Skip to content

FRESCO

Translate videos with spatial temporal consistency

Visit official site

What FRESCO is

The framework is described as a zero shot video translation method built on spatial temporal correspondence.

What you can do with it

  • Apply intra frame and inter frame constraints
  • Translate video without training or fine tuning
  • Combine with existing models for custom results

Application scenarios

  • Run video style transfer without pretraining
  • Preview video effects for film work
  • Create visual art with consistent video effects

Pros & cons

✓ What we like

  • Visual coherence of translated video is described
  • Customized translation through existing models is listed

! What to watch out for

  • The method relies on spatial temporal correspondence
  • Named compatible models are ControlNet and LoRA

FAQ

Is training required?

The material states zero shot learning without training or fine tuning.

Which models are named?

ControlNet and LoRA are listed as compatible.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review