Hey Product Hunt! 👋 I built Gemini Omni Video because creating AI videos still feels too fragmented. You often need to jump between prompts, image references, model settings, downloads, and retries before getting something usable. Gemini Omni Video is a simple AI video generator that helps creators turn text prompts and images into videos faster. The goal is to make AI video creation feel more like using a creative tool, not managing a technical workflow. With this launch, you can: - Generate videos from text prompts - Create videos from image references - Explore example prompts and outputs - Make short videos for social posts, product demos, and creative ideas I’d love to hear your feedback, especially on the generation flow, output quality, and what features you would like to see next.

Gemini Omni Video

Create AI videos from text and images in seconds

Create AI videos from text and images in seconds