xinyun/TeaCache
1
0
Fork 0
mirror of https://git.datalinker.icu/ali-vilab/TeaCache synced 2026-01-23 12:04:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

Support parameter -- use_ret_stpes

Browse Source
This commit is contained in:
zishen-ucap 2025-03-13 17:06:39 +08:00
parent 2295d6a10c
commit cabe560cf6
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TeaCache4Wan2.1/README.md
View File

@ -91,7 +91,7 @@ https://github.com/user-attachments/assets/d1340197-20c1-4f9e-a780-31f789af0893
| True | ~903 s (0.00) | ~430 s (0.20) | ~340 s (0.30) |
You can refer to the previous video generation instructions and use the `use_ret_steps` parameter to speed up the video generation process, achieving results closer to **Wan2.1**. Simply add the `--use_ret_steps` parameter to the original command and adjust the `--teacache_thresh` parameter to achieve more efficient video generation. The value of the `--teacache_thresh` parameter can be referenced from the table, allowing you to choose the appropriate value based on different models and settings.
You can refer to the previous video generation instructions and use the `use_ret_steps` parameter to speed up the video generation process, achieving results closer to [Wan2.1](https://github.com/Wan-Video/Wan2.1). Simply add the `--use_ret_steps` parameter to the original command and adjust the `--teacache_thresh` parameter to achieve more efficient video generation. The value of the `--teacache_thresh` parameter can be referenced from the table, allowing you to choose the appropriate value based on different models and settings.
### Example Command: