home / skills / inference-sh / skills / nano-banana-2
This skill generates images and edits visuals using Gemini 3.1 Flash Image Preview via inference.sh, enabling up to 14 inputs and Google search grounding.
npx playbooks add skill inference-sh/skills --skill nano-banana-2Review the files below or copy the command above to add this skill to your agents.
---
name: nano-banana-2
description: "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"
allowed-tools: Bash(infsh *)
---
# 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
> Requires inference.sh CLI (`infsh`). Get installation instructions: `npx skills add inference-sh/skills@agent-tools`
```bash
infsh login
infsh app run google/gemini-3-1-flash-image-preview --input '{"prompt": "a banana in space, photorealistic"}'
```
## 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@agent-tools
# 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 images
This skill provides CLI access to Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via the inference.sh tool for fast image generation and editing. It supports text-to-image, multi-image inputs (up to 14), image editing, custom aspect ratios and resolutions, and optional Google Search grounding for up-to-date context. Use the infsh CLI to run generation tasks or sample inputs, and stream live progress when needed.
You run the prebuilt infsh CLI and invoke the google/gemini-3-1-flash-image-preview app with a JSON input containing a prompt and optional parameters. The skill accepts images for editing, controls for num_images, aspect_ratio, resolution, and a flag to enable Google Search grounding. Output returns generated image files, a text description, and metadata about the run for pricing and tracking. The CLI supports sampling templates, saving input files, and streaming progress updates during long runs.
How many input images can I provide?
Up to 14 input images in supported formats (JPEG, PNG, WebP).
What resolutions are available?
Options include 1K (default), 2K, and 4K; specify resolution in the input JSON.
Can I stream progress updates?
Yes. The SDK and CLI support streaming updates so you can monitor progress and partial outputs.