mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-19 06:48:12 +00:00
17 lines
1002 B
Markdown
17 lines
1002 B
Markdown
# TeaCache
|
|
|
|
TeaCache ([Timestep Embedding Aware Cache](https://github.com/ali-vilab/TeaCache)) is a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps, thereby accelerating the inference.
|
|
|
|
## Examples
|
|
|
|
We provide examples on FLUX.1-dev. See [./flux_teacache.py](./flux_teacache.py).
|
|
|
|
Steps: 50
|
|
|
|
GPU: A100
|
|
|
|
|TeaCache is disabled|tea_cache_l1_thresh=0.2|tea_cache_l1_thresh=0.4|tea_cache_l1_thresh=0.6|tea_cache_l1_thresh=0.8|
|
|
|-|-|-|-|-|
|
|
|23s|13s|9s|6s|5s|
|
|
|||||
|