  #11781 closed Jul 5, 2025

• [FR] Please support WanVACETransformer3DModel.from_single_file

  #11630 closed Jul 5, 2025

• set_lora_device reports KeyError even though lora is loaded

  #11833 closed Jul 4, 2025

42 Issues opened by 37 people

• 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

• 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 opened Jul 28, 2025

• Using AutoModel.from_pretrained for wan2.1 crash my notebook

  #11996 opened Jul 27, 2025

• Problems with Kontext quantization

  #11992 opened Jul 25, 2025

• Groupoffloading introduce bad results

  #11981 opened Jul 23, 2025

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

  #11978 opened Jul 23, 2025

• how to load a finetuned model especially during validation phase

  #11977 opened Jul 23, 2025

• train_dreambooth_lora_flux_kontext.py: error: the following arguments are required: --instance_prompt

  #11973 opened Jul 22, 2025

• How about forcing the first and last block on device when groupoffloading is used?

  #11966 opened Jul 21, 2025

• Highdream multiple gpu to offload llama

  #11965 opened Jul 21, 2025

• KeyError when loading LoRA for Flux model: missing lora_unet_final_layer_adaLN_modulation_1 weights

  #11964 opened Jul 21, 2025

• New Adapter/Pipeline Request: IT-Blender for Creative Conceptual Blending

  #11961 opened Jul 20, 2025

• Flash/Sage varlen does not work with torch.compile

  #11957 opened Jul 18, 2025

• Frequency-Decoupled Guidance (FDG) for diffusion models

  #11956 opened Jul 18, 2025

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

  #11948 opened Jul 17, 2025

• Floating point exception with nightly PyTorch and CUDA

  #11945 opened Jul 17, 2025

• ValueError when loading Lycoris safetensors LoRA: keys not correctly renamed

  #11943 opened Jul 16, 2025

• train flux_controlnet code need to update

  #11939 opened Jul 16, 2025

• RMSNorm's weight not registered as submodules when initializing

  #11938 opened Jul 16, 2025

• how to run convert_cosmos_to_diffusers.py correctly?

  #11930 opened Jul 15, 2025

• FLUX.1-Fill-dev running problem

  #11922 opened Jul 14, 2025

• Create modular pipeline from existing pipeline

  #11915 opened Jul 12, 2025

• Fused QKV projections incompatible with training

  #11903 opened Jul 9, 2025

• SD3.5-Controlnet-8b does not use encoder_hidden_states

  #11902 opened Jul 9, 2025

• can not load Wan2.1-Fun-14B-InP-MPS_reward_lora_comfy.safetensors to wan2.1-14b-720p-diffusers

  #11901 opened Jul 9, 2025

• stabilityai/stable-diffusion-2 is missing fp16 files

  #11899 opened Jul 9, 2025

• Error during batch inference using FluxControlNetInpaintingPipeline

  #11889 opened Jul 8, 2025

• `load_lora_weights` bug in FLUX.1 `diffusers-0.35.0.dev0`

  #11885 opened Jul 8, 2025

• [lora] `exclude_modules` won't consider the modules names in `target_modules`

  #11874 opened Jul 7, 2025

• CPU Offloading Inefficiency: UNet/Transformer Repeatedly Moved Between CPU/GPU During Loops

  #11872 opened Jul 6, 2025

• STORK Scheduler

  #11859 opened Jul 4, 2025

45 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.

• [tests] unbloat `tests/lora/utils.py`

  #11845 commented on Jul 7, 2025 • 2 new comments

• [ci] enable hotswapping tests on our nightly CI.

  #11826 commented on Jul 16, 2025 • 2 new comments

• [LoRA training] add aspect ratio bucketing

  #11438 commented on Jul 16, 2025 • 2 new comments

• WanVACEPipeline: Passing a list of prompts is not yet supported. This may be supported in the future.

  #11821 commented on Jul 5, 2025 • 0 new comments

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

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

• AnimateDiff SparseCtrl RGB does not work as expected

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

• [Fix Issue #1197 since 2022] Support pre-trained openai/guided-diffusion (ADM) with minimal code change

  #6730 commented on Jul 4, 2025 • 0 new comments

• Support for control-lora

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

• Bump transformers from 4.38.0 to 4.48.0 in /examples/research_projects/realfill

  #10766 commented on Jul 10, 2025 • 0 new comments

• [WIP] Add FlashVideo Text-to-Video Pipeline

  #10838 commented on Jul 21, 2025 • 0 new comments

• Add gradient checkpointing support for AutoencoderKLWan

  #11105 commented on Jul 22, 2025 • 0 new comments

• [Quantization] Add TRT-ModelOpt as a Backend

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

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

  #11234 commented on Jul 10, 2025 • 0 new comments

• Laplace Scheduler for DDPM

  #11320 commented on Jul 9, 2025 • 0 new comments

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

  #11415 commented on Jul 10, 2025 • 0 new comments

• Update pipeline_flux_fill.py

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

• Bump torch from 2.2.0 to 2.7.1 in /examples/research_projects/realfill

  #11664 commented on Jul 10, 2025 • 0 new comments

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

  #11684 commented on Jul 16, 2025 • 0 new comments

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

  #11686 commented on Jul 15, 2025 • 0 new comments

• Add MAGI-1: Autoregressive Video Generation at Scale

  #11713 commented on Jul 24, 2025 • 0 new comments

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

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

• [wip] Higgs quantization

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

• Propose to refactor output normalization in several transformers

  #11850 commented on Jul 18, 2025 • 0 new comments

• FlowMatchEulerDiscreteScheduler Timesteps have Floating Point Errors

  #11749 commented on Jul 5, 2025 • 0 new comments

• set_adapters not support for compiled model

  #11408 commented on Jul 5, 2025 • 0 new comments

• WanImageToVideoPipeline - swap out a limited number of blocks

  #10999 commented on Jul 5, 2025 • 0 new comments

• `StableAudioDiTModel` throws `[rank0]: RuntimeError: DDP...` on `accelerator.prepare` when training on 4 GPUs

  #10160 commented on Jul 5, 2025 • 0 new comments

• StableDiffusionXLControlNetUnionInpaintPipeline requires a float for controlnet_conditioning_scale & control_guidance_end

  #11828 commented on Jul 6, 2025 • 0 new comments

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

  #11489 commented on Jul 6, 2025 • 0 new comments

• EMA training for PEFT LoRAs

  #9998 commented on Jul 8, 2025 • 0 new comments

• Comments bug in FluxPriorReduxPipeline

  #10457 commented on Jul 9, 2025 • 0 new comments

• Try load gguf for FluxKontextPipeline but invalid input size

  #11839 commented on Jul 11, 2025 • 0 new comments

• HunyuanVIdeo in diffusers use negative_prompt but generate wrong video

  #10901 commented on Jul 15, 2025 • 0 new comments

• Dreambooth finetune FLUX dev CLIPTextModel

  #10925 commented on Jul 16, 2025 • 0 new comments

• Bug: lora trained with train_dreambooth_lora_sdxl_advanced.py, the weight cannot be loaded

  #11790 commented on Jul 16, 2025 • 0 new comments

• Add SUPIR Upscaler

  #7219 commented on Jul 16, 2025 • 0 new comments

• Multi-gpus Context Parallel training support?

  #11020 commented on Jul 18, 2025 • 0 new comments

• Wan Video Vae RemoteVae

  #11326 commented on Jul 18, 2025 • 0 new comments

• Different generation with `Diffusers` in I2V tasks for LTX-video

  #10565 commented on Jul 18, 2025 • 0 new comments

• F5-TTS Integration

  #10043 commented on Jul 19, 2025 • 0 new comments

• Implementation error of v_prediction in eulara and eular

  #7046 commented on Jul 21, 2025 • 0 new comments

• Loading a Lora on quantized model ? TorchaoLoraLinear.__init__() missing 1 required keyword-only argument: 'get_apply_tensor_subclass'

  #10621 commented on Jul 21, 2025 • 0 new comments

• AttributeError: 'str' object has no attribute 'convert' when training controlnet

  #6858 commented on Jul 21, 2025 • 0 new comments

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

  #11499 commented on Jul 25, 2025 • 0 new comments

• Flux FIll lora / dreambooth finetune support

  #11145 commented on Jul 28, 2025 • 0 new comments