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 inpu...
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Generate images with Google Gemini 3.1 Flash Image Preview via inference.sh CLI.
curl -fsSL https://cli.inference.sh | sh && infsh logininfsh app run google/gemini-3-1-flash-image-preview --input '{"prompt": "a banana in space, photorealistic"}'
Install note: The install script only detects your OS/architecture, downloads the matching binary from
, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.dist.inference.sh
infsh app run google/gemini-3-1-flash-image-preview --input '{ "prompt": "A futuristic cityscape at sunset with flying cars" }'
infsh app run google/gemini-3-1-flash-image-preview --input '{ "prompt": "Minimalist logo design for a coffee shop", "num_images": 4 }'
infsh app run google/gemini-3-1-flash-image-preview --input '{ "prompt": "Panoramic mountain landscape with northern lights", "aspect_ratio": "16:9" }'
infsh app run google/gemini-3-1-flash-image-preview --input '{ "prompt": "Add a rainbow in the sky", "images": ["https://example.com/landscape.jpg"] }'
infsh app run google/gemini-3-1-flash-image-preview --input '{ "prompt": "Detailed illustration of a medieval castle", "resolution": "4K" }'
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 }'
| Parameter | Type | Description |
|---|---|---|
| string | Required. What to generate or change |
| array | Input images for editing (up to 14). Supported: JPEG, PNG, WebP |
| integer | Number of images to generate |
| string | Output ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "auto" |
| string | "1K", "2K", "4K" (default: 1K) |
| string | Output format for images |
| boolean | Enable real-time info grounding (weather, news, etc.) |
| Field | Type | Description |
|---|---|---|
| array | The generated or edited images |
| string | Text description or response from the model |
| object | Metadata about inputs/outputs for pricing |
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
# 1. Generate sample input to see all options infsh app sample google/gemini-3-1-flash-image-preview --save input.json2. Edit the prompt
3. Run
infsh app run google/gemini-3-1-flash-image-preview --input input.json
from inferencesh import inferenceclient = 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']}")
# Original Nano Banana (Gemini 3 Pro Image, Gemini 2.5 Flash Image) npx skills add inference-sh/skills@nano-bananaFull 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 imageNo automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.