Allegro
Open text-to-video diffusion transformer generating 6-second 720p clips.
About
Allegro is an open text-to-video model from Rhymes AI, open-sourced in October 2024, built on a 2.8B diffusion transformer plus a 175M VAE. It generates 88-frame clips — about 6 seconds at 15 fps in 720p — from text prompts, with a TI2V variant that also accepts an image input.
It was one of the first capable open video models and remains useful for research, though inference is heavy (around 20 minutes on a single H100, or minutes on 8xH100) and newer closed models have moved well past its quality bar. Confirm the license on the Hugging Face repo before commercial use.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 6/10
Scored 6/10 (verified tier, metrics-v1). Evidence: Early open video model; quality bar moved on; heavy inference cost.; Open-sourced 2024-10-22 per repo news.. License: Open-sourced; confirm license on the Hugging Face repo before commercial use..
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 6.0/10
- Maintenance · recency, releases, issue load
- 4.0/10
- Openness · license + docs
- 8.0/10
- Manual review · sanity read + red-flag check
- 7.0/10
- · Early open video model; quality bar moved on; heavy inference cost.
- · Open-sourced 2024-10-22 per repo news.