Google has released Nano Banana Pro, a new image generation and editing model built into the Gemini app. It focuses on clarity, control, and production-ready results, making it a strong upgrade for designers working with visuals, mockups, and layouts.

The biggest improvement is its ability to generate sharp, legible text inside images. Posters, diagrams, UI mockups, and product callouts now render with cleaner typography. You can describe the font style you want or even simulate handwriting, and the model will place it clearly within the final frame.

Nano Banana Pro also introduces stronger studio-level control. Designers can adjust angles, shot types, depth of field, and lighting. Switching a scene from day to night, changing color grades, or exploring close-ups and wide shots is straightforward. The model supports clean upscaling to 1k, 2k, or 4k, and you can toggle aspect ratios to fit any platform.

Another key update is real-world knowledge integration. It handles accurate details inside complex scenes, detailed infographics, historical references, and technical concepts. You can annotate images, turn scribbles into diagrams, or quickly mock up product ideas with more believable context.

Text translation inside images is also improved. You can localize posters, packaging concepts, and product interfaces for different markets. This makes it easier to preview how a design works across regions without manually recreating assets.

Finally, Nano Banana Pro supports subject consistency, maintaining resemblance for up to five characters and fourteen objects in one workflow. It also generates multiple variations from a single prompt, letting you explore options faster.

Nano Banana Pro begins rolling out globally inside the Gemini app today. Users with Google AI Plus, Pro, or Ultra plans receive higher usage limits, while free users can try it with a smaller quota.

Try on Gemini: gemini.google.com