Generate and edit images using Google's Gemini 3 Pro Image API, supporting text-to-image and image-to-image workflows at 1K, 2K, or 4K resolution.
by
Peter Steinberger
Nano Banana Pro generates new images from text prompts or edits existing images with natural language instructions using the Gemini 3 Pro Image API.
It supports 1K, 2K, and 4K output sizes and a draft-to-final workflow so you can iterate fast at low resolution before generating a high-res final.
Choose text-to-image or image-to-image, then pass the prompt and optional input image.
Invoke the Python script using `uv run` to call the Gemini 3 Pro Image API.
Generate 1K drafts to refine the prompt quickly.
When satisfied, output a 4K final for production-ready quality.
Create images from descriptive prompts with Gemini 3 Pro Image.
Edit existing images with natural language instructions.
Choose 1K (~1024px), 2K (~2048px), or 4K (~4096px) output sizes.
Iterate quickly at low resolution, then generate a high-res final.
Outputs files with `yyyy-mm-dd-hh-mm-ss-name.png` naming.
Built-in templates for both generation and precise editing tasks.
Generate visual concepts for design projects in minutes.
Remove objects, change backgrounds, or adjust styles with image-to-image.
Create illustrations and graphics for blogs, presentations, or social media.
Refine prompts at 1K/2K before committing to a 4K final.
npx clawhub@latest install nano-banana-proRun in your terminal, or click the Install button at the top of this page for one-click setup.
The skill supports 1K, 2K, and 4K outputs.
Yes. Provide an input image and editing instructions for image-to-image workflows.
The API call will fail until you set `GEMINI_API_KEY`.
Outputs are saved to your current working directory with timestamped filenames.
Start with 1K drafts for speed, then produce 4K finals once the prompt is locked.