Hasty Briefsbeta

Bilingual

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

4 months ago
  • #diffusion-models
  • #machine-learning
  • #video-generation
  • TurboDiffusion accelerates video diffusion models by 100-200 times using SageAttention, SLA, and rCM.
  • Supports models like TurboWan2.1 and TurboWan2.2 with resolutions up to 720p.
  • Install via pip or compile from source; requires Python 3.9+ and torch 2.7.0+.
  • Different checkpoints available for GPUs with varying memory capacities (quantized for RTX 5090, unquantized for H100).
  • Includes detailed inference scripts for T2V and I2V models with customizable parameters.
  • Training code provided with support for FSDP2, Ulysses CP, and SAC.
  • Community contributions welcomed, with ongoing improvements and integrations planned.
  • Citations provided for related research papers and software.