gemini-imagen

SKILL.md

This skill enables image generation from text prompts using Google's Gemini Imagen API. It provides a reusable script that handles API authentication, request formatting, response processing, and automatic image saving with proper error handling.

The Gemini API requires an API key for authentication. Obtain a key from Google AI Studio.

Recommended approach: Store the API key as an environment variable:

Generate images from text prompts using Google's Gemini Imagen API. This skill should be used when the user requests image creation, generation, or visualization from text descriptions (e.g., "create an image of...", "generate a picture showing...", "make me an image for..."). Source: agentiveau/myagentive.

View raw