-
Notifications
You must be signed in to change notification settings - Fork 10.6k
Pull requests: comfyanonymous/ComfyUI
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Use same code for chroma and flux blocks so that optimizations are shared.
#10746
by comfyanonymous
was merged Nov 14, 2025
Loading…
feat: add create_time dict to prompt field in /history and /queue
Core
Core team dependency
#10741
by ric-yu
was merged Nov 13, 2025
Loading…
add PR template for API-Nodes
Core
Core team dependency
#10736
by bigcat88
was merged Nov 13, 2025
Loading…
Update Python 3.14 compatibility notes in README
#10730
by comfyanonymous
was merged Nov 12, 2025
Loading…
Update README.md for Intel Arc GPU installation, remove IPEX
#10729
by qiacheng
was merged Nov 12, 2025
Loading…
always unload re-used but modified models - Fixed bad outputs in some Upscaler / Lora flows
#10724
by rattus128
was merged Nov 12, 2025
Loading…
Don't pin tensor if not a torch.nn.parameter.Parameter
#10718
by comfyanonymous
was merged Nov 12, 2025
Loading…
Update CI workflow to remove dead macOS runner.
Run-CI-Test
This is an administrative label to tell the CI to run full automatic testing on this PR now.
#10704
by comfyanonymous
was merged Nov 10, 2025
Loading…
Try to disable pinned memory if wrong behavior detected.
#10703
by comfyanonymous
was closed Nov 12, 2025
Loading…
ops: Put weight cast on the offload stream - Fixes --async-offload black screen
#10697
by rattus128
was merged Nov 10, 2025
Loading…
Unload weights if vram usage goes up between runs.
#10690
by comfyanonymous
was merged Nov 9, 2025
Loading…
Only unpin tensor if it was pinned by ComfyUI
#10677
by comfyanonymous
was merged Nov 7, 2025
Loading…
mm: guard against double pin and unpin explicitly
#10672
by rattus128
was merged Nov 7, 2025
Loading…
Tell users they need to upload their logs in bug reports.
#10671
by comfyanonymous
was merged Nov 7, 2025
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.