huggingface/diffusers

View on GitHub

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Stars: 34.5k
Forks: 7.3k
Open beginner issues: 22
Indexed issues: 838
Avg merge: 3d 3h
Merged PRs (30d): 91

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 15, 2026
Latest indexed: Sep 17, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: help wanted good first issue

Open All

838 open issues indexed

stabilityai/stable-diffusion-2-1 does not appear to have a file named config.json. Open

bug stale

huggingface/diffusers#7935 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Combining community pipeline for image generation Open

bug stale

huggingface/diffusers#7945 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
custom_pipeline not being cached Open

bug stale

huggingface/diffusers#7946 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Support MuLan, a plug-and-play language adapter to adapt existing diffusion model for up to 110+ languages without additional training Open

community-examples contributions-welcome stale

huggingface/diffusers#7948 · 2 comments · 3 reactions · 0 assignees · Indexed Sep 17, 2026
ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preservation Open

community-examples contributions-welcome stale

huggingface/diffusers#7955 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Increasing RAM usage with enable_model_cpu_offload Open

bug stale

huggingface/diffusers#7970 · 9 comments · 7 reactions · 0 assignees · Indexed Sep 17, 2026
Full SDXL DreamBooth finetuning, LoRA extraction Open

stale

huggingface/diffusers#7997 · 7 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
FIFO-Diffusion: Generating Infinite Videos from Text without Training through Rolling Video Denoising Open

community-examples contributions-welcome Good second issue

huggingface/diffusers#8274 · 6 comments · 2 reactions · 0 assignees · Indexed Sep 17, 2026
Consistency training fails to converge Open

stale

huggingface/diffusers#8277 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
DPM solver ++ third order with SDE Open

stale

huggingface/diffusers#8288 · 8 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Training] Resume checkpoint global step inconsistent/confusion across scripts Open

bug stale

huggingface/diffusers#8296 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Diffusion Transformers License Open

bug stale

huggingface/diffusers#8306 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Add Conditional Diffusion Distillation Open

stale

huggingface/diffusers#8309 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[0.27.2]: from_single_file: 'AutoencoderKL' object has no attribute '__name__'. Did you mean: '__ne__'? Open

bug stale

huggingface/diffusers#8320 · 10 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
scheduler文件无法识别 Open

bug stale

huggingface/diffusers#8323 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Bug in FlaxDiffusionPipeline's from_pt option in Google Collab's TPUv2 Open

bug stale

huggingface/diffusers#8358 · 15 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[Community] Help us fix the LR schedulers when `num_train_epochs` is passed in a distributed training env Open

contributions-welcome Good second issue

huggingface/diffusers#8384 · 16 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Make the input `UNet2DConditionModel` and the returned `UNetMotionModel` instances share weights Open

stale

huggingface/diffusers#8398 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Use multiple controlnets tensor size error Open

bug stale

huggingface/diffusers#8405 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
support TextDiffuser pipelines natively in Diffusers Open

contributions-welcome stale

huggingface/diffusers#8410 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[🌟 New Model] ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation Open

contributions-welcome stale

huggingface/diffusers#8414 · 13 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Request to add discriminator based guidance Open

consider-for-modular-diffusers stale

huggingface/diffusers#8418 · 7 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
controlNet training for dstilled models Open

stale

huggingface/diffusers#8424 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Support multiple control nets in the `StableDiffusionControlNetXSPipeline`/`StableDiffusionXLControlNetXSPipeline` Open

community-examples contributions-welcome good first issue

huggingface/diffusers#8434 · 12 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
How to use EDM2 model with diffusers? Open

stale

huggingface/diffusers#8439 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
create_dynamic_module infinite recursion when setting HF_HOME using relative path Open

bug stale

huggingface/diffusers#8441 · 6 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
Running `diffusers/stable-diffusion-xl-1.0-inpainting-0.1` with `StableDiffusionXLInpaintPipeline` introduces weird noise when strength is set to 1.0 during inference Open

bug stale

huggingface/diffusers#8450 · 15 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
StableCascadeUNet.from_single_file not working error runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json. Open

single_file stale

huggingface/diffusers#8465 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Allow user to pick which Text Encoders to train with SD3-Medium. Open

stale

huggingface/diffusers#8504 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SD3] train_dreambooth_sd3.py --train_text_encoder fails Open

bug stale

huggingface/diffusers#8507 · 3 comments · 3 reactions · 0 assignees · Indexed Sep 17, 2026
EMAModel causes InstructP2P parallel fine-tuning error Open

bug stale

huggingface/diffusers#8514 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
playground cuda error Open

stale

huggingface/diffusers#8523 · 15 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
SD3 dreambooth training - caching of embeddings and vae representations Open

stale

huggingface/diffusers#8540 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
SD3 latents error 'tuple' object has no attribute 'to' issue on stable_diffusion_3/pipeline_stable_diffusion_3.py Open

stale

huggingface/diffusers#8545 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SD3] Incorrect stochastic sampling implementation Open

bug stale

huggingface/diffusers#8549 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
StableDiffusionXLInpaintPipeline: image latent not transferred to correct device when using `device_map="balanced"` on VAE model Open

bug stale

huggingface/diffusers#8551 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[BUG] convert T5 text encoder to float16 results corrupted image Open

bug stale

huggingface/diffusers#8604 · 15 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
global, eager model weight GPU unloading Open

stale

huggingface/diffusers#8605 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
can not use custom_pipeline hd_painter with IP_adapter Open

bug stale

huggingface/diffusers#8609 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Classifier free guidance(CFG) on different prediction types and karras style schedulers Open

stale

huggingface/diffusers#8617 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
There is no create_diffusers_controlnet_model_from_ldm function in single_file_utils.py Open

bug single_file stale

huggingface/diffusers#8645 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
StableDiffusionControlNetImg2ImgPipeline call report “argument of type 'NoneType' is not iterable” Open

bug stale

huggingface/diffusers#8647 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
train_text_to_image_sdxl.py fail resume from checkpoint and also can not load for infer Open

bug stale

huggingface/diffusers#8659 · 4 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
AnimateDiffSDXL + Multi Controlnets support Open

consider-for-modular-diffusers contributions-welcome stale

huggingface/diffusers#8664 · 7 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Attention masks are missing in SD3 to mask out text padding tokens Open

contributions-welcome wip

huggingface/diffusers#8673 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
A bug about one-step inference in PixArtAlphaPipeline Open

bug stale

huggingface/diffusers#8689 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Text encoder errors in both SD3 dreambooth training scripts Open

bug stale

huggingface/diffusers#8726 · 8 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Clarification Needed on Hardcoded Value in Conditional Statement in LeditPP Open

stale

huggingface/diffusers#8760 · 3 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
Model and input data type is not same Open

stale

huggingface/diffusers#8780 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
SDXL TensorRT + IP Adapter Open

stale

huggingface/diffusers#8790 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 17, 2026

huggingface/diffusers

Get new issues in your inbox