Stable Video Diffusion AI video generator
Stability AI's early open image-to-video foundation model, now mainly useful as a historical and open baseline.
Decision Snapshot
Score: 67
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 Stability AI. Public access is listed as Open Weights, Research Only, Aggregator.
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 | 64 | 24% | Provisional quality proxy based on official/research evidence and catalogue presence; exact external rank requires live leaderboard/API collection. | medium |
| Capability Depth | 53 | 16% | Supported workflow tags: i2v, open_weights. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where present. | medium |
| Access And Pricing | 48 | 12% | Access types: open_weights, research_only, aggregator. Pricing note: Open checkpoint; self-hosting or hosted inference cost depends on runtime and provider. | low |
| Version Maturity | 63 | 12% | 2 version/history entries in the profile; latest public date is 2023-11. | medium |
| Ecosystem Popularity | 100 | 10% | GitHub snapshot includes 1 repo(s), 27,233 stars, 3,102 forks, 340 open issues, latest pushed 2025-12-16T08:36:18Z. | high |
| Web Authority | 92 | 10% | SEO snapshot found product domain stability.ai and company domain stability.ai; sampled sitemap URL count is 238. | medium |
| Company Distribution | 46 | 10% | Stability AI distribution profile: Stable Video Diffusion is older than current frontier models, but it remains an important historical and open/self-hosted baseline for understanding AI video generation.. | medium |
| Source Confidence | 98 | 6% | Profile source confidence is confirmed with 2 official URL(s), 2 feature evidence item(s), SEO present, GitHub present. | high |
What It Is
Primary content is rendered into static HTML.
Stable Video Diffusion was one of the first widely distributed open video foundation model releases. It is not a current frontier consumer model, but it remains important for historical comparison and open-model baselines.
The family focuses on image-to-video generation, with SVD and SVD-XT checkpoints used heavily by community tools after release. For a consumer-facing site, it belongs in a research/open baseline category rather than the main top-product recommendation set.
Key Features
- Open video model releaseStability AI described SVD as an open generative AI video model release.Source
- SVD-XT checkpointHugging Face hosts the SVD-XT image-to-video checkpoint.Source
- Primary source-backed profileStable Video Diffusion has an official source, repository, paper, or model card attached for verification.Source
Version Progress
- Stable Video DiffusionPublic open AI video model release from Stability AI.
- SVD-XTExtended image-to-video checkpoint used by the open-source community.
Latest News
Model-specific news entries link directly to the original publisher; article bodies stay off-site.
- stable-video-diffusion-img2vid-xt External source link for this model. Open original
- Stable Video Diffusion: Stability AI's first open video model External source link for this model. Open original
Limitations And Pricing
Open checkpoint; self-hosting or hosted inference cost depends on runtime and provider.