xinyun/TeaCache
1
0
Fork 0
mirror of https://git.datalinker.icu/ali-vilab/TeaCache synced 2025-12-09 04:44:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

update consisid readme

Browse Source
This commit is contained in:
SHYuanBest 2024-12-27 15:34:12 +08:00
parent a091d03fb7
commit f70d270409
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TeaCache4ConsisID/README.md
View File

@ -3,7 +3,7 @@
[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. The following video shows the videos generated by TeaCache-ConsisID with various `rel_l1_thresh` values: 0 (1.6x speedup), 0.1 (1.6x speedup), 0.15 (1.6x speedup), and 2.0 (1.6x speedup).
https://github.com/user-attachments/assets/501d71ef-0e71-4ae9-bceb-51cc18fa33d8
## 📈 Inference Latency Comparisons on a Single H100 GPU