generate-image

Generate images from text prompts using the Gemini API.

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/tegnike/ai-agent-game-streamer --skill generate-image-tegnike
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/tegnike/ai-agent-game-streamer/tree/main/.agents/skills/generate-image
Command: npx skills add https://github.com/tegnike/ai-agent-game-streamer --skill generate-image-tegnike

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables generating high-quality images from text prompts by calling the Gemini API, allowing creators to rapidly visualize ideas without requiring local image generation tools.

Core Features & Use Cases

  • Generate images from natural language prompts using Gemini's gemini-3-pro-image-preview model.
  • Fine-grained controls: aspectRatio and imageSize to fit various layouts.
  • Use Case: Create concept art, social media visuals, thumbnails, or marketing assets with a single prompt.

Quick Start

Run a basic image generation example. Replace YOUR_PROMPT_HERE and set GEMINI_API_KEY to authorize the request.

For Quick Start, you can try: curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image-preview:generateContent"
-H "x-goog-api-key: $GEMINI_API_KEY"
-H "Content-Type: application/json"
-d '{"contents": [{"parts": [{"text": "YOUR_PROMPT_HERE"}]}], "generationConfig": {"responseModalities": ["IMAGE"]}}' | jq -r '.candidates[0].content.parts[0].inlineData.data' | base64 -d > output.png

Frequently Asked Questions about generate-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using the Gemini API?▼

To generate images from text prompts using the Gemini API, you send a POST request to the generativelanguage endpoint with your text prompt and GEMINI_API_KEY, specifying IMAGE in the responseModalities to receive base64-encoded image data.

Can I use the Gemini API for AI art generation without local image tools?▼

Yes, you can use the Gemini API for AI art generation without local tools by calling the gemini-3-pro-image-preview model remotely, allowing you to rapidly visualize ideas and create concept art directly through API requests.

Does the Gemini API image generation support aspect ratio and image size controls?▼

The Gemini API image generation supports aspectRatio and imageSize options within the generationConfig, enabling you to fine-tune the output dimensions to fit various layouts for social media visuals or marketing assets.

What is the best way to automate image generation via curl for rapid visual prototyping?▼

The best way to automate image generation via curl for rapid visual prototyping is to execute a POST request with your prompt and GEMINI_API_KEY, then pipe the JSON response through jq to extract and decode the base64 image data into a PNG file.

Do I need an API key to generate content with the gemini-3-pro-image-preview model?▼

Yes, you need an API key to generate content with the gemini-3-pro-image-preview model, which must be provided via the GEMINI_API_KEY environment variable or passed directly in the x-goog-api-key header for authorization.