← All posts

Nano Banana 2.1: from a quick direction to a detailed image

Explore Google’s image model for readable lettering, edits from multiple references, optional search grounding and output up to 4K.

Marmalade toast, a butter knife, and a few crumbs sit on a cobalt plate.

A useful image often starts as a question. Would this product work in a quieter setting? Can the headline become part of the composition? What happens if the same idea is framed for a poster instead of a feed? Nano Banana 2.1 gives those questions a place in the SUPERMODELS image creation tool.

Bring the ingredients into one scene

Google’s model creates images from text and edits supplied pictures. It accepts up to 14 references, so a brief can include a product, a setting and a visual direction together. The documentation highlights improved lettering and sharper output compared with Nano Banana 2. For a campaign concept, that makes it an option to explore when both the picture and the words matter.

Give each reference a job. A photograph of a bottle might define its shape and label; a room photograph might establish the setting. Ask for the bottle on the windowsill, then describe the light, the camera position and the space needed for copy. Review the label and proportions before making another change.

Choose the size when the idea is working

The platform offers 1K, 2K and 4K output, several aspect ratios, and JPG or PNG files. Larger renders take longer and change the price. Start at 1K to compare a few directions, then use a larger output when you have settled on the composition.

For a café poster, try: “A blue ceramic cup on a sunlit counter. The headline reads ‘A GOOD MORNING’ above it in large cream lettering. Leave the lower quarter clear for details.” Keep the same brief while changing only the framing, so the alternatives are easier to judge.

Use search when the brief needs it

Optional Google Search and Image Search controls can add current information or web imagery as context. They are useful for grounded visual briefs, but the finished image still needs a factual and lettering check.

Open Nano Banana 2.1, add a brief or references, and review the estimate for your chosen settings before creating.

Capabilities checked against the official Nano Banana 2.1 documentation on Replicate.

Cover image prompt

Editorial cover artwork generated with OpenAI image generation. The exact prompt is below.

Illustrate this everyday scene for the SUPERMODELS illustration collection: One slice of toast just spread with orange marmalade on a cobalt ceramic plate, with a butter knife and a crumb or two. Close view of a quiet breakfast table.

Contemporary SUPERMODELS editorial gouache illustration with clean cut-paper shapes, fine subtle risograph grain, warm ivory, cobalt blue, moss green and burnt orange, tactile matte painted paper, soft directional light, generous negative space and an elegant playful composition. Limit the palette to those colors and charcoal shadows. Use broad simplified shapes and visible dry gouache texture, as in a printed editorial illustration. Avoid photorealism, 3D rendering, glossy materials, ornate fantasy, clutter, outlines, gradients and collage grids. One self-contained full-bleed landscape artwork, exact 16:9 aspect ratio, with the focal subject comfortably inside the middle 75 percent. No text, lettering, logo, frame, borders or watermark.

← All posts