StepFunStep-Video
Step-Video T2V Turbo
Step-Video T2V Turbo is the inference-step-distilled version of Step-Video T2V. It is a separate trained release, not only a faster API tier.
Use the Turbo sampling settings
The Turbo checkpoint has its own recommended inference parameters. The original model's 50-step example is not the Turbo recommendation.StepFun stepvideo-t2v-turbo model card
Compare quality at the intended speed
Practical guidance. Fewer steps are useful only if the clip keeps the details your task needs. Check motion, text and small objects with the recommended settings before increasing speed further.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | stepvideo-t2v-turboStep-Video-T2V-Turbo |
| License | MIT.StepFun stepvideo-t2v-turbo model card |
| Sampling guidance | The official table recommends 10 to 15 inference steps, guidance scale 5.0 and time shift 17.0 for 204 frames.StepFun stepvideo-t2v-turbo model card |
Related models
- Step-Video TI2V
StepFun · Step-Video
A video-generation model that animates a starting image from a text instruction.
Launch date Downloadable - Step-Video T2V
StepFun · Step-Video
Step-Video T2V is a 30B text-to-video model that can generate up to 204 frames.
Launch date Downloadable