Upload a product photo, portrait, illustration, real-estate shot, or reference image. Describe the motion you want — slow zoom, camera orbit, parallax depth, cinematic push-in — and Omni turns the still image into a short video powered by Gemini Omni Flash.
Start with one still image, add a camera direction, and check whether the motion feels usable.
This page is focused on practical still-image animation: keep the source visual recognizable while adding useful motion for real content workflows.
Image-to-video is especially useful when you already have good visuals but need motion for ads, reels, landing pages, or demos.
You can use common web image formats such as JPG, PNG, and WebP. For best results, upload a clear image with a visible subject and good lighting.
The model uses your image as the visual reference and tries to preserve the main subject, framing, and style while adding motion. Very small text or logos may not always remain perfect, so product images should be reviewed before publishing.
Yes. Text-to-video starts from a written prompt only. Image-to-video starts from your uploaded visual, which gives the model a stronger reference for subject, style, composition, and brand look.
Describe the camera movement, subject emphasis, speed, mood, and use case. For example: slow cinematic push-in, keep product centered, soft studio lighting, premium ecommerce ad.
Upload a source image, describe the motion, and create your first AI image-to-video clip with Omni.
Create an image-to-video clip