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

fix typo

Browse Source
This commit is contained in:
LiewFeng 2024-12-30 16:10:41 +08:00
parent bceec3f9ab
commit 43183b210b
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TeaCache4FLUX/README.md
View File

@ -10,7 +10,7 @@
| FLUX.1 [dev] | TeaCache (0.25) | TeaCache (0.4) | TeaCache (0.6) | TeaCache (0.8) |
|:-----------------------:|:----------------------------:|:--------------------:|:---------------------:|:---------------------:|
| ~18 s | ~12 s | ~10 s | ~9s | ~8s |
| ~18 s | ~12 s | ~10 s | ~9 s | ~8s |
## Installation

2
TeaCache4HunyuanVideo/README.md
View File

@ -3,7 +3,7 @@
[TeaCache](https://github.com/LiewFeng/TeaCache) can speedup [HunyuanVideo](https://github.com/Tencent/HunyuanVideo) 2x without much visual quality degradation, in a training-free manner. The following video shows the results generated by TeaCache-HunyuanVideo with various `rel_l1_thresh` values: 0 (original), 0.1 (1.6x speedup), 0.15 (2.1x speedup).
https://github.com/user-attachments/assets/7f75f4e2-3d7e-4762-9afe-c5cc3dcabe44
https://github.com/user-attachments/assets/34b5dab0-5b0f-48a0-968d-88af18b84803
## 📈 Inference Latency Comparisons on a Single A800 GPU