Gemini Omni brings Google DeepMind's multimodal video generation into PhotoGPT. Create 720p videos from prompts, first frames, and up to 10 visual references in landscape or portrait.
Create anything
Start with a prompt, first frame, or visual references and guide Gemini Omni toward a cohesive video. It is built for multimodal creation, beginning with video.
Edit through
Build a scene step by step with plain-language edits. Each request can refine the previous result while keeping the scene coherent.
Reference anything
Combine your prompt with a first frame or up to 10 reference images to control characters, products, environments, and visual style.
Grounded motion
Gemini Omni is designed to bring together reasoning, physics, and real-world context so generated scenes feel more meaningful and believable.
Guide video generation with a prompt, first frame, and up to 10 reference images, then create portrait or landscape clips for social, ads, stories, and visual exploration.
Choose the plan that works for you
For getting started
per month · billed $99.99 every 6 months
per month · ≈ 500 AI images
Credits work across AI images, AI videos, model training, editing, upscaling, and PhotoGPT Flow.
For regular creators
per month · billed $149.99 every 6 months
per month · ≈ 900 AI images
Credits work across AI images, AI videos, model training, editing, upscaling, and PhotoGPT Flow.
For power users
per month · billed $199.99 every 6 months
per month · ≈ 1600 AI images
Credits work across AI images, AI videos, model training, editing, upscaling, and PhotoGPT Flow.
Join our Discord community of 1000s of active users, get insights on latest prompt ideas and explore community generations