Nano Banana 2

This wraps Google's Gemini 3.1 Flash Image Preview API for generating and editing images straight from the command line. You get explicit control over resolution (512px through 4K) and aspect ratios, plus the ability to feed in up to 14 reference images when you need character consistency or multi-source composition. The skill maps natural language like "quick draft" or "hero image" to actual parameters, which saves you from memorizing the API. It's faster than waiting on Midjourney's queue and more scriptable than clicking through web UIs. If you're building workflows that need repeatable image generation with version control and CI integration, this is the straightforward Python wrapper you'd write yourself if you had an afternoon.

skills.sh installs: 897
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add intellectronica/agent-skills --skill nano-banana-2 --agent claude-code

Installs into .claude/skills of the current project.

Files

Nano Banana 2 Image Generation & Editing

Generate new images or edit existing images with Nano Banana 2 (gemini-3.1-flash-image-preview).

Usage

Run the script using absolute or workspace-relative path (do NOT cd into the skill directory first):

Generate new image:

uv run ./.agents/skills/nano-banana-2/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 512px|1K|2K|4K] [--aspect-ratio RATIO] [--api-key KEY]

Edit image(s) with references:

uv run ./.agents/skills/nano-banana-2/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input1.png" [--input-image "path/to/input2.png" ...] [--resolution 512px|1K|2K|4K] [--aspect-ratio RATIO] [--api-key KEY]

Always run from the user's current working directory so outputs are saved in the active project context.