Video
Legacy
Open weights
Stable Video Diffusion
Short image-to-video experiments
Release2023-11
Context1K
Max output—
Parameters1.5B
Local / VRAM12–24 GB
LicenseOpen weights
Overview
Stable Video Diffusion is a model in the Video category from Stability AI. It was released in 2023-11. The vendor is based in UK. Best for: Short image-to-video experiments.
Strengths
- Small
- Local
- Mature
Limits
- Very short
- No text-to-video
- Dated
Specifications
| Vendor | Stability AI |
|---|---|
| Category | Video |
| Release | 2023-11 |
| Status | Legacy |
| License | Open weights |
| License name | Stability Community License |
| Commercial use | Conditional |
| Parameters | 1.5B |
| Architecture | latent video diffusion |
| Context window | 1K |
| Input modalities | Image |
| Output modalities | Video |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 clip |
| Resolution | 576x1024 |
| Duration | 2-4s |
| Frame rate | 25 fps |
| Audio generation | No |
| Local deployment | Yes |
| VRAM | 12–24 GB |
| System RAM | 16–32 GB |
| API access | Yes |
| Pricing | Free weights (conditional) |
| Confidence | High |
| Vendor country | UK |
| Vendor type | Open lab |
Pricing & hardware
Free weights (conditional)
This model can be self-hosted or run locally. Approximate GPU memory: 12–24 GB. Approximate system RAM: 16–32 GB. API access is available.