0
Video generationApache-2.0Python

Open-Sora

Fully open-source video generation: weights, training code and data pipeline.

GitHub
Stars
29.9K
Forks
3.1K
Open issues
14
Last commit
2026-04-09

Live from the GitHub API · updated 2026-10-15

What is Open-Sora?

Open-Sora by HPC-AI Tech publishes not only model weights but the full training and data processing pipeline, aiming to democratize Sora-style video generation research.

Key features

  • Open weights and complete training code
  • Text-to-video and image-to-video
  • Data processing tools

System requirements

Platforms
Linux
GPU
NVIDIA
VRAM
High-end GPU; multi-GPU for higher resolutions

How to install Open-Sora

Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.

Linux

  1. 1
    Clone and install.
    git clone https://github.com/hpcaitech/Open-Sora
cd Open-Sora
pip install -v .
  2. 2
    Download weights and run inference with the commands in the README.

Strengths

  • Everything is open, including training
  • Good for research

Limitations

  • Heavy hardware requirements
  • Quality trails Wan and HunyuanVideo

Open-Sora alternatives compared

SoftwareStarsLicensePlatformsVRAM
Open-Sora

Fully open-source video generation: weights, training code and data pipeline.

29.9KApache-2.0High-end GPU; multi-GPU for higher resolutions
Wan 2.2

Alibaba’s open-weight video generation models (text, image and speech to video).

17.9KApache-2.024 GB for TI2V-5B at 720p; 80 GB-class GPUs (or offloading) for A14B models
HunyuanVideo

Tencent’s 13B-parameter open video foundation model.

12.6KTencent Hunyuan Community License45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations
CogVideoX

Open text-to-video and image-to-video models from Zhipu AI / Tsinghua.

13.1KApache-2.0~12–24 GB depending on model and optimizations (see the README table)
LTX-Video

Fast, real-time-capable open video generation from Lightricks.

11.1KApache-2.012 GB+ for smaller variants; more for 13B models
FramePack

Long image-to-video generation on laptop GPUs with as little as 6 GB VRAM.

17.3KApache-2.06 GB minimum

Related models

SoraOpenAI’s video model with synchronized audio and a social app.WanAlibaba’s open-weight video model you can run yourself.

FAQ

Is Open-Sora free?

Yes — Open-Sora is open-source software released under the Apache-2.0 license. Check the license (and any model weight licenses) before commercial use.

Does Open-Sora run on Windows, Mac and Linux?

Open-Sora supports: Linux.

What hardware do I need for Open-Sora?

NVIDIA. VRAM: High-end GPU; multi-GPU for higher resolutions

How do I install Open-Sora?

1. Clone and install. 2. Download weights and run inference with the commands in the README.

What are the best Open-Sora alternatives?

Popular alternatives include Wan 2.2, HunyuanVideo, CogVideoX, LTX-Video. See the comparison table on this page.

Can I use Open-Sora online without installing it?

If you don’t have a large GPU, AiLoft runs Veo 3.1 and Kling 2.5 in the cloud — generate and compare clips in the browser.

No 24 GB GPU? Generate AI video online

Run Veo 3.1 and Kling 2.5 in the cloud and compare clips side by side — pay per clip.

AI Video Generator
Open-source AI video generators