Skip to content

Allegro

Open text-to-video clips from short prompts

Visit official site

What Allegro is

The model is a text-to-video system from Rhymes AI that turns short prompts into video clips. It generates 6-second clips at 15 frames per second in 720p.

What you can do with it

  • Make short clips from text prompts
  • Choose among FP32, BF16 and FP16 precision
  • Compress video into visual tokens with VideoVAE

Example uses

  • Show sea life from an ocean-world prompt
  • Render a rider in a dusty fantasy scene
  • Spin a smartphone for an ad clip

Pros & cons

✓ What we like

  • Weights and code are open under Apache 2.0
  • BF16 mode uses 9.3 GB of GPU memory

! What to watch out for

  • Local use needs Python and a deep learning framework
  • Model weights must be loaded with a configured runtime

FAQ

How long are the clips?

The material states 6 seconds at 15 frames per second in 720p.

Is the model open?

The material states weights and code are released under Apache 2.0.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review