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

adea2be
Cleaner handling of attention mask in ltxv model code.
comfyanonymous committed 1 year ago
ff83865
Improve some logging messages.
comfyanonymous committed 1 year ago
2307ff6
Properly calculate inner dim for t5 model.
comfyanonymous committed 1 year ago
d0f3752
c515bdf
Make a few more samplers deterministic.
comfyanonymous committed 1 year ago
4209edf
Document get_attr and get_model_object (#6357)
Chenlei Hu committed 1 year ago
d055325
Update frontend to v1.6.18 (#6368)
Chenlei Hu committed 1 year ago
eeab420
Make ancestral samplers more deterministic.
comfyanonymous committed 1 year ago
916d1e1
Update CODEOWNERS (#6338)
Yoland Yan committed 1 year ago
7da85fa
Add update-frontend github action (#6336)
Chenlei Hu committed 1 year ago
b65b83a
c8a3492
Add advanced device option to clip loader nodes.
comfyanonymous committed 1 year ago
5cbf797
Remove old unused function.
comfyanonymous committed 1 year ago
d45ebb6
Update web content to release v1.6.17 (#6337)
Chenlei Hu committed 1 year ago
caa6476
Update web content to release v1.6.16 (#6335)
Chenlei Hu committed 1 year ago
45671cd
Change defaults in nightly package workflow.
comfyanonymous committed 1 year ago
8f29664
Update web content to release v1.6.15 (#6324)
Chenlei Hu committed 1 year ago
0b9839e
add fov and mask for load 3d node (#6308)
Terry Jia committed 1 year ago
953693b
Update web content to release v1.6.14 (#6312)
Chenlei Hu committed 1 year ago
a39ea87
Clear cache as often on AMD as Nvidia.
comfyanonymous committed 1 year ago
9e9c8a1
Fix and enforce all ruff W rules.
comfyanonymous committed 1 year ago
79eea51
Add missing model_options param (#6296)
Jedrzej Kosinski committed 1 year ago
1c99734
Fix custom node type-hinting examples (#6281)
filtered committed 1 year ago
67758f5
fixed "verbose" argument (#6289)
Alexander Piskun committed 1 year ago
02eef72