xinyun/TeaCache
1
0
Fork 0
mirror of https://git.datalinker.icu/ali-vilab/TeaCache synced 2025-12-08 20:34:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #12 from SHYuanBest/main

Browse Source 
add a video for TeaCache4ConsisID
This commit is contained in:
Feng Liu 2024-12-27 15:55:44 +08:00 committed by GitHub
commit 2b8b201b3c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
TeaCache4ConsisID/README.md
View File

@ -1,7 +1,9 @@
<!-- ## **TeaCache4ConsisID** -->
# TeaCache4ConsisID
[TeaCache](https://github.com/LiewFeng/TeaCache) can speedup [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) 2x without much visual quality degradation, in a training-free manner.
[TeaCache](https://github.com/LiewFeng/TeaCache) can speedup [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) 2.1x without much visual quality degradation, in a training-free manner. The following video shows the results generated by TeaCache-ConsisID with various `rel_l1_thresh` values: 0 (original), 0.1 (1.6x speedup), 0.15 (2.1x speedup), and 0.2 (2.7x speedup).
https://github.com/user-attachments/assets/501d71ef-0e71-4ae9-bceb-51cc18fa33d8
## 📈 Inference Latency Comparisons on a Single H100 GPU
@ -29,7 +31,7 @@ python3 teacache_sample_video.py \
--output_path ./teacache_results
```
To generate a video with 8 GPUs, you can use the following [here](https://github.com/PKU-YuanGroup/ConsisID/tree/main/tools).
To generate a video with 8 GPUs, you can following [here](https://github.com/PKU-YuanGroup/ConsisID/tree/main/tools).
## Resources