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

..

hydit_clip_tokenizer

Basic hunyuan dit implementation. (#4102)

2024-07-25 18:21:08 -04:00

t5_pile_tokenizer

Better tokenizing code for AuraFlow.

2024-07-12 01:15:25 -04:00

t5_tokenizer

Refactor: Move some code to the comfy/text_encoders folder.

2024-07-15 17:36:24 -04:00

aura_t5.py

Add model_options for text encoder.

2024-08-17 11:17:20 -04:00

bert.py

Lower CLIP memory usage by a bit.

2024-07-31 01:32:35 -04:00

flux.py

Support scaled fp8 t5xxl model.

2024-10-20 22:27:00 -04:00

genmo.py

Basic Genmo Mochi video model support.

2024-10-26 06:54:00 -04:00

hydit_clip.json

Basic hunyuan dit implementation. (#4102)

2024-07-25 18:21:08 -04:00

hydit.py

Add model_options for text encoder.

2024-08-17 11:17:20 -04:00

long_clipl.json

Support loading long clipl model with the CLIP loader node.

2024-08-20 10:46:36 -04:00

long_clipl.py

Long CLIP L support for SDXL, SD3 and Flux.

2024-09-15 07:59:38 -04:00

mt5_config_xl.json

Basic hunyuan dit implementation. (#4102)

2024-07-25 18:21:08 -04:00

sa_t5.py

Add model_options for text encoder.

2024-08-17 11:17:20 -04:00

sd2_clip_config.json

Fix potential issue with non clip text embeddings.

2024-07-30 14:41:13 -04:00

sd2_clip.py

Properly set if clip text pooled projection instead of using hack.

2024-08-20 10:46:36 -04:00

sd3_clip.py

Support scaled fp8 t5xxl model.

2024-10-20 22:27:00 -04:00

spiece_tokenizer.py

Basic hunyuan dit implementation. (#4102)

2024-07-25 18:21:08 -04:00

t5_config_base.json

Refactor: Move some code to the comfy/text_encoders folder.

2024-07-15 17:36:24 -04:00

t5_config_xxl.json

Refactor: Move some code to the comfy/text_encoders folder.

2024-07-15 17:36:24 -04:00

t5_pile_config_xl.json

AuraFlow model implementation.

2024-07-11 16:52:26 -04:00

t5.py

Fix to get fp8 working on T5 base.

2024-07-31 02:00:19 -04:00