generate-image

Generate images from text prompts by running the script with your description: `python scripts/generate_image.py "your prompt here"`. The Skill uses AI models via OpenRouter API to create photorealistic or artistic images directly from natural language descriptions without manual design work.

Image generation supports multiple models including Gemini 3 Pro Image Preview and Flux Pro through OpenRouter. These models let you balance quality and speed depending on your project needs—choose faster models for quick iterations or premium models for higher-quality results.

You can both generate new images from prompts and edit existing images by applying targeted changes. This lets you refine artwork without recreating it entirely, combining generation and editing workflows in one Skill.

You need an OpenRouter API key to authenticate requests. The Skill requires Python, the requests library for API calls, and a descriptive text prompt. Setup is minimal—just provide your API credentials and run the generation script.

Create photorealistic images for marketing, artistic renderings for presentations, concept art for projects, and visual assets for design work. The Skill handles any visual content you can describe in natural language—from product mockups to conceptual illustrations.