Open-Sora AI video generator
An open-source video generation project and training/inference framework inspired by Sora-style video models.
Decision Snapshot
Score: 56
Score source: Provisional quality proxy based on official/research evidence and catalogue presence; exact external rank requires live leaderboard/API collection.. Evidence confidence is medium.
Best For
Supported Workflows
Access And Company
Built by Hpcaitech. Public access is listed as Open Weights, Research Only.
Entry Points
Score Breakdown
Weighted evidence dimensions separate model quality from access, web authority, ecosystem, and source confidence.
| Dimension | Score | Weight | Evidence | Confidence |
|---|---|---|---|---|
| Model Quality Proxy | 61 | 24% | Provisional quality proxy based on official/research evidence and catalogue presence; exact external rank requires live leaderboard/API collection. | low |
| Capability Depth | 70 | 16% | Supported workflow tags: t2v, i2v, open_weights, training. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where present. | medium |
| Access And Pricing | 30 | 12% | Access types: open_weights, research_only. Pricing note: Open-source/self-hosted; cost depends on compute. | low |
| Version Maturity | 48 | 12% | 2 version/history entries in the profile; latest public date is 2024-2025. | medium |
| Ecosystem Popularity | 100 | 10% | GitHub snapshot includes 1 repo(s), 29,229 stars, 3,001 forks, 12 open issues, latest pushed 2026-04-09T01:52:40Z. | high |
| Web Authority | 28 | 10% | SEO snapshot found product domain github.com and company domain github.com; sampled sitemap URL count is unknown. No public source link is attached yet. |
medium |
| Company Distribution | 30 | 10% | Company profile is missing; distribution score is provisional. | low |
| Source Confidence | 78 | 6% | Profile source confidence is partial with 1 official URL(s), 1 feature evidence item(s), SEO present, GitHub present. | medium |
What It Is
Primary content is rendered into static HTML.
Open-Sora is an open research and engineering project from the HPC-AI/Colossal-AI ecosystem. It provides code, models, and training/inference workflows for open video generation.
It is not a consumer product, but it is important for open-source evaluation because it provides a public baseline and implementation path for researchers and developers.
Key Features
- Open frameworkThe project provides open code and model resources for video generation research.Source
- Primary source-backed profileOpen-Sora has an official source, repository, paper, or model card attached for verification.Source
- Open/self-hosted access pathOpen-Sora can be evaluated through open code, weights, or model-card resources when license terms allow.Source
Version Progress
- Open-Sora 1.xEarly open Sora-style video generation project releases.
Latest News
Model-specific news entries link directly to the original publisher; article bodies stay off-site.
- Open-Sora GitHub repository External source link for this model. Open original
Limitations And Pricing
Open-source/self-hosted; cost depends on compute.