3 people 2eb809a0c8 Add lora cache mode in comfyui && Use cuda in merge_lora func for speeding up. (#172) ...

* fix lora precision problem during multiple merge unmerge, keep the original weights on cpu

* add comments

* update

* Update Lora cache

---------

Co-authored-by: mengli.cml <mengli.cml@alibaba-inc.com>
Co-authored-by: bubbliiiing <3323290568@qq.com>

2024-12-24 10:02:57 +08:00

..

__init__.py

Create Code

2024-04-12 17:42:52 +08:00

diffusion_utils.py

Create Code

2024-04-12 17:42:52 +08:00

discrete_sampler.py

Update V5 (#128)

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

fp8_optimization.py

Update V5 (#128)

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

gaussian_diffusion.py

Create Code

2024-04-12 17:42:52 +08:00

lora_utils.py

Add lora cache mode in comfyui && Use cuda in merge_lora func for speeding up. (#172)

2024-12-24 10:02:57 +08:00

respace.py

Create Code

2024-04-12 17:42:52 +08:00

utils.py

Update V5 (#128)

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