nano-banana
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseNano Banana - Gemini Native Image Generation
Nano Banana - Gemini原生图像生成
Generate images with Google Gemini native image models via inference.sh CLI.

通过inference.sh CLI使用Google Gemini原生图像模型生成图片。

Quick Start
快速开始
bash
curl -fsSL https://cli.inference.sh | sh && infsh login
infsh app run google/gemini-3-pro-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
Models
支持模型
| Model | App ID | Speed | Quality |
|---|---|---|---|
| Gemini 3 Pro Image | | Slower | Best |
| Gemini 2.5 Flash Image | | Fast | Excellent |
| 模型 | 应用ID | 速度 | 质量 |
|---|---|---|---|
| Gemini 3 Pro Image | | 较慢 | 最佳 |
| Gemini 2.5 Flash Image | | 快速 | 优秀 |
Search Gemini Image Apps
搜索Gemini图像应用
bash
infsh app list --search "gemini image"bash
infsh app list --search "gemini image"Examples
使用示例
Basic Text-to-Image
基础文本生成图像
bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "A futuristic cityscape at sunset with flying cars"
}'bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "A futuristic cityscape at sunset with flying cars"
}'Multiple Images
生成多张图像
bash
infsh app run google/gemini-2-5-flash-image --input '{
"prompt": "Minimalist logo design for a coffee shop",
"num_images": 4
}'bash
infsh app run google/gemini-2-5-flash-image --input '{
"prompt": "Minimalist logo design for a coffee shop",
"num_images": 4
}'Custom Aspect Ratio
自定义宽高比
bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "Panoramic mountain landscape with northern lights",
"aspect_ratio": "16:9"
}'bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "Panoramic mountain landscape with northern lights",
"aspect_ratio": "16:9"
}'Image Editing (with input image)
图像编辑(含输入图像)
bash
infsh app run google/gemini-2-5-flash-image --input '{
"prompt": "Add a rainbow in the sky",
"images": ["https://example.com/landscape.jpg"]
}'bash
infsh app run google/gemini-2-5-flash-image --input '{
"prompt": "Add a rainbow in the sky",
"images": ["https://example.com/landscape.jpg"]
}'High Resolution (4K)
高分辨率(4K)
bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "Detailed illustration of a medieval castle",
"resolution": "4K"
}'bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "Detailed illustration of a medieval castle",
"resolution": "4K"
}'With Google Search Grounding
结合Google搜索Grounding
bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "Current weather in Tokyo visualized as an artistic scene",
"enable_google_search": true
}'bash
infsh app run google/gemini-3-pro-image-preview --input '{
"prompt": "Current weather in Tokyo visualized as an artistic scene",
"enable_google_search": true
}'Input Options
输入参数选项
| Parameter | Type | Description |
|---|---|---|
| string | Required. What to generate or change |
| array | Input images for editing (up to 14) |
| integer | Number of images to generate |
| string | Output ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "auto" |
| string | "1K", "2K", "4K" (Gemini 3 Pro only) |
| string | Output format for images |
| boolean | Enable real-time info grounding |
| 参数 | 类型 | 描述 |
|---|---|---|
| string | 必填项。 要生成或修改的内容描述 |
| array | 用于编辑的输入图像(最多14张) |
| integer | 要生成的图像数量 |
| string | 输出比例:"1:1"、"16:9"、"9:16"、"4:3"、"3:4"、"auto" |
| string | "1K"、"2K"、"4K"(仅Gemini 3 Pro支持) |
| string | 图像的输出格式 |
| boolean | 启用实时信息Grounding |
Prompt Tips
提示词技巧
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
风格:照片写实、插画、水彩画、油画、数字艺术、动漫、3D渲染
构图:特写、广角镜头、航拍、微距、肖像、风景
光线:自然光、工作室灯光、黄金时段、戏剧性阴影、霓虹灯光
细节:添加关于纹理、颜色、情绪、氛围的具体细节
Sample Workflow
示例工作流
bash
undefinedbash
undefined1. Generate sample input to see all options
1. 生成示例输入以查看所有选项
infsh app sample google/gemini-3-pro-image-preview --save input.json
infsh app sample google/gemini-3-pro-image-preview --save input.json
2. Edit the prompt
2. 编辑提示词
3. Run
3. 运行
infsh app run google/gemini-3-pro-image-preview --input input.json
undefinedinfsh app run google/gemini-3-pro-image-preview --input input.json
undefinedRelated Skills
相关技能
bash
undefinedbash
undefinedFull platform skill (all 150+ apps)
完整平台技能(包含150+应用)
npx skills add inference-sh/skills@inference-sh
npx skills add inference-sh/skills@inference-sh
All image generation models
所有图像生成模型
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@ai-image-generation
Video generation (for image-to-video)
视频生成(用于图像转视频)
npx skills add inference-sh/skills@ai-video-generation
Browse all image apps: `infsh app list --category image`npx skills add inference-sh/skills@ai-video-generation
浏览所有图像应用:`infsh app list --category image`Documentation
文档
- Running Apps - How to run apps via CLI
- Streaming Results - Real-time progress updates
- File Handling - Working with images