TeaCache
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
Speed up video generation by using a caching method that learns from previous outputs.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeTimestep Embedding Tells: It's Time to Cache for Video Diffusion Model
TeaCache has 1.4k stars on GitHub. It has been forked 60 times. TeaCache is written mainly in Python. It has been in active development since 2024. TeaCache is available under the Apache-2.0 license. Its main topics are cogvideox, diffusion-models, hunyuan-video, inference-acceleration.
What is TeaCache?
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
Is TeaCache open source?
TeaCache is an open-source project. It is released under the Apache-2.0 license.
Is TeaCache free?
Yes. TeaCache is free and open source — you can use, modify and self-host it.
What license does TeaCache use?
TeaCache is available under the Apache-2.0 license.
What language is TeaCache written in?
TeaCache is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/ali-vilab-teacache.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.