Video
GA
Open weights
Step-Video 2
Open-weight text-to-video
Release2026-04
Context—
Max output—
Parameters30B
Local / VRAM48–80 GB
LicenseOpen weights
Overview
Step-Video 2 is a model in the Video category from StepFun. It was released in 2026-04. The vendor is based in China. Best for: Open-weight text-to-video.
Strengths
- Apache-2.0
- Runs locally
Limits
- No audio
- Short clips
Specifications
| Vendor | StepFun |
|---|---|
| Category | Video |
| Release | 2026-04 |
| Status | GA |
| License | Open weights |
| License name | Apache-2.0 |
| Commercial use | Allowed |
| Parameters | 30B |
| Architecture | DiT |
| Input modalities | Text, Image |
| Output modalities | Video |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Resolution | 720p-1080p |
| Duration | 5-10s |
| Frame rate | 24 fps |
| Audio generation | No |
| Local deployment | Yes |
| VRAM | 48–80 GB |
| System RAM | 64–128 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | Medium |
| Vendor country | China |
| Vendor type | Open lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 48–80 GB. Approximate system RAM: 64–128 GB. API access is available.