wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-12-20 11:32:58 +08:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity
4,293 Commits 55 Branches 102 Tags 1.2 GiB
e1e50e017c
Commit Graph

4 Commits

Author SHA1 Message Date
comfyanonymous
e1e50e017c Make old scaled fp8 format use the new mixed quant ops system. 
Since model saving is not implemented for the mixed quant system this
breaks model saving for every scaled fp8 model which needs to be fixed
before this gets merged.
 2025-11-30 00:33:01 -05:00
comfyanonymous
3e8155f7a3 More flexible long clip support. 
Add clip g long clip support.

Text encoder refactor.

Support llama models with different vocab sizes.
 2025-04-15 10:32:21 -04:00
comfyanonymous
6c9dbde7de Fix mochi all in one checkpoint t5xxl key names. 2024-11-03 01:40:42 -05:00
comfyanonymous
5cbb01bc2f Basic Genmo Mochi video model support. 
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.

EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
 2024-10-26 06:54:00 -04:00