Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Commits on master

Nightly Nvidia pytorch is now cu132 (#13288)
comfyanonymous committed 7 months ago
13917b3
Add portable release for intel XPU. (#13272)
comfyanonymous committed 7 months ago
f21f6b2
Update template to 0.9.43 (#13265)
Daxiong (Lin) committed 7 months ago
eb0686b
feat(api-nodes): new Partner nodes for Wan2.7 (#13264)
Alexander Piskun committed 7 months ago
5de94e7
Fix some issue with insecure browsers. (#13261)
comfyanonymous committed 7 months ago
76b75f3
Remove dead code. (#13251)
comfyanonymous committed 7 months ago
0c63b4f
chore: update workflow templates to v0.9.41 (#13242)
Daxiong (Lin) committed 7 months ago
7d43768
e2ddf28
Update README with note on model support (#13235)
comfyanonymous committed 7 months ago
076639f
Update README.md with latest AMD Linux pytorch. (#13228)
comfyanonymous committed 7 months ago
537c10d
Fix/tweak pinned memory accounting (#13221)
rattus committed 7 months ago
8d723d2
CORE-13 feat: Support RT-DETRv4 detection model (#12748)
Jukka Seppänen committed 7 months ago
a500f1e
Fix #13214 (#13216)
comfyanonymous committed 7 months ago
3f77450
b353a7c
Allow flux conditioning without a pooled output. (#13198)
comfyanonymous committed 7 months ago
3a56201
chore: update workflow templates to v0.9.39 (#13196)
ComfyUI Wiki committed 7 months ago
85b7495
chore: update workflow templates to v0.9.38 (#13176)
ComfyUI Wiki committed 7 months ago
359559c
feat(api-nodes): added new Topaz model (#13175)
Alexander Piskun committed 7 months ago
8165485
fix: regression in text generate with LTXAV model (#13170)
Jukka Seppänen committed 7 months ago
b0fd65e
Make Qwen 8B work with TextGenerate node. (#13160)
comfyanonymous committed 7 months ago
2a1f402
feat: Support Qwen3.5 text generation models (#12771)
Jukka Seppänen committed 7 months ago
404d7b9