Scenario
← All Models
video

Flash VSR Upscale Video

Flash VSR Upscale Video by Tsinghua/Shanghai AI Lab provides real-time diffusion-based upscaling with a one-step streaming framework.

  • Academia
  • V2V
  • Video Upscale
  • video-upscale
Use in Scenario ↗

Flash VSR is an ultra-fast one-step diffusion model designed for real-time, high-fidelity video super-resolution. By utilizing locality-constrained sparse attention and a lightweight decoder, it delivers a 12x speed boost over prior models, upscaling footage to 4K at 17 FPS while ensuring sharp textures and flawless temporal stability

More models from Academia