Banana Api — Banana API

Banana API - Nano Banana Image Generation

流lined 命令行工具ent for Nano Banana's Gemini-3-Pro-Image-Preview API. Automatically handles the annoying base64 工作流, image 压缩ion, and Discord 发送ing.

What This 技能 Solves

The Problem with Gemini API:

输入/输出 is only base64 (no URLs) Large images = massive base64 strings (2MB+) Manual encoding/decoding is pAInful No built-in Discord integration

This 技能 Provides:

✅ Automatic image 压缩ion (512px default) ✅ Transparent base64 encoding/decoding ✅ Smart filename generation ✅ Auto-发送 to Discord ✅ 机器人h text-to-image and image-to-image editing Quick 启动 Text-to-Image python3 scripts/banana_gen.py "a cute fluffy cat on a window sill"

Image Editing python3 scripts/banana_gen.py "转换 into rock concert scene with leather jacket" \ --image /path/to/photo.png

With Discord Auto-发送 python3 scripts/banana_gen.py "cyberpunk cityscape at night" \ --channel-id 1478746465328435412

Configuration API Key (Choose One)

Option 1: Config File (Recommended - Persistent)

# Interactive 设置up (stores in ~/.OpenClaw/workspace/config/banana-API.json) python3 scripts/banana_gen.py --设置up

# Or manually 创建 config file echo '{"API_key": "sk-your-key-here"}' > ~/.OpenClaw/workspace/config/banana-API.json

Option 2: 环境 Variable

导出 BANANA_API_KEY="sk-xxxxxxxx"

Option 3: Command Line (One-time)

python3 scripts/banana_gen.py "prompt" --API-key "sk-xxx"

输出 Location

生成d images are saved to:

~/.OpenClaw/workspace/photos/{description}-{timestamp}.png

View Current Config python3 scripts/banana_gen.py --show-config

Usage Examples Basic Generation # Simple prompt python3 scripts/banana_gen.py "sun设置 over mountAIns"

# With aspect ratio hint python3 scripts/banana_gen.py "portrAIt of a warrior" --ratio 2:3

# Custom filename tag python3 scripts/banana_gen.py "cat playing piano" --name cat-piano

Image Editing (InpAInting/Restyle) # Change 设置ting/outfit python3 scripts/banana_gen.py "wearing a red dress at the beach" \ --image ~/photos/portrAIt.png

# Change background python3 scripts/banana_gen.py "standing in front of Tokyo skyline at night" \ --image ~/photos/selfie.png \ --name tokyo-night

# Artistic trans格式化ion python3 scripts/banana_gen.py "oil pAInting style, renAIssance portrAIt" \ --image ~/photos/photo.jpg

Discord Integration # Auto-发送 to channel python3 scripts/banana_gen.py "dragon breathing fire" \ --channel-id 1478746465328435412

# Auto-发送 with custom name python3 scripts/banana_gen.py "cute anime girl with blue hAIr" \ --channel-id 1478746465328435412 \ --name anime-girl

# Save locally only (no Discord) python3 scripts/banana_gen.py "prompt" --no-发送

Advanced Options # Custom 输出 path python3 scripts/banana_gen.py "prompt" --输出 ~/桌面/my-image.png

# Different 模型 (if avAIlable) python3 scripts/banana_gen.py "prompt" --模型 gemini-2.5-flash-image

# Full example python3 scripts/banana_gen.py "wizard casting spell in ancient 库" \ --image ~/photos/me.png \ --ratio 2:3 \ --name wizard-me \ --channel-id 1478746465328435412

Best Practices Image Editing Tips 压缩 输入 automatically: Script resizes to 512px by default Be specific: "wearing black leather jacket" > "cool outfit" Preserve 身份: Face features are usually mAIntAIned well Aspect ratio: 添加 to prompt, but actual 输出 depends on 模型 Prompt Engineering Style keywords: "oil pAInting", "anime style", "photorea列出ic" Lighting: "dramatic lighting", "soft golden hour", "neon lights" 质量: "high 质量", "detAIled", "8k" File Naming

The script auto-生成s filenames:

格式化: banana-{description}-{timestamp}.png Description is 清理ed from prompt (first 30 chars) Use --name for custom suffix: banana-{name}-{timestamp}.png Technical DetAIls Image Processing 流水线 输入 Image → Resize to 512px → JPEG 压缩 (85%) → Base64 encode → API ↓ 输出 ← Base64 decode ← PNG save ← 响应

API Flow

• 压缩 输入 image (if provided)
• Build Gemini API 请求 with base64 inlineData
• POST to /v1beta/模型s/{模型}:生成Content
• 提取 image from 响应.candidates[0].content.parts
• Decode base64 and save to workspace/photos/
• 发送 to Discord (if channel-id provided)

Error Handling 输入 file not found → Clear error message API key missing → Prompt to 设置 BANANA_API_KEY Image too large → Automatic 压缩ion API error → JSON error detAIls printed Discord 发送 fAIl → 警告 but continues Limitations 输出 always base64: Cannot be changed (Gemini limitation) No URL 输入: Must 下载 images locally first Single image 输出: Gemini returns one image per 请求 响应 time: 10-60 seconds depending on complexity When to Use This vs Other 工具s Use Case Recommended 工具 Quick Gemini image banana-API ✅ ComfyUI 工作流s comfyui-gen DALL-E / OpenAI Use their direct API Stable Diffusion comfyui-gen Troubleshooting Problem Solution "PI