comfyanonymous 2ff3104f70 WIP support for Nvidia Cosmos 7B and 14B text to world (video) models.

2025-01-10 09:14:16 -05:00

..

hydit_clip_tokenizer

…

llama_tokenizer

…

t5_pile_tokenizer

…

t5_tokenizer

…

aura_t5.py

…

bert.py

…

cosmos.py

WIP support for Nvidia Cosmos 7B and 14B text to world (video) models.

2025-01-10 09:14:16 -05:00

flux.py

…

genmo.py

…

hunyuan_video.py

Properly tokenize the template for hunyuan video.

2024-12-17 16:22:02 -05:00

hydit_clip.json

…

hydit.py

…

llama.py

Pick attention implementation based on device in llama code.

2024-12-18 01:30:20 -05:00

long_clipl.json

…

long_clipl.py

…

lt.py

…

mt5_config_xl.json

…

pixart_t5.py

Add PixArt model support (#6055)

2024-12-20 15:25:00 -05:00

sa_t5.py

…

sd2_clip_config.json

…

sd2_clip.py

…

sd3_clip.py

…

spiece_tokenizer.py

…

t5_config_base.json

…

t5_config_xxl.json

…

t5_old_config_xxl.json

WIP support for Nvidia Cosmos 7B and 14B text to world (video) models.

2025-01-10 09:14:16 -05:00

t5_pile_config_xl.json

…

t5.py

Properly calculate inner dim for t5 model.

2025-01-07 17:33:03 -05:00