playbooks

home / skills / openclaw / openclaw / nano-banana-pro

nano-banana-pro skill

/skills/nano-banana-pro

This skill helps you generate or edit images with Gemini 3 Pro Image using prompts and save results to a file.

npx playbooks add skill openclaw/openclaw --skill nano-banana-pro

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
1.5 KB
---
name: nano-banana-pro
description: Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
homepage: https://ai.google.dev/
metadata:
  {
    "openclaw":
      {
        "emoji": "🍌",
        "requires": { "bins": ["uv"], "env": ["GEMINI_API_KEY"] },
        "primaryEnv": "GEMINI_API_KEY",
        "install":
          [
            {
              "id": "uv-brew",
              "kind": "brew",
              "formula": "uv",
              "bins": ["uv"],
              "label": "Install uv (brew)",
            },
          ],
      },
  }
---

# Nano Banana Pro (Gemini 3 Pro Image)

Use the bundled script to generate or edit images.

Generate

```bash
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png" --resolution 1K
```

Edit (single image)

```bash
uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "output.png" -i "/path/in.png" --resolution 2K
```

Multi-image composition (up to 14 images)

```bash
uv run {baseDir}/scripts/generate_image.py --prompt "combine these into one scene" --filename "output.png" -i img1.png -i img2.png -i img3.png
```

API key

- `GEMINI_API_KEY` env var
- Or set `skills."nano-banana-pro".apiKey` / `skills."nano-banana-pro".env.GEMINI_API_KEY` in `~/.openclaw/openclaw.json`

Notes

- Resolutions: `1K` (default), `2K`, `4K`.
- Use timestamps in filenames: `yyyy-mm-dd-hh-mm-ss-name.png`.
- The script prints a `MEDIA:` line for OpenClaw to auto-attach on supported chat providers.
- Do not read the image back; report the saved path only.

Overview

This skill provides a command-line wrapper to generate and edit images using Gemini 3 Pro Image (Nano Banana Pro). It exposes a small Python script that creates single images, edits inputs, or composes up to 14 images into one scene. It is designed for local use with an API key and integrates cleanly with OpenClaw workflows.

How this skill works

You run the bundled script with a prompt, output filename, and optional inputs or resolution flags. The script accepts single-image edits (-i for input) and multiple -i flags for composing up to 14 images. It outputs the saved file path and prints a MEDIA: line so OpenClaw-capable chat providers can auto-attach results.

When to use it

  • Quickly generate concept art or prototypes from textual prompts.
  • Edit a specific photo or asset using text-based instructions.
  • Combine multiple image assets into a single coherent scene.
  • Produce high-resolution exports (1K, 2K, 4K) for review or delivery.
  • Integrate image generation into OpenClaw-based chat workflows.

Best practices

  • Set GEMINI_API_KEY as an environment variable or in ~/.openclaw/openclaw.json to avoid runtime prompts.
  • Use timestamps in filenames (yyyy-mm-dd-hh-mm-ss-name.png) to prevent overwrites and keep history.
  • Start with 1K for iterations, then use 2K or 4K for final renders to save time and cost.
  • When composing multiple images, prepare consistent lighting and perspective to improve blending.
  • Let the script save files and report the path; do not programmatically read the image back in the same run.

Example use cases

  • Generate a product mockup from a brief prompt and export a 2K image for review.
  • Apply targeted edits to a single photo by passing -i input.png and a text instruction.
  • Merge character renders (up to 14) into a group scene for portfolio assembly.
  • Automate image generation in chat by capturing the MEDIA: output for auto-attachment.

FAQ

How do I provide the API key?

Set GEMINI_API_KEY in your environment or add skills."nano-banana-pro".apiKey or skills."nano-banana-pro".env.GEMINI_API_KEY in ~/.openclaw/openclaw.json.

What resolutions are supported?

Supported flags are 1K (default), 2K, and 4K. Use lower resolution for quick iterations.

Can I compose many images?

Yes. The script supports up to 14 -i inputs for multi-image composition into a single output.