T
TurboDiffusion
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
★3.6kstars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging ai-infra and consistency-model, built with Python, open-source
Who made it?Maintained by thu-ml team, 3.6K⭐ on GitHub, #417 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the thu-ml team identified the need for better ai-infra solutions. TurboDiffusion was created to simplify consistency-model workflows.
What can it do?Key use cases: diffusion-models, distillation, inference-acceleration
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/thu-ml/TurboDiffusion | 官网 https://arxiv.org/pdf/2512.16093
🔗 github.com/thu-ml/TurboDiffusion | 官网 https://arxiv.org/pdf/2512.16093
Topics
ai-infraconsistency-modeldiffusion-modelsdistillationinference-accelerationmlsystemrcmsageattentionsparse-linear-attentionvideo-generation