Open-Sora
Open-source 11B text-to-video and image-to-video model with full training code.
About Open-Sora
Open-Sora is an open-source video generation model from HPC-AI Tech. Version 2.0 (March 2025) is an 11B-parameter model that does both text-to-video and image-to-video, and the team says it works best from a starting image. It renders at 256px or 768px, with demo clips of 5 seconds at 1024x576. The weights, training code and checkpoints are public, and the team reports training it for under $200K. It is heavy to run: at 768px a single GPU peaks near 60 GB of memory, so you need a data-center card or multi-GPU setup.
Key Features
💰 Pricing
Free open weights and code (Apache-2.0). You supply the GPUs.
Frequently Asked Questions
Is Open-Sora free?
What is Open-Sora used for?
What platforms does Open-Sora work on?
What are the best alternatives to Open-Sora?
Reviews
Loading reviews...
Questions & Answers
Questions submitted will appear here soon
Join the community to share knowledge about Open-Sora
📊 Comparison vs Alternatives
| Feature | ||||
|---|---|---|---|---|
| Pricing | Free | Paid | Freemium | Paid |
| Rating | — | — | ⭐ 4.3 | ⭐ 4.7 |
| Free Tier | ✅ | ❌ | ✅ | ❌ |
| Popularity | 50% | 85% | 82% | 82% |
Are you the creator of Open-Sora?
Claim this listing to get a verified badge, edit tool details, and respond to reviews. You’ll sign in and confirm a work email so we can verify ownership.
Claim this listingQuick Stats
Categories
Open-Sora Alternatives
The Weekly AI Tools & Skills Digest
Launching soon: trending agent skills, new tools, and what's actually worth trying. Sign up to get the first issue.
Free forever. Unsubscribe anytime.