Step Video T2V is StepFun's video generation model. A text-to-video generation model from StepFun that synthesizes high-quality video clips from natural language descriptions.
step-video-t2v |
| Video Generation |
| Active |
| Text |
| Video |
| Benchmarks | |
|---|---|
| Elo Rating | 923#272 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio·
Video✓
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·