nano-banana-2
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation
Best use case
nano-banana-2 is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation
Teams using nano-banana-2 should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/nano-banana-2/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How nano-banana-2 Compares
| Feature / Agent | nano-banana-2 | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Nano Banana 2 - Gemini 3.1 Flash Image Preview
Generate images with Google Gemini 3.1 Flash Image Preview via [inference.sh](https://inference.sh) CLI.
## Quick Start
```bash
curl -fsSL https://cli.inference.sh | sh && infsh login
infsh app run google/gemini-3-1-flash-image-preview --input '{"prompt": "a banana in space, photorealistic"}'
```
> **Install note:** The [install script](https://cli.inference.sh) only detects your OS/architecture, downloads the matching binary from `dist.inference.sh`, and verifies its SHA-256 checksum. No elevated permissions or background processes. [Manual install & verification](https://dist.inference.sh/cli/checksums.txt) available.
## Examples
### Basic Text-to-Image
```bash
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "A futuristic cityscape at sunset with flying cars"
}'
```
### Multiple Images
```bash
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Minimalist logo design for a coffee shop",
"num_images": 4
}'
```
### Custom Aspect Ratio
```bash
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Panoramic mountain landscape with northern lights",
"aspect_ratio": "16:9"
}'
```
### Image Editing (with input images)
```bash
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Add a rainbow in the sky",
"images": ["https://example.com/landscape.jpg"]
}'
```
### High Resolution (4K)
```bash
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Detailed illustration of a medieval castle",
"resolution": "4K"
}'
```
### With Google Search Grounding
```bash
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Current weather in Tokyo visualized as an artistic scene",
"enable_google_search": true
}'
```
## Input Options
| Parameter | Type | Description |
|-----------|------|-------------|
| `prompt` | string | **Required.** What to generate or change |
| `images` | array | Input images for editing (up to 14). Supported: JPEG, PNG, WebP |
| `num_images` | integer | Number of images to generate |
| `aspect_ratio` | string | Output ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "auto" |
| `resolution` | string | "1K", "2K", "4K" (default: 1K) |
| `output_format` | string | Output format for images |
| `enable_google_search` | boolean | Enable real-time info grounding (weather, news, etc.) |
## Output
| Field | Type | Description |
|-------|------|-------------|
| `images` | array | The generated or edited images |
| `description` | string | Text description or response from the model |
| `output_meta` | object | Metadata about inputs/outputs for pricing |
## Prompt Tips
**Styles**: photorealistic, illustration, watercolor, oil painting, digital art, anime, 3D render
**Composition**: close-up, wide shot, aerial view, macro, portrait, landscape
**Lighting**: natural light, studio lighting, golden hour, dramatic shadows, neon
**Details**: add specific details about textures, colors, mood, atmosphere
## Sample Workflow
```bash
# 1. Generate sample input to see all options
infsh app sample google/gemini-3-1-flash-image-preview --save input.json
# 2. Edit the prompt
# 3. Run
infsh app run google/gemini-3-1-flash-image-preview --input input.json
```
## Python SDK
```python
from inferencesh import inference
client = inference()
# Basic generation
result = client.run({
"app": "google/gemini-3-1-flash-image-preview@0c7ma1ex",
"input": {
"prompt": "A banana in space, photorealistic"
}
})
print(result["output"])
# Stream live updates
for update in client.run({
"app": "google/gemini-3-1-flash-image-preview@0c7ma1ex",
"input": {
"prompt": "A futuristic cityscape at sunset"
}
}, stream=True):
if update.get("progress"):
print(f"progress: {update['progress']}%")
if update.get("output"):
print(f"output: {update['output']}")
```
## Related Skills
```bash
# Original Nano Banana (Gemini 3 Pro Image, Gemini 2.5 Flash Image)
npx skills add inference-sh/skills@nano-banana
# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@inference-sh
# All image generation models
npx skills add inference-sh/skills@ai-image-generation
```
Browse all image apps: `infsh app list --category image`
## Documentation
- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
- [Streaming Results](https://inference.sh/docs/api/sdk/streaming) - Real-time progress updates
- [File Handling](https://inference.sh/docs/api/sdk/files) - Working with imagesRelated Skills
nano-banana
Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image. Capabilities: text-to-image, image editing, multi-image input. Triggers: nano banana, gemini image, gemini 3 pro image, gemini 2.5 flash image, google image generation, native image generation, gemini native image
openakita/skills@yuque-skills
Manage Yuque (语雀) knowledge bases, documents, and team collaboration through API integration. Supports personal search, weekly reports, knowledge base management, document CRUD, and group collaboration workflows. Based on yuque/yuque-skills.
openakita/skills@youtube-summarizer
Summarize YouTube videos by extracting transcripts and generating structured notes. Use when the user wants to summarize a YouTube video, extract key points from a talk, create study notes from a lecture, or get timestamps for important moments. Supports multiple URL formats and languages.
openakita/skills@xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
openakita/skills@xiaohongshu-creator
Create engaging Xiaohongshu (RED/小红书) content including titles, body text, hashtags, and image style recommendations. Supports multiple content types such as product reviews, tutorials, lifestyle sharing, and shopping guides with platform-specific optimization.
openakita/skills@xiaodu-control
Xiaodu smart device control skill via MCP protocol. Control Xiaodu devices and ecosystem hardware for smart home IoT tasks, scene automation, and physical interaction. Use when user wants to control smart home devices or IoT equipment.
openakita/skills@wecom-cli
WeCom (Enterprise WeChat) CLI - official open-source CLI tool from WeCom. Covers 7 business categories: Contacts, Todos, Meetings, Messages, Schedules, Documents, Smartsheets. Built in Rust for macOS/Linux/Windows. Use when user wants to operate WeCom resources.
openakita/skills@wechat-article
Create and format WeChat Official Account (公众号) articles with proper Markdown-to-WeChat HTML conversion, rich formatting, cover image guidance, and both API and manual publishing workflows.
openakita/skills@webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
openakita/skills@web-artifacts-builder
Suite of tools for creating elaborate, multi-component interactive HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
openakita/skills@video-downloader
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
openakita/skills@translate-pdf
Translate PDF documents while preserving original layout, styling, tables, images, and formatting. Supports Simplified Chinese, Traditional Chinese, English, Japanese, Korean, and more. Page-by-page translation with structure preservation.