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

31 beginner-friendly issues open

TangentialClassifierFreeGuidance.is_conditional reads an attribute that does not exist Open

bug needs-env-info pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#14794 · Opened Sep 16, 2026
Deprecating `Siglip2ImageProcessorFast` Open

bug needs-code-example needs-env-info pipelines

Difficulty 1/5 Under an hour Newbie friendliness 86/100

huggingface/diffusers#14780 · 1 comment · Opened Sep 15, 2026
save_pretrained(safe_serialization=False) leaves the old safetensors checkpoint behind, and from_pretrained loads it instead of the new weights Open

bug pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

huggingface/diffusers#14769 · 1 comment · Opened Sep 14, 2026
MiniMax-H3: float64 rotary position grid cannot be moved to MPS (`Cannot convert a MPS Tensor to float64`) Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

huggingface/diffusers#14639 · Opened Aug 28, 2026
document output_type="pt" in the agent docs Open

Difficulty 1/5 Under an hour Newbie friendliness 88/100

huggingface/diffusers#14616 · Opened Aug 27, 2026
Update remaining pipeline docstrings from `torch_dtype` to `dtype` Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

huggingface/diffusers#14591 · Opened Aug 24, 2026
InpaintProcessor.preprocess returns a bare tensor when no mask is passed, breaking its own 3-value contract Open

bug pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

huggingface/diffusers#14470 · 1 comment · Opened Aug 13, 2026
`register_to_config` mislabels positional `__init__` args as `_use_default_values`, so `from_config` round trips silently revert them to defaults Open

bug models

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

huggingface/diffusers#14460 · 3 comments · Opened Aug 13, 2026
VaeImageProcessorLDM3D ignores constructor configuration arguments Open

bug pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

huggingface/diffusers#14429 · 3 comments · Opened Aug 9, 2026
VaeImageProcessorLDM3D.preprocess fails for batched NumPy RGB/depth inputs Open

bug pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

huggingface/diffusers#14428 · Opened Aug 9, 2026
Division by 0 bug when only one denoising step Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#14411 · Opened Aug 6, 2026
Issue Labeler fails on most bug reports: 'needs-env-info' label does not exist Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

huggingface/diffusers#14377 · Opened Aug 3, 2026
Secret Leaks workflow fails on every new-branch push (6 of the last 30 runs) Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

huggingface/diffusers#14376 · 1 comment · Opened Aug 3, 2026
Remove deprecated VQModel/VQEncoderOutput shim (past target version 0.31) Open

bug models needs-code-example

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#14365 · 3 comments · Opened Aug 3, 2026
Incompatibility with torchao >= 0.17.0 due to hardcoded legacy import paths in torchao_quantizer.py Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

huggingface/diffusers#14303 · Opened Jul 27, 2026
[Bug] ChatGLMTokenizer special token property getters and setters are broken Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

huggingface/diffusers#14291 · Opened Jul 25, 2026
LTX2Pipeline: dynamic timestep shift `mu` is constant, ignores the actual sequence length Open

bug pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

huggingface/diffusers#14243 · 1 comment · Opened Jul 19, 2026
VaeImageProcessor.blur() docstring is missing blur_factor and has a copy-pasted description Open

bug needs-code-example pipelines

Difficulty 1/5 Under an hour Newbie friendliness 88/100

huggingface/diffusers#14209 · Opened Jul 17, 2026
DiffusionPipeline.download() on Windows silently skips all subfolder config.json files with huggingface_hub>=1.22.0 Open

bug pipelines

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#14142 · 2 comments · Opened Jul 8, 2026
Backport workflow-hardening fix (excessive-permissions) to 3 release branches Open

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

huggingface/diffusers#14085 · Opened Jun 29, 2026
SD1.5 - pipeline_controlnet_img2img and pipeline_controlnet_inpaint are mixing variables "image" and "control_image" Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 70/100

huggingface/diffusers#14057 · 1 comment · Opened Jun 23, 2026
Remove link to HEIM for diffusion model evaluation Open

Difficulty 1/5 Under an hour Newbie friendliness 90/100

huggingface/diffusers#14033 · Opened Jun 22, 2026
attention dispatcher assumes wrong attributes for flash attn kernel from hub Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#14012 · 1 comment · Opened Jun 20, 2026
from_pretrained fails loading deprecated pipelines Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#14008 · 1 comment · Opened Jun 20, 2026
Fix incorrect batch handling in _prepare_image_ids usage in train_dreambooth_lora_flux2_img2img.py Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

huggingface/diffusers#13811 · 1 comment · Opened May 26, 2026
UNet2DModel dtype property fails under nn.DataParallel with UnboundLocalError in get_parameter_dtype Open

bug models

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

huggingface/diffusers#13789 · Opened May 22, 2026
Division by zero in rescale_noise_cfg can produce NaNs during inference Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

huggingface/diffusers#13425 · Opened Apr 6, 2026
DDPMScheduler allows num_inference_steps=0 without validation (inconsistent with DDIMScheduler) Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 65/100

huggingface/diffusers#13394 · 2 comments · Opened Apr 3, 2026
Distributed gather crashes on PyTorch < 2.6 Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

huggingface/diffusers#13074 · Opened Feb 3, 2026
[DDIMInverseScheduler] `inf` values at first iteration when `set_alpha_to_one=True` and `prediction_type="sample"` Open

bug stale

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

huggingface/diffusers#10920 · 4 comments · Opened Feb 27, 2025
Bugs in PixArtImageProcessor.resize_and_crop_tensor Open

bug stale

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

huggingface/diffusers#8911 · 3 comments · Opened Jul 20, 2024

huggingface/diffusers

Get new issues in your inbox