hkunzhe 4839daa1ff support vae gradient checkpointing in reward training

2025-01-22 14:35:25 +08:00

..

__init__.py

Update V5.1 and mix multi text_encoders to one pipeline

2025-01-17 02:18:48 +00:00

attention.py

Update V5.1 and mix multi text_encoders to one pipeline

2025-01-17 02:18:48 +00:00

autoencoder_magvit.py

Update V5.1 and mix multi text_encoders to one pipeline

2025-01-17 02:18:48 +00:00

embeddings.py

Update V5.1 and mix multi text_encoders to one pipeline

2025-01-17 02:18:48 +00:00

motion_module.py

Updated to v3 version, supports image generated videos, with a maximum support of 960x960x144 video generation. (#40)

2024-07-05 20:27:24 +08:00

norm.py

Update V5.1 and mix multi text_encoders to one pipeline

2025-01-17 02:18:48 +00:00

patch.py

Update V5 (#128)

2024-11-08 19:46:50 +08:00

processor.py

Update Comment

2025-01-17 02:27:05 +00:00

resampler.py

update v4

2024-07-18 16:33:56 +08:00

transformer2d.py

support vae gradient checkpointing in reward training

2025-01-22 14:35:25 +08:00

transformer3d.py

support vae gradient checkpointing in reward training

2025-01-22 14:35:25 +08:00