Gemini Omni is Google DeepMind's video generation model. It makes video from a text prompt, animates a still image, fills in the motion between a first and a last frame, and builds a scene from up to six reference images, in 16:9 or 9:16 at resolutions from 360p to 4K.
Made by Google DeepMind. All credit for the model goes to Google. Civitai runs it through the Gemini API so you can generate on-site with no setup; there is nothing to download on this page.
Versions
- 1.2 Flash (released November 2026): choose any length from 3 to 15 seconds (up to 10 seconds for first/last-frame videos). Stronger consistency with your reference images, at a lower price per second than 1.1.
- 1.1 Flash: the earlier release, making clips of up to 10 seconds.
On Civitai
- Text to video, image to video, first/last frame and reference to video (3 to 6 images).
- Cost is per second of video and rises with resolution.
Links
- Announcement: Introducing Gemini Omni 1.2 Flash
- Model card: Gemini Omni Flash on Google DeepMind
- Terms: Gemini API Additional Terms of Service