Skip to content

AuraFlow

An open flow-based text-to-image model

Visit official site

What AuraFlow is

The model is described as a fully open, flow-based text-to-image generation model at version v0.1.

What you can do with it

  • Generate high-resolution images from text
  • Set size and inference step parameters
  • Control randomness with torch.Generator

Key details

  • CUDA hardware is named for running the model
  • GenEval results are cited in the material
  • Community feedback is folded into ongoing work

Pros & cons

✓ What we like

  • The model is fully open
  • Randomness can be controlled with a generator

! What to watch out for

  • The model is in beta
  • CUDA hardware is named for running it

FAQ

What stage is it in?

The material calls v0.1 a beta release.

Who is credited?

Two engineers, cloneofsimo and isidentical, plus earlier researchers.

Last reviewed: 2026-11-15

More AI image generation tools

View all →

How we review