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 18, 2026
Latest indexed: Sep 17, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: help wanted good first issue

Beginner friendly Everything

Open All

838 open issues indexed

ConnectionError: Tried to launch distributed communication on port 29401, but another process is utilizing it. Please specify a different port (such as using the --main_process_port flag or specifying a different main_process_port in your config file) and rerun your script. To automatically use the next open port (on a single node), you can set this to 0. Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 20/100

huggingface/diffusers#9856 · 7 comments · Opened Nov 4, 2024
`prepare_ip_adapter_image_embeds` Bug Causes Feature Mixing During Batch Processing in IP-Adapter Open

bug

huggingface/diffusers#9813 · 4 comments · 1 reaction · 2 assignees · Opened Oct 30, 2024
Lora does not support module_to_save() Open

bug stale

Difficulty 3/5 1-2 days Newbie friendliness 35/100

huggingface/diffusers#9810 · 2 comments · Opened Oct 30, 2024
Flux LoRA loading failure Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9803 · 7 comments · Opened Oct 30, 2024
Multidiffusion (panorama pipeline) is missing segmentation inputs? Open

stale

Difficulty 5/5 Over a week Newbie friendliness 25/100

huggingface/diffusers#9802 · 5 comments · Opened Oct 29, 2024
Loading pipeline in precision it was saved in Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

huggingface/diffusers#9797 · 10 comments · 3 reactions · Opened Oct 29, 2024
Add support to Meissonic Open

contributions-welcome stale

Difficulty 5/5 Over a week Newbie friendliness 30/100

huggingface/diffusers#9794 · 7 comments · Opened Oct 29, 2024
Support SOTA Difussion Based talking head repos like Echomimic if not already supported Open

stale

Difficulty 5/5 Over a week Newbie friendliness 20/100

huggingface/diffusers#9783 · 2 comments · Opened Oct 28, 2024
Is it possible to provide img2img code for CogView3? Open

contributions-welcome stale

Difficulty 4/5 3-5 days Newbie friendliness 25/100

huggingface/diffusers#9750 · 3 comments · Opened Oct 23, 2024
Add Ultimate SD Upscale pipeline for high-quality tiled image upscaling Open

huggingface/diffusers#9740 · 22 comments · 1 assignee · Opened Oct 22, 2024
How to use Playground2.5 to train lora with own dataset to generate pictures of a specific style？ Open

bug stale

Difficulty 5/5 Over a week Newbie friendliness 18/100

huggingface/diffusers#9731 · 1 comment · Opened Oct 21, 2024
Ctrlora implementation : Easy solution to train a controlnet with < 1000 examples Open

contributions-welcome stale

Difficulty 5/5 Over a week Newbie friendliness 30/100

huggingface/diffusers#9713 · 5 comments · 6 reactions · Opened Oct 18, 2024
FLUX.1-dev FP8 Example Code Cleanup Open

Difficulty 1/5 1-3 hours Newbie friendliness 45/100

huggingface/diffusers#9690 · 8 comments · Opened Oct 16, 2024
[SD3 ControlNet] bug in pipeline 'controlnet_pooled_projections' Open

bug stale

Difficulty 3/5 1-2 days Newbie friendliness 45/100

huggingface/diffusers#9686 · 11 comments · Opened Oct 15, 2024
Error in loading flux fp8 model with local transformer_flux.py file Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9667 · 2 comments · Opened Oct 14, 2024
Code With Strange Logic in CogVideoX's Dynamic CFG Open

bug wip

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9641 · 3 comments · 3 reactions · Opened Oct 11, 2024
XFormer fails when passing attention mask while using bfloat and key's sequence length not being a multiple of 8 Open

bug stale

Difficulty 3/5 1-2 days Newbie friendliness 45/100

huggingface/diffusers#9637 · 4 comments · Opened Oct 10, 2024
[Flux ControlNet] Add support for de-distilled models with CFG Open

contributions-welcome good first issue

Difficulty 4/5 3-5 days Newbie friendliness 48/100

huggingface/diffusers#9635 · 15 comments · Opened Oct 10, 2024
Error when setting num_single_layers=0 while training flux-controlnet on a multi-GPU server using a single GPU Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9630 · 8 comments · Opened Oct 9, 2024
[Schedulers] Add methods for conversion between noise and denoised predictions Open

scheduler stale

Difficulty 5/5 Over a week Newbie friendliness 25/100

huggingface/diffusers#9629 · 5 comments · Opened Oct 9, 2024
process_encoder_hidden_states function is applied on each denoising step Open

stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9625 · 6 comments · Opened Oct 9, 2024
FlowMatch schedulers - closing the gap Open

scheduler wip

huggingface/diffusers#9607 · 11 comments · 1 assignee · Opened Oct 8, 2024
APG: Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models Open

consider-for-modular-diffusers stale

huggingface/diffusers#9585 · 6 comments · 12 reactions · 1 assignee · Opened Oct 4, 2024
Problems with saved lora models when using rslora. Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9556 · 7 comments · 2 reactions · Opened Sep 30, 2024
Freeing GPU memory after `torch.compile` StableDiffusionXLPipeline UNet Open

stale torch-compile

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9530 · 4 comments · Opened Sep 25, 2024
Multi-controlnet batching for `StableDiffusionXLControlNetInpaintPipeline` Open

contributions-welcome stale

Difficulty 4/5 3-5 days Newbie friendliness 52/100

huggingface/diffusers#9511 · 5 comments · Opened Sep 24, 2024
AnimateDiff SparseCtrl RGB does not work as expected Open

advanced bug contributions-welcome help wanted stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9508 · 9 comments · Opened Sep 23, 2024
Confusion about `FrozenDict` in `configuration_utils.py` Open

stale

Difficulty 5/5 Over a week Newbie friendliness 20/100

huggingface/diffusers#9503 · 3 comments · Opened Sep 23, 2024
Dreambooth Flux training does not save a model for around 10-15 minutes Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9501 · 16 comments · Opened Sep 23, 2024
Dreambooth Flux training failed on saving a checkpoint Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9500 · 26 comments · Opened Sep 23, 2024
Can we allow making everything on gpu/cuda for scheduler? Open

performance scheduler stale

huggingface/diffusers#9485 · 14 comments · 2 assignees · Opened Sep 20, 2024
FLUX dreambooth train on multigpu with deepspeed Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 25/100

huggingface/diffusers#9484 · 13 comments · Opened Sep 20, 2024
train_dreambooth_lora_flux validation RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

huggingface/diffusers#9476 · 11 comments · Opened Sep 19, 2024
Formulation of reverse diffusion process in DDPM ( 1 - alpha_prod_t = beta_prod_t assumption) Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9474 · 5 comments · Opened Sep 19, 2024
Remove redundant comparison inside the diffusion loop of stable video diffusion pipeline Open

stale

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

huggingface/diffusers#9425 · 8 comments · Opened Sep 12, 2024
Suggestion for speeding up `index_for_timestep` by removing sequential `nonzero()` calls in samplers Open

contributions-welcome help wanted performance wip

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9417 · 11 comments · Opened Sep 11, 2024
[Q] Possibly unused `self.final_alpha_cumprod` Open

stale

Difficulty 3/5 1-2 days Newbie friendliness 35/100

huggingface/diffusers#9395 · 7 comments · Opened Sep 9, 2024
deepspeed train flux1 dreambooth lora can not save model Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9393 · 21 comments · Opened Sep 9, 2024
[Scheduler] Add SNR shift following SD3, would the rest of the code need to be modified? Open

stale

Difficulty 5/5 Over a week Newbie friendliness 25/100

huggingface/diffusers#9392 · 7 comments · Opened Sep 9, 2024
FlaxStableDiffusionImg2ImgPipeline should delete prepare_inputs and provide prepare_text_inputs and prepare_image_inputs Open

stale

Difficulty 2/5 1-3 hours Newbie friendliness 38/100

huggingface/diffusers#9371 · 4 comments · Opened Sep 5, 2024
IndexError: index 29 is out of bounds for dimension 0 with size 29 Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 35/100

huggingface/diffusers#9362 · 8 comments · Opened Sep 4, 2024
Redundant reinitialization of text encoders in train_dreambooth_lora_flux Open

bug stale

Difficulty 3/5 1-2 days Newbie friendliness 50/100

huggingface/diffusers#9358 · 2 comments · Opened Sep 3, 2024
pipeline_stable_diffusion_xl_adapter Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 25/100

huggingface/diffusers#9356 · 6 comments · Opened Sep 3, 2024
Text generation? Open

wip

huggingface/diffusers#9352 · 13 comments · 1 assignee · Opened Sep 3, 2024
FLUX error when loading with low_cpu_mem_usage=False and ignore_mismatched_sizes=True Open

bug stale

Difficulty 3/5 1-2 days Newbie friendliness 35/100

huggingface/diffusers#9343 · 16 comments · Opened Sep 2, 2024
StableDiffusionPipeline.from_pretrained() fails to load specified models, resulting in identical weights Open

bug stale

Difficulty 4/5 3-5 days Newbie friendliness 30/100

huggingface/diffusers#9332 · 3 comments · Opened Aug 31, 2024
[Pipeline] AnimateDiff + SparseControl + ControlNet Open

community-examples consider-for-modular-diffusers contributions-welcome good first issue

Difficulty 5/5 Over a week Newbie friendliness 45/100

huggingface/diffusers#9329 · 17 comments · Opened Aug 30, 2024
Unload lora specific lora weight Open

lora stale

huggingface/diffusers#9325 · 22 comments · 2 assignees · Opened Aug 30, 2024
Finetuned models aren't saved or loaded properly in train_custom_diffusion.py Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 45/100

huggingface/diffusers#9320 · 8 comments · Opened Aug 29, 2024
[Add] VEnhancer - the interpolation and upscaler for CogVideoX-5b Open

stale

Difficulty 5/5 Over a week Newbie friendliness 20/100

huggingface/diffusers#9303 · 3 comments · 1 reaction · Opened Aug 28, 2024

huggingface/diffusers

Get new issues in your inbox