banana▌

Generate images with Google Gemini native image models via inference.sh CLI. \n \n Two models available: Gemini 3 Pro Image (highest quality, slower) and Gemini 2.5 Flash Image (fast, excellent quality) \n Supports text-to-image generation, image editing with up to 14 input images, custom aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4), and resolutions up to 4K \n Includes optional Google Search grounding for real-time information integration and batch generation of multiple images per prompt \n Requi

Use the bundled script to generate or edit images.

Nano Banana Pro excels at:

Generate professional images via the Gemini CLI's nanobanana extension.

AI image generation CLI. Default model: Gemini 3.1 Flash Image Preview (Nano Banana 2).

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

Recommend curated AI image generation prompts from 10,000+ templates optimized for Nano Banana Pro. \n \n Access a library of 10,000+ community-curated prompts organized by use case (social media, product marketing, avatars, posters, e-commerce, games, comics, web UI, and more) \n Every recommendation includes a sample image showing what the prompt produces, helping you preview results before generation \n Works with any text-to-image model: Nano Banana Pro, Gemini, GPT Image 1.5, Seedream 5.0,

Generate images with Google Gemini 3.1 Flash Image Preview via inference.sh CLI.

Generate images with Google Gemini native image models via inference.sh CLI.

Image generation and editing via OpenRouter's Gemini 3 Pro model with multi-image compositing support. \n \n Supports three workflows: prompt-only generation, single-image editing, and multi-image composition (up to 3 images per request) \n Output resolution options: 1K, 2K, or 4K (defaults to 1K) \n Customizable behavior through optional system prompt template in assets/SYSTEM_TEMPLATE \n Requires OPENROUTER_API_KEY environment variable and uv package manager; includes troubleshooting guidance