rhymes-ai/Allegro

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1135 stars · 68 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Allegro is an open-source text-to-video generation model that produces high-quality 720p videos up to 6 seconds at 15 FPS from text prompts, with a TI2V variant supporting first/last-frame image conditioning. The repository provides inference and fine-tuning code, with models hosted on Hugging Face and support integrated into diffusers.

Use cases

• generate short videos from text prompts
• create video clips from a start and end image
• fine-tune a text-to-video model on custom data
• run video generation locally on GPUs
• integrate video generation into a Python pipeline via diffusers

When to choose

• you need an open-weights text-to-video model with 720p output
• you want to fine-tune or adapt a video generation model
• you need image-conditioned (TI2V) video generation

When to avoid

• you need long videos beyond a few seconds
• you lack high-end multi-GPU hardware for fast inference
• you need a production video API rather than a research model

Facets

library · maturity active

video-processing machine-learning deep-learning llm-inference artificial-intelligence deep-learning image-processing python text-to-video diffusion-model image-to-video video-generation diffusers generative-ai video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rhymes-ai/Allegro")