raykindle 3daba169b8 feat: support TeaCache acceleration for 2x faster inference with minimal quality loss

2025-05-05 12:55:40 +08:00

..

__init__.py

feat: init

2025-04-30 17:10:09 +08:00

get_flash_attn.py

feat: init

2025-04-30 17:10:09 +08:00

model_loader_teacache.py

feat: support TeaCache acceleration for 2x faster inference with minimal quality loss

2025-05-05 12:55:40 +08:00

model_loader.py

fix: optimize the loading of modules

2025-05-04 16:25:44 +08:00

sampling.py

feat: init

2025-04-30 17:10:09 +08:00

step1x_edit_utils.py

feat: init

2025-04-30 17:10:09 +08:00

teacache.py

feat: support TeaCache acceleration for 2x faster inference with minimal quality loss

2025-05-05 12:55:40 +08:00