Nano Banana 2: Fast Image Generation & Editing

HOW IT WORKS

Step 1. Write your prompt Describe the image you want to make, or the edit you want to apply. Nano Banana 2 is strong at legible text, infographics, and photorealism, so spell out any words you want in the image. Works great with: text and typography · infographics · photorealism · product shots

Step 2. Add an image to edit (optional) Upload a photo to transform it, like changing the background, lighting, or a single element. Leave it out to generate from the prompt alone.

Step 3. Hit run and download You get back your image in seconds. Preview it in the workflow, then download. Ready for: Photoshop · Figma · Canva · any editor

First time? Leave every setting as-is. The defaults (1K · PNG · auto aspect ratio · random seed) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard generation (most people) Start here — 1K · PNG · auto aspect ratio. The right starting point for almost everyone.

• Need print or large-format quality — Step the resolution up to 2K or 4K. Nano Banana 2 holds detail when you print or zoom.

• Want a specific shape — Set the aspect ratio to 1:1, 16:9, or 9:16 instead of auto, so the image fits where it will be used.

• Generating text or an infographic — Spell out the exact words and where they go. This model renders legible, multi-language text, so the more precise you are, the cleaner the type.

• Want real-world accuracy — Turn on web search grounding. The model can pull in current facts to build accurate diagrams, maps, and factual visuals.

• Editing a photo — Upload it and name the change plainly, like "change the background to a sunset, keep the subject unchanged." The rest of the image stays put.

• Reproduce a result you liked — Set a fixed seed instead of randomizing. The same prompt and seed give you the same image again.

Prompt: Be specific. For a new image, name the subject, style, lighting, and any text. For an edit, name the change and what to keep. Clear, detailed prompts get you closer on the first run.

USE CASES

🎨 Designers & Marketers Make posters, infographics, social graphics, and mockups with legible text baked in, instead of adding type in a separate pass.

🛍️ Product & E-commerce Generate or edit product visuals, swap scenes and lighting, and keep branding consistent across a set of images.

📊 Diagrams & Explainers Build accurate diagrams and maps, with web search grounding to keep the facts and labels right.

⚡ Fast Iteration Generate in seconds and run many variations cheaply. The speed makes it easy to explore directions before committing to one.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Images with text, signs, or typography

• Infographics, posters, and layouts

• Photorealistic scenes and product shots

• Clear, detailed prompts

⚠️ May produce softer results

• Dense paragraphs of tiny text

• Vague or contradictory prompts

• Edits that fight the original lighting

• Many unrelated elements crammed into one image

NEW TO COMFYUI?

Start with the free ComfyUI for Beginners Course on Floyo. Sixteen short videos take you from zero to running your own AI workflows. No setup headaches, no jargon, clear hands-on lessons. Watch the course, then run any workflow here in your browser.

👉 Watch the free ComfyUI for Beginners Course →

FAQ

What is Nano Banana 2? Nano Banana 2 is Google DeepMind's image generation and editing model, officially called Gemini 3.1 Flash Image and released in February 2026. It delivers Nano Banana Pro's quality at Flash speed, generating an image in a couple of seconds. It handles both making images from a prompt and editing images you upload, and it is strong at text rendering and world knowledge.

How is Nano Banana 2 different from Nano Banana Pro? Nano Banana 2 is built on Gemini Flash, so it is faster and cheaper while matching Pro-level quality. Nano Banana Pro runs on Gemini 3 Pro and takes a more deliberate pass, which can help on the most complex compositions. For most generation and editing work, Nano Banana 2 is the quicker, more cost-efficient choice, and Google has made it the default image model in the Gemini app.

Why is Nano Banana 2 called the #1 ranked image model? At launch it took the top Text-to-Image position on the Artificial Analysis and LMArena image leaderboards, ahead of models like Midjourney, DALL-E, and Flux. Those rankings are based on human preference comparisons, so it reflects how often people pick its output over the alternatives.

Can Nano Banana 2 render readable text in images? Yes. Strong text rendering carries over from the Nano Banana family, so it produces legible text in multiple languages. That makes it a fit for infographics, posters, menus, and slides where the words need to come out right.

What resolutions and aspect ratios can it output? Nano Banana 2 supports resolutions from 512px up to 4K. This workflow defaults to 1K PNG with an auto aspect ratio, and you can set a fixed ratio like 1:1, 16:9, or 9:16 and step the resolution up for print or large-format use.

Can I use the results commercially? Yes. Images you generate on Floyo carry full commercial rights. Note that Google embeds an invisible SynthID watermark and C2PA Content Credentials in Nano Banana 2 output to mark it as AI-generated, and you are responsible for having the right to any images you upload to edit.

How to run Nano Banana 2 online? You can run Nano Banana 2 online through Floyo. No installation, no setup, no API keys to wire up. Open the workflow in your browser, write a prompt or upload an image, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs a prompt and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it? Write a prompt or upload an image, and run it. The settings are already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.