Skip to content

Pull requests: Comfy-Org/ComfyUI

New pull request New
677 Open 4,772 Closed
677 Open 4,772 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

Move file reads out of the remaining asset write transactions
#16486 opened Sep 23, 2026 by synap5e Contributor • 2/2 Loading…
8
Support w6a8 quantization format
#16483 opened Sep 22, 2026 by kijai Collaborator • Draft
feat: ming-image support
#16482 opened Sep 22, 2026 by kijai Collaborator • Draft
Drain the device before unpinning prefix-cache host memory
#16481 opened Sep 22, 2026 by sqz269 Loading…
5
Take the SQLite write lock up front for asset scan and output-registration writes
#16480 opened Sep 22, 2026 by synap5e Contributor • 1/2 Loading…
@guill
34
[Partner Nodes] feat(Anthropic): add Claude Opus 5.5 to the Claude node
#16479 opened Sep 22, 2026 by bigcat88 Contributor Loading…
4 of 8 tasks
1
[Partner Nodes] feat(Quiver): add Arrow 2 models with reasoning effort widget
#16478 opened Sep 22, 2026 by bigcat88 Contributor Loading…
4 of 8 tasks
1
Prevent conditioning fill from indexing empty regional destinations
#16477 opened Sep 22, 2026 by perfloop-agent Loading…
4
Fix stale Qwen3-VL generation cache state
#16476 opened Sep 22, 2026 by johnstonconnor773-ops Loading…
1
1
Add NVIDIA Easypanel deployment configuration
#16475 opened Sep 22, 2026 by lhresultadosdigitais-dev Loading…
6
Fix JSONDecodeError when a layer's comfy_quant marker is empty
#16474 opened Sep 22, 2026 by chelsealong Contributor Loading…
1
5
Add optional ROCmFPX Qwen text encoders
#16473 opened Sep 22, 2026 by Yasei-no-otoko Loading…
7
Fix Generate LTX2 Prompt leaking reasoning chain for Qwen3.5
#16469 opened Sep 22, 2026 by SDS-CC Loading…
3
Fix MiniMax H3 packed-sequence memory admission
#16460 opened Sep 22, 2026 by xmarre • Draft
[DO NOT MERGE] Assets: integration branch for #16358 + #16393
#16459 opened Sep 21, 2026 by synap5e-bot Bot • Draft
Bump comfyui-frontend-package to 1.54.7
#16456 opened Sep 21, 2026 by comfy-pr-bot Member • Draft
Fix Qwen flash attention CUDA gating
#16453 opened Sep 21, 2026 by johnstonconnor773-ops • Draft
1
1
docs: fix dead in-page anchor in README Apple Silicon install section
#16452 opened Sep 21, 2026 by aniketkrs Loading…
4
Re-enable int8 compute on MPS for PyTorch >= 2.15
#16451 opened Sep 21, 2026 by Isalia20 Loading…
3
Fix native abort: pause block-weight malloc graph while reading Qwen-Image 2.1 prefix cache
#16450 opened Sep 21, 2026 by chelsealong Contributor Loading…
1
2
Fix Qwen Image PEFT LoRA mapping
#16446 opened Sep 21, 2026 by johnstonconnor773-ops • Draft
1
17
Fix default inpainting workflow to preserve unmasked pixels
#16445 opened Sep 21, 2026 by johnstonconnor773-ops • Draft
1
19
README: tell NVIDIA users what to do about "no kernel image is available"
#16438 opened Sep 20, 2026 by joelp22-maker Loading…
6
Support NVFP4 conditioning for Qwen Image 2.1
#16432 opened Sep 20, 2026 by BennyDaBall930 Loading…
3
Add a node which enables safe passthrough behavior
#16417 opened Sep 20, 2026 by altoiddealer Loading…
19
ProTip! Exclude everything labeled bug with -label:bug.