Give your photo a next moment.

Start with a still image and describe what should happen next. Studio Rabbit’s video mode uses your photo as the starting point for an AI-generated clip.

Describe motion, not just a mood

A useful prompt explains who or what moves, what that movement looks like, and how the camera behaves. Keep the action consistent with the scene in your source image.

The person slowly turns toward the camera and gives a small smile. The camera gently moves closer. Keep the background still, the lighting consistent and the movement natural.

Create a video from an image

1. Choose Video mode and upload an image you have permission to use.
2. Select a motion preset or write a detailed custom prompt.
3. Check the current video credit cost and generate.
4. Watch the progress indicator, then play and download the clip.

Video generation usually takes about 4–5 minutes plus queue time. Duration varies with the selected model, settings and server load.

Choose a good starting image

Use a sharp image with one clearly visible adult subject. If there are several people, describe them by position and say what each person should do. Avoid vague instructions such as “dance” when several subjects could interpret the action differently.

Can I control the camera?

You can request a slow push-in, a small pan or a fixed camera. These are instructions to the model, not guaranteed camera controls. Start with one movement.

Will the subject look exactly the same?

Appearance can drift as frames are generated. Modest movement and clear instructions help communicate your intent, but inspect the full clip before sharing.

Explore the image-to-video prompt examples or edit your starting photo first.