# Nano Banana — 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 Google's Gemini 3 Pro Image and Gemini 2.5 Flash Image, multi-image input too.

- **Type:** [Model](https://skills.varg.ai/models.md) · [Images & thumbnails](https://skills.varg.ai/browse/skills/image.md)
- **Slug:** `inference-sh-nano-banana`
- **Status:** live
- **Publisher:** inference.sh (vendor, verified)
- **License:** MIT
- **Source:** https://github.com/inference-sh/skills/tree/main/tools/image/nano-banana
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI
- **Requires:** inference.sh account, belt CLI (`belt login`)
- **Cost:** Billed by inference.sh
- **Adoption:** 6 installs, 781 GitHub stars (skills.sh, 2026-10-26)

## What it does

Runs Google's native Gemini image models through inference.sh: Gemini 3 Pro Image (Nano Banana Pro) and Gemini 2.5 Flash Image. It covers text-to-image, image editing and multi-image input.

## Use when

- Nano Banana Pro generation or edits
- Combining several reference images

## Install

- Claude Code: `npx skills add inference-sh/skills --skill nano-banana -a claude-code`
- Codex: `npx skills add inference-sh/skills --skill nano-banana -a codex`
- Cursor: `npx skills add inference-sh/skills --skill nano-banana -a cursor`
- Gemini CLI: `npx skills add inference-sh/skills --skill nano-banana -a gemini-cli`

**Models it drives:** nano_banana_pro, gemini-2.5-flash-image

## Example output

https://skills.varg.ai/previews/inference-sh-nano-banana.webp — Nano Banana Pro (Gemini 3 Pro Image, the skill's default model) example from Google DeepMind's model page: a sunny Berlin street whose old houses are shaped like the letters B-E-R-L-I-N (credit: Google DeepMind (Nano Banana Pro), https://deepmind.google/models/gemini-image/pro/)

## More images & thumbnails skills

- [Higgsfield YouTube Thumbnail](https://skills.varg.ai/skills/higgsfield-youtube-thumbnail.md): Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
- [Slack GIF Creator](https://skills.varg.ai/skills/anthropic-slack-gif-creator.md): Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
- [PixiJS GIFs](https://skills.varg.ai/skills/pixijs-gif.md): Load, play and control animated GIFs inside a PixiJS v8 scene.
- [AI Image Generation](https://skills.varg.ai/skills/inference-sh-ai-image-generation.md): Generate images with 50+ models from one CLI: GPT Image 2.5, FLUX, Gemini, Grok, Seedream, Reve and more.
- [Background Removal](https://skills.varg.ai/skills/inference-sh-background-removal.md): Cut subjects out of photos into clean transparent PNGs with BiRefNet.
- [FLUX Image](https://skills.varg.ai/skills/inference-sh-flux-image.md): Generate and restyle images with FLUX Dev LoRA and FLUX.2 Klein, including custom LoRA styles.

## 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.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt