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
Better Hidream O1 mem usage factor for non dynamic vram. (#13864)
2bd65f2 comfyanonymous committed 6 months ago
fix: create input directory if missing in LoadAudio define_schema (#13834)
cccb697 angad777 committed 6 months ago
Fix LTXV mid-video multi-frame guide alignment (CORE-129) (#13625)
1d95ed2 drozbay committed 6 months ago
Suppress false-positive Spectral lint on WebSocket endpoint (#13842)
a5f7bc5 Matt Miller committed 6 months ago
[Partner Nodes] new OpenAI Image node with DynamicCombo and Autogrow (#13838)
428c323 Alexander Piskun committed 6 months ago
[Partner Nodes] new ByteDanceSeedreamNodeV2 node with DynamicCombo and autogrow (#13811)
46063aa Alexander Piskun committed 6 months ago
[Partner Nodes] new Flux2ImageNode and GrokImageEditNodeV2 nodes with DynamicCombo and Autogrow (#13814)
b565dc7 Alexander Piskun committed 6 months ago
Remove advanced flag from layers input in EmptyQwenImageLayeredLatentImage node (#13823)
1eeaf23 Daxiong (Lin) committed 6 months ago
Add cloud-runtime experiment node-schema endpoints to spec (#13806)
4e82343 Matt Miller committed 6 months ago
I don't think there was any because nobody complained. (#13807)
66669b2 comfyanonymous committed 6 months ago
[Partner Nodes] additionally use Baidu server to detect the accessibility of internet (#13803)
6504573 Alexander Piskun committed 6 months ago
fix: Fix bug when mask not on same device (CORE-181) (#13801)
c5ecd23 Alexis Rolland committed 6 months ago