hpcaitech/Open-Sora

Health v2 · maintenance only

Adoption not part of the score

29314 stars · 3014 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Open-Sora is an open-source initiative for efficiently producing high-quality videos from text prompts using deep learning models. It provides the model, training tools, and full pipeline details to democratize access to advanced video generation techniques.

Use cases

• generate videos from text prompts
• train a custom text-to-video diffusion model
• produce short AI-generated video clips for content creation
• experiment with video generation model architectures
• fine-tune a video generation model on my own dataset

When to choose

• you need an open-source, self-hosted text-to-video pipeline you can inspect and modify
• you want to train or fine-tune video generation models on your own GPUs
• you are researching video diffusion models and want reproducible training details

When to avoid

• you need production-grade, polished video generation without managing GPU infrastructure
• you lack access to significant GPU compute for inference or training
• you only need simple video editing rather than generative video synthesis

Facets

library · maturity active

video-processing deep-learning machine-learning llm-training deep-learning artificial-intelligence media python text-to-video video-generation diffusion-models open-source generative-ai video gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hpcaitech/Open-Sora")