Skip to content

Pull requests: huggingface/diffusers

New pull request New
314 Open 6,716 Closed
314 Open 6,716 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[ci] claude in ci.
#13297 opened Mar 20, 2026 by sayakpaul Loading…
remove str option for quantization config in torchao
#13291 opened Mar 19, 2026 by howardzhang-cv Loading…
15
[export] Add export-safe LRU cache helper
#13290 opened Mar 19, 2026 by cbensimon Loading…
3
[Neuron] Add AWS Neuron (Trainium/Inferentia) as an officially supported device
#13289 opened Mar 19, 2026 by JingyaHuang • Draft
1
Add low precision attention API from torchao to TorchAoConfig
#13285 opened Mar 19, 2026 by howardzhang-cv • Draft
2 tasks
Update attention_backends.md to update FA3 minimum support to Ampere
#13283 opened Mar 18, 2026 by sayakpaul Loading…
4
Fix the attention mask in ulysses SP for QwenImage
#13278 opened Mar 17, 2026 by zhtmike Loading…
2 of 6 tasks
18
[WIP] [core] fix group offloading when using torchao
#13276 opened Mar 17, 2026 by sayakpaul • Draft
4
fix: wrap validation inference with torch.no_grad() in dreambooth examples
#13273 opened Mar 16, 2026 by gambletan Loading…
2 tasks
1
fix: compute image_seq_len from spatial dims in Lumina2 pipeline
#13272 opened Mar 16, 2026 by gambletan Loading…
1
Add DiffSynth blockwise ControlNet support to QwenImageControlNetModel
#13268 opened Mar 15, 2026 by aryabyte21 Loading…
4 of 5 tasks
1
Fix missing gradient_checkpointing init in ZImageControlNetModel
#13267 opened Mar 15, 2026 by yunjoochoi Loading…
add tensor and numpy array support for image input in Flux2KleinPipeline
#13265 opened Mar 14, 2026 by abhixb Loading…
2
[not for land yet]: improve cuda graph support for Qwen-Image
#13263 opened Mar 12, 2026 by vkuzo Loading…
6 tasks
2
[CI] Refactor LTX Transformer Tests
#13254 opened Mar 11, 2026 by DN6 Loading…
6 tasks
[CI] Refactor Z Image Transformer Tests
#13253 opened Mar 11, 2026 by DN6 Loading…
6 tasks
fix: handle LoKr format keys in Z-image LoRA conversion
#13250 opened Mar 10, 2026 by s-zx Loading…
1
3
[tests] Tests for conditional pipeline blocks
#13247 opened Mar 10, 2026 by sayakpaul Loading…
Fix double-shifted sigma_min/sigma_max in FlowMatchEulerDiscreteScheduler
#13246 opened Mar 10, 2026 by kvr06-ai Loading…
3 tasks done
1
[tests] test load_components in modular
#13245 opened Mar 10, 2026 by sayakpaul Loading…
Fix IndexError in HunyuanVideo I2V pipeline
#13244 opened Mar 10, 2026 by kaixuanliu Loading…
3
[tests] migrate test_hooks.py to pytest
#13242 opened Mar 10, 2026 by sayakpaul Loading…
fix: deduplicate timesteps in DPMSolverMultistep for squaredcos_cap_v2 + karras/lu sigmas
#13240 opened Mar 10, 2026 by Chase-Xuu Loading…
1
Add support for FLUX.2 Klein 9B and 4B in single_file_utils
#13237 opened Mar 9, 2026 by eliemichel Loading…
2 of 6 tasks
Fix error message in gguf_quantizer.py
#13236 opened Mar 9, 2026 by eliemichel Loading…
1 task done
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.