Google's creative ladder — images in chat, video clips, and whole scenes built in Flow.
The full script, word for word — 202 words, about 1 minutes to read. Current as at August 2026. AI tools change quickly; if something looks different when you try it, check the product's own help pages.
Gemini doesn't just write — it makes. Images, video clips, even whole scenes. Three tools, one ladder, and you climb exactly as far as your idea needs.
First rung: images, right in the chat. Describe what you want, or upload a picture and describe the change — swap the background, fix the lighting, restyle the whole thing. Seconds, not complex software.
Second rung: video. Give Gemini a line of text, an image, or a clip, and it creates a short video — then you edit it the same way you made it, by describing the change. Availability varies by region and plan, but this is where casual video creation now lives.
Third rung: when a short clip isn't enough, there's Flow — Google's creative studio. This one lives outside the Gemini app — at labs.google — and it's built for real projects: characters kept consistent from shot to shot, scenes built into sequences, sound generated with the footage, dialogue and all. A storyboard-to-screen pipeline, driven by plain language.
Start on the first rung today: take a real image from your work and ask Gemini to change one thing about it. Once you've felt that, you'll know when a project deserves the ladder.