Image to video models

An image to video model starts from a still picture and sets it in motion: a product turns, a portrait smiles, a landscape fills with weather. The picture fixes the first frame, so the look you approved stays in the clip. 91 models do this job in the catalog right now. Each model's page shows its form and a price guide in US dollars.

Models

Page 1 of 4

Questions

How is an image to video model priced?
Video models usually charge per second of output or per video, and resolution, duration and audio can change the rate. Each model page shows its price guide in US dollars, and the studio shows the exact price for your settings before you generate. If a generation fails, the reserved amount goes back to your balance.
What do I need to start?
One image, usually the first frame, and a short prompt about the movement and the camera. Some models also take a last frame, reference images or a duration; the model page lists every field. Uploading starts after you sign in.
Which model should I start with?
Use the same image and prompt on two or three models whose examples look closest to your idea, then compare the motion and the price. When you only have words and no picture yet, start with a text to video or text to image model.
Can I call these models from the API?
Yes. Every model on this page has an API tab with its input fields, and the studio and the API share one account balance.

Other types

Found your direction?

Open the studio