Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

Image & videoPythonApache-2.0

hpcaitech/Open-Sora

Open-Sora provides training and inference code for open video generation, including model weights, data pipelines and configuration for different GPU budgets. It is a research-oriented project: expect rough edges, significant hardware requirements and fast-moving dependencies.

29.0k stars2.9k forks120 contributors240 open issuesUpdated

What it does

  • Provides open video generation models and inference code.
  • Documents training data processing and distributed training.
  • Supports text-to-video and image-to-video experiments.

Key features

  • Open weights and training recipes.
  • Configurable model sizes for different GPUs.
  • Colab and Docker examples.
  • Active research community.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Python
git clone https://github.com/hpcaitech/Open-Sora
cd Open-Sora && pip install -e .

Alternatives to consider

Open-Sora is a strong default for image & video, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

ComfyUI video nodesRunwayVeo

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

Open-Sora FAQ

Adoption questions we hear most often about this project.

Related repositories

Image & video · Python

A node-based interface for diffusion models with fine-grained control over image and video pipelines.

88.0k9.8kGPL-3.0

Image & video · Python

Automated YouTube Shorts, TikTok and video generator using Claude 3.5 Sonnet, EdgeTTS, Pexels footage and dynamic subtitles.

16.8k2.6kMIT