thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
TurboDiffusion dramatically accelerates the process of generating videos from text descriptions or images. You provide an English text prompt or an image, and it quickly outputs a high-quality video. This tool is designed for content creators, marketers, or anyone needing to rapidly produce visual media from creative ideas.
3,410 stars. Actively maintained with 2 commits in the last 30 days. Available on PyPI.
Use this if you need to generate high-quality videos from text or images extremely fast, especially for rapid prototyping or content creation.
Not ideal if your video generation requires non-English prompts or highly customized, non-standard resolutions beyond 480p/720p.
Stars
3,410
Forks
242
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 06, 2026
Commits (30d)
2
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/thu-ml/TurboDiffusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
Fantasy-AMAP/fantasy-talking
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis