nano-banana-2

Generate images with Google Nano Banana 2 text-to-image via the RunComfy CLI.

Updated Jun 11, 2026
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill nano-banana-2-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-2
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/nano-banana-2
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill nano-banana-2-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Generating images with the Nano Banana 2 model requires knowing its prompting patterns, supported aspect ratios, resolution tiers, and parameter schema; this Skill bundles that knowledge so prompts produce predictable output instead of trial-and-error API calls. ## Core Features & Use Cases - Text-to-image generation: Calls runcomfy run google/nano-banana-2/text-to-image with a validated JSON input schema covering prompt, seed, aspect ratio, resolution, and output format. - Documented prompting patterns: Subject-first grammar, quoted in-image typography, seed locking for reproducible variants, and optional web grounding for current-event imagery. - Model routing guidance: Decision table for when to use Nano Banana 2 versus Nano Banana Pro, Nano Banana Edit, GPT Image 2, Flux 2, or Seedream. - Use Case: A marketer needs four vertical 9:16 thumbnail drafts for a social campaign; the Skill runs a 0.5K batch of 4 for ideation, then promotes the winner to 2K with a locked seed. ## Quick Start Ask the AI to generate an image with Nano Banana 2 from your prompt, for example a 16:9 product card with quoted headline text, and it will run the RunComfy CLI and download the result to your output directory.

Frequently Asked Questions about nano-banana-2

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images with Nano Banana 2?▼

Run `runcomfy run google/nano-banana-2/text-to-image` with a JSON input containing your prompt and an output directory. Install the CLI with `npm i -g @runcomfy/cli` and authenticate via `runcomfy login` or the RUNCOMFY_TOKEN environment variable.

Nano Banana 2 vs Nano Banana Pro: which should I use?▼

Nano Banana 2 is the flash-tier model suited for rapid drafts, batch variants, and in-image typography. Nano Banana Pro is the better choice for hyperrealistic portraits and maximum detail; default to Pro for portraits and 2 for everything else.

What aspect ratios and resolutions does Nano Banana 2 support?▼

It supports 11 aspect ratios from 21:9 to 9:16 including 1:1, 16:9, and 4:5, plus four resolution tiers: 0.5K, 1K, 2K, and 4K. Values outside these lists return a 422 error.

How do I render text inside a generated image reliably?▼

Quote the exact characters in the prompt, such as "the label reads 'AURA' in clean bold sans-serif", and specify placement and font style. Non-quoted text requests produce unpredictable rendering.

Can Nano Banana 2 edit existing images or generate video?▼

No, this endpoint is still-image text-to-image only with a maximum of 4 outputs per request. For image editing that preserves a subject, use the sibling nano-banana-edit skill with the /edit endpoint.

Why did my Nano Banana 2 request fail with exit code 77?▼

Exit code 77 means the CLI is not signed in or the token was rejected. Run `runcomfy login` to complete the browser device-code flow, or set a valid RUNCOMFY_TOKEN environment variable in CI environments.