ali-vilab/TeaCache
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
TeaCache significantly speeds up the process of generating creative content like videos, images, and audio using AI diffusion models. By intelligently caching information during the generation steps, it helps content creators, animators, and designers get their final outputs faster, reducing the wait time for high-quality generated media.
1,290 stars. No commits in the last 6 months.
Use this if you are a content creator, animator, or designer who frequently uses AI diffusion models to generate videos, images, or audio and want to significantly reduce the time it takes to get your final results.
Not ideal if your primary work does not involve generating visual or audio content with diffusion models, or if you are not experiencing long generation times.
Stars
1,290
Forks
52
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ali-vilab/TeaCache"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlorianFuerrutter/genQC
Generative Quantum Circuits
horseee/DeepCache
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
Gen-Verse/MMaDA
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion,...
kuleshov-group/mdlm
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Shark-NLP/DiffuSeq
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models