TurboDiffusion: Video Diffusion Model Acceleration Framework Achieves 100-200x Speedup
By
meander_water
5mo ago· 15 min readenCode
100/100
Golden Brown
Bagelometer↗
Crisp on the outside, thoughtful on the inside. A keeper.
Score100TypenewsSentimentpositive
Summary
TurboDiffusion is a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200 times on a single RTX 5090 GPU while maintaining video quality. The framework uses SageAttention, SLA (Sparse-Linear Attention) for attention acceleration, and rCM for timestep distillation. The repository provides the official implementation, though checkpoints and paper are not yet finalized and will be updated later to improve quality.
Key quotes
· 4 pulledTurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by $100 \sim 200\times$ on a single RTX 5090, while maintaining video quality.
TurboDiffusion primarily uses SageAttention, SLA (Sparse-Linear Attention) for attention acceleration, and rCM for timestep distillation.
Paper: TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Note: the checkpoints and paper are not finalized, and will be updated later to improve quality.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models - thu-ml/TurboDiffusion
