Video
Gemini Omni 1.2 Flash
Use it ↗Google Gemini Omni 1.2 Flash: text or image to video with native audio and dialogue, 3 to 15 s, optional last frame and up to 10 reference images, 360p to 4K.
Google Gemini Omni 1.2 Flash generates video with native audio (dialogue, sound effects, ambience) from a prompt, a first-frame image, or both. Duration 3 to 15 s (max 10 s with a last frame). Optional lastFrameImage to interpolate between two images, and up to 10 referenceImages to keep subjects consistent; frames count toward the 10. Aspect ratio 16:9 or 9:16. Resolution 360p (draft), 720p, 1080p or 4K (1080p and 4K are upscaled). Renders short on-screen labels; timecoded prompts like [0-5s] stage beats. For reference-only scenes use R2V.