Nano Banana 2 — model skill for images & thumbnails

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Generate and edit images with Nano Banana 2, with up to 14 reference images and search grounding.

What it does

Runs Google Gemini 3.1 Flash Image Preview (Nano Banana 2) through inference.sh for text-to-image and image editing. It accepts up to 14 input images and supports Google Search grounding.

Use when

Install

Models it drives: nano_banana_2

Example output

https://skills.varg.ai/previews/inference-sh-nano-banana-2.webp — Nano Banana 2 (Gemini 3.1 Flash Image) output from inference.sh's launch guide: a workspace flat lay with legible handwritten 'TODO: ship it', showing its text rendering (credit: inference.sh blog (Nano Banana 2 generation), https://inference.sh/blog/guides/nano-banana-2-image-generation)

More images & thumbnails skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.