Captured photo
damo-text-to-video
30

About

A text-to-video model that creates videos through multiple generation stages, processing text descriptions into visual sequences. Outputs short video clips suitable for concept visualization and creative experimentation. Designed for generating diverse video content from natural language prompts.

Percs

High quality
High-fidelity output suitable for professional use.
9:16 vertical
Native vertical output for social platforms.

Settings

Frames-  Number of frames for the output video
Inference Steps
FPS-  Frames per second
Seed