gemini-imagegen

使用Gemini API(Nano Banana)生成和编辑图像。在根据文本提示创建图像、编辑现有图像、应用风格转换、生成带文本的标志、创建贴纸、产品模型或任何图像生成/操作任务时使用此技能。支持文本到图像、图像编辑、多轮精炼和从多个参考图像组合。

📖 中文导读:使用Gemini API(Nano Banana)生成和编辑图像。在根据文本提示创建图像、编辑现有图像、应用风格转换、生成带文本的标志、创建贴纸、产品模型或任何图像生成/操作任务时使用此技能。支持文本到图像、图像编辑、多轮精炼和从多个参考图像组合。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。

name: gemini-imagegen description: Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Gemini Image Generation (Nano Banana)

Generate and edit images using Google's Gemini API. The environment variable GEMINI_API_KEY must be set.

Available Models

Model Alias Resolution Best For
gemini-2.5-flash-image Nano Banana 1024px Speed, high-volume tasks
gemini-3-pro-image-preview Nano Banana Pro Up to 4K Professional assets, complex instructions, text rendering

Quick Start Scripts

Text-to-Image

python ~/.claude/skills/gemini-imagegen/scripts/generate_image.py "A cat wearing a wizard hat" output.png

Edit Existing Image

python ~/.claude/skills/gemini-imagegen/scripts/edit_image.py input.png "Add a rainbow in the background" output.png

Multi-Turn Chat (Iterative Refinement)

python ~/.claude/skills/gemini-imagegen/scripts/multi_turn_chat.py

Core API Pattern

All image generation uses the generateContent endpoint with responseModalities: ["TEXT", "IMAGE"]:

import os
import base64
from google import genai

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

response = client.models.generate_content(
    model="gemini-2.5-flash-image",
    contents=["Your prompt here"],
)

for part in response.parts:
    if part.text:
        print(part.text)
    elif part.inline_data:
        image = part.as_image()
        image.save("output.png")

Image Configuration Options

Control output with image_config:

from google.genai import types

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[prompt],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        image_config=types.ImageConfig(
            aspect_ratio="16:9",  # 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
            image_size="2K"       # 1K, 2K, 4K (Pro only for 4K)
        ),
    )
)

Editing Images

Pass existing images with text prompts:

from PIL import Image

img = Image.open("input.png")
response = client.models.generate_content(
    model="gemini-2.5-flash-image",
    contents=["Add a sunset to this scene", img],
)

Multi-Turn Refinement

Use chat for iterative editing:

from google.genai import types

chat = client.chats.create(
    model="gemini-2.5-flash-image",
    config=types.GenerateContentConfig(response_modalities=['TEXT', 'IMAGE'])
)

response = chat.send_message("Create a logo for 'Acme Corp'")
# Save first image...

response = chat.send_message("Make the text bolder and add a blue gradient")
# Save refined image...

Prompting Best Practices

Photorealistic Scenes

Include camera details: lens type, lighting, angle, mood.

"A photorealistic close-up portrait, 85mm lens, soft golden hour light, shallow depth of field"

Stylized Art

Specify style explicitly:

"A kawaii-style sticker of a happy red panda, bold outlines, cel-shading, white background"

Text in Images

Be explicit about font style and placement. Use gemini-3-pro-image-preview for best results:

"Create a logo with text 'Daily Grind' in clean sans-serif, black and white, coffee bean motif"

Product Mockups

Describe lighting setup and surface:

"Studio-lit product photo on polished concrete, three-point softbox setup, 45-degree angle"

Whiteboard Visualization

"Take this text and create an image of a whiteboard that summarizes it using diagrams, arrows, colors, and captions explaining the core idea: [CONTENT]"

Advanced Features (Pro Model Only)

Google Search Grounding

Generate images based on real-time data:

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["Visualize today's weather in Tokyo as an infographic"],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        tools=[{"google_search": {}}]
    )
)

Multiple Reference Images (Up to 14)

Combine elements from multiple sources:

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[
        "Create a group photo of these people in an office",
        Image.open("person1.png"),
        Image.open("person2.png"),
        Image.open("person3.png"),
    ],
)

REST API (curl)

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "A serene mountain landscape"}]}]
  }' | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' | base64 --decode > output.png

Setup

1. Get API Key

Visit Google AI Studio and create an API key.

2. Set Environment Variable

Add to your shell profile (~/.zshrc or ~/.bashrc):

export GEMINI_API_KEY="your-api-key-here"

3. Install Dependencies

pip install google-genai pillow

Notes

  • All generated images include SynthID watermarks
  • Image-only mode (responseModalities: ["IMAGE"]) won't work with Google Search grounding
  • For editing, describe changes conversationally—the model understands semantic masking
  • CRITICAL: Do NOT read generated image files with the Read tool - they are large and will fill up context and break the CLI