xinyun/TeaCache
1
0
Fork 0
mirror of https://git.datalinker.icu/ali-vilab/TeaCache synced 2026-05-20 05:57:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixed issues based on PR review

Browse Source
This commit is contained in:
zishen-ucap 2025-01-17 18:48:17 +08:00
parent 3a5b9c092a
commit f7a4d67e35
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
TeaCache4CogVideoX1.5/README.md
View File

@ -27,7 +27,7 @@ pip install --upgrade diffusers[torch] transformers protobuf tokenizers sentence
You can modify the `rel_l1_thresh` to obtain your desired trade-off between latency and visul quality, and change the `ckpts_path`, `prompt`, `image_path` to customize your identity-preserving video. You can modify the `rel_l1_thresh` to obtain your desired trade-off between latency and visul quality, and change the `ckpts_path`, `prompt`, `image_path` to customize your identity-preserving video.
For T2v inference, you can use the following command: For T2V inference, you can use the following command:
```bash ```bash
cd TeaCache4CogVideoX1.5 cd TeaCache4CogVideoX1.5
@ -41,7 +41,7 @@ python3 teacache_sample_video.py \
--output_path ./teacache_results --output_path ./teacache_results
``` ```
For I2v inference, you can use the following command: For I2V inference, you can use the following command:
```bash ```bash
cd TeaCache4CogVideoX1.5 cd TeaCache4CogVideoX1.5