doctorpangloss
b309e0424e
Fix transformers 5 compatibility
2025-12-12 12:11:25 -08:00
doctorpangloss
a00c902067
Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.3.76-snapshot
2025-12-09 08:58:52 -08:00
comfyanonymous
43071e3de3
Make old scaled fp8 format use the new mixed quant ops system. ( #11000 )
2025-12-05 14:35:42 -05:00
doctorpangloss
d79d7a7e08
fix imports and other basic problems
2025-06-17 11:19:48 -07:00
doctorpangloss
5823497d55
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-04-21 13:14:36 -07:00
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
doctorpangloss
7655be873c
Updates to support Hunyuan Video
2024-12-25 22:39:12 -08:00
doctorpangloss
8ba412897e
Mochi and SageAttention improvements
2024-11-18 15:40:15 -08:00
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
