Nano Banana Pro

A straightforward wrapper around Google's Gemini 3.1 Flash Image API for generating and editing images from the command line. You can create new images from text prompts or edit existing ones, with resolution options from 512px up to 4K. The workflow is sensible: iterate at 1K for speed, then run your final prompt at 4K once you've got it right. Image editing uses the same interface but takes an input image and modification instructions. It saves PNGs to your current directory with timestamped filenames. Requires a Gemini API key and uv for execution. Nothing fancy here, just a clean CLI for image generation when you need it in your terminal workflow.

skills.sh installs: 303
GitHub stars: 7.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add steipete/agent-scripts --skill nano-banana-pro --agent claude-code

Installs into .claude/skills of the current project.

Files

Nano Banana 2 Image Generation & Editing

Generate new images or edit existing ones using Google's Nano Banana 2 API (Gemini 3.1 Flash Image).

Usage

Run the script using absolute path (do NOT cd to skill directory first):

Generate new image:

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

Edit existing image:

uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--resolution 512|1K|2K|4K] [--api-key KEY]

Important: Always run from the user's current working directory so images are saved where the user is working, not in the skill directory.