H-EmbodVis/EasyCache
Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
If you generate videos from text descriptions or images, this project dramatically speeds up the process. It takes your existing video generation prompts and models, and outputs the same high-quality videos in significantly less time. This is ideal for video creators, marketers, or researchers who regularly produce content using AI video tools and need faster results.
290 stars. No commits in the last 6 months.
Use this if you are generating videos with AI models like HunyuanVideo or Wan2.1 and want to significantly reduce the time it takes to produce them without sacrificing quality.
Not ideal if you are not currently using large video generation AI models or if your primary concern is generating highly unique, complex videos rather than speed.
Stars
290
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/H-EmbodVis/EasyCache"
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