Shypd.aiThe largest open index of AI toolsTeaCache is an AI Frameworks & Infra tool that accelerates video diffusion models. It uses a training-free caching approach to estimate and leverage fluctuating differences among model outputs across timesteps, improving inference efficiency.
Trending
Also listed in
About
TeaCache, or Timestep Embedding Aware Cache, is an innovative, training-free caching approach designed to significantly accelerate the inference process for various diffusion models. It achieves this by estimating and leveraging the fluctuating differences among model outputs across timesteps. While primarily focused on Video Diffusion Models, TeaCache also demonstrates effectiveness with Image Diffusion Models and Audio Diffusion Models. The project is open-source and available on GitHub, offering support for a wide range of models including Open-Sora, Latte, CogVideoX, and many others. It has been recognized as a highlight in CVPR 2025, underscoring its significance in the field. TeaCache also encourages community contributions and provides instructions for supporting new models, making it a versatile and evolving tool for researchers and developers.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
