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

Support new hunyuan video i2v model.
comfyanonymous committed 1 year ago
7395b0c
Fix stable cascade VAE on some lowvram machines.
comfyanonymous committed 1 year ago
0952569
Print the frontend version in the log.
comfyanonymous committed 1 year ago
c3d9cc4
Update frontend to 1.11.8 (#7119)
Chenlei Hu committed 1 year ago
84cc9cb
Add back taesd to nightly package.
comfyanonymous committed 1 year ago
ebbb920
Reduce size of nightly package.
comfyanonymous committed 1 year ago
d60fe0a
Update nightly instructions in readme.
comfyanonymous committed 1 year ago
5dbd250
4ab1875
Set WAN default compute dtype to fp16.
comfyanonymous committed 1 year ago
11b1f27
70e15fd
Typo in node_typing.py (#7092)
JettHu committed 1 year ago
e62d72e
ComfyUI version v0.3.24
comfyanonymous committed 1 year ago
a131258
dfa36e6
ComfyUI version v0.3.23
comfyanonymous committed 1 year ago
0124be4
Support HunyuanVideo image to video model.
comfyanonymous committed 1 year ago
29a70ca
Support llava clip vision model.
comfyanonymous committed 1 year ago
0bef826
Make applying embeddings more efficient.
comfyanonymous committed 1 year ago
85ef295
Add type hint for FileLocator (#6968)
Chenlei Hu committed 1 year ago
5d84607
c1909f3
Bump ComfyUI version to v0.3.22
comfyanonymous committed 1 year ago
8895199
Revert "Partially revert last commit."
comfyanonymous committed 1 year ago
76739c2
Partially revert last commit.
comfyanonymous committed 1 year ago
a80bc82
fix: ltxv crop guides works with 0 keyframes (#7085)
Andrew Kvochko committed 1 year ago
872780d
Bump ComfyUI version to v0.3.21
comfyanonymous committed 1 year ago
6d45ffb
Remove unused variable.
comfyanonymous committed 1 year ago
77633ba