Skip to content

Pull requests: huggingface/diffusers

New pull request New
296 Open 6,634 Closed
296 Open 6,634 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

Support Flux Klein peft (fal) lora format
#13169 opened Feb 20, 2026 by asomoza Loading…
1
3
[Modular] Save Modular Pipeline weights to Hub
#13168 opened Feb 20, 2026 by DN6 Loading…
6 tasks
9
[attention backends] use dedicated wrappers from fa3 for cp.
#13165 opened Feb 19, 2026 by sayakpaul Loading…
7
[attention backends] change to updated repo and version.
#13161 opened Feb 18, 2026 by sayakpaul Loading…
5
[docs] deprecate pipelines
#13157 opened Feb 17, 2026 by stevhliu Loading…
2
[tests] refactor UNet model tests to align with the new pattern
#13153 opened Feb 16, 2026 by sayakpaul Loading…
3
[Modular] update the auto pipeline blocks doc
#13148 opened Feb 15, 2026 by yiyixuxu Loading…
13
Fix T5GemmaEncoder loading for transformers 5.x composite T5GemmaConfig
#13143 opened Feb 13, 2026 by DavidBert Loading…
3 of 6 tasks
1
1
Allows DDPM Scheduler to have Zero Variance on Generation Runs
#13141 opened Feb 13, 2026 by rustadadam Loading…
[docs] kernels
#13139 opened Feb 13, 2026 by stevhliu Loading…
7
Add Claude Diffusers skill and Claude Code plugin scaffold (#12935)
#13138 opened Feb 13, 2026 by aazeeem11 Loading…
1
fix: freeze shared transformer modules in ZImageControlNet.from_transformer
#13136 opened Feb 13, 2026 by jscaldwell55 Loading…
1
1
Fix missing .unsqueeze(1) in attention mask for HunyuanVideo VAE
#13133 opened Feb 13, 2026 by Minisal Loading…
1
[LoRA] Add support for Z-Image Base distilled loras
#13126 opened Feb 11, 2026 by asomoza Loading…
5
Fix CogVideoX scheduler prev_timestep for non-leading spacing
#13125 opened Feb 11, 2026 by Mr-Neutr0n Loading…
3 tasks
Allow Automodel to use from_config with custom code.
#13123 opened Feb 11, 2026 by DN6 Loading…
6 tasks
9
Fixing Kohya loras loading: Flux.1-dev loras with TE ("lora_te1_" prefix) + Flux.2-dev loras
#13118 opened Feb 10, 2026 by christopher5106 Loading…
1
8
Fix: handle remaining meta tensors in from_single_file before dispatch
#13117 opened Feb 10, 2026 by kitsune-hash Loading…
1
[tests] tests for modules_to_not_convert
#13116 opened Feb 10, 2026 by sayakpaul Loading…
Cosmos Transfer2.5 Auto-Regressive Inference Pipeline
#13114 opened Feb 10, 2026 by miguelmartin75 Loading…
4
Fix AudioLDM2Pipeline AttributeError with GPT2Model
#13111 opened Feb 9, 2026 by Mr-Neutr0n Loading…
3 tasks
1
1
Add bounds check for AuraFlow positional embedding indices
#13110 opened Feb 9, 2026 by Mr-Neutr0n Loading…
2 tasks
1
1
Fix SanaCombinedTimestepGuidanceEmbeddings to handle missing guidance
#13109 opened Feb 9, 2026 by Mr-Neutr0n Loading…
2 tasks
1
1
Fix DDIMScheduler.step() prev_timestep for non-leading spacing
#13108 opened Feb 9, 2026 by Mr-Neutr0n Loading…
3 tasks
1
1
fix(pipeline): Preserve dtype in from_pipe() instead of defaulting to float32
#13103 opened Feb 8, 2026 by Mr-Neutr0n Loading…
1
1
ProTip! Adding no:label will show everything without a label.