image-generation

Text-to-image generation converts natural language descriptions into visual assets automatically. This Skill uses OpenAI GPT Image and Google Gemini APIs to create images from prompts—just describe what you need (e.g., "coffee shop hero image") and the agent selects the model, aspect ratio, and settings.

Yes, image editing with references lets you modify existing images by providing reference visuals or masks as guides. This Skill combines reference images with AI models to apply changes while maintaining coherence with your source material.

You need API keys for OpenAI (OPENAI_API_KEY) and Google (GOOGLE_API_KEY) configured in your environment. The Skill runs local Python scripts that authenticate with these APIs to execute generation and editing workflows.

Multi-image composition merges several images into one coherent output. This Skill uses AI models to blend and integrate multiple source images while maintaining visual consistency and style alignment across the final result.

Yes, style transfer applies artistic effects to images, and product placement adds items to scenes automatically. Both run through the same AI-powered workflows, letting you transform visuals or insert products without manual design work.

Automating image generation removes manual design bottlenecks by letting you run text-to-image workflows programmatically via scripts. This Skill handles aspect ratio selection and model routing, making batch or triggered generation practical for product visuals, marketing assets, or mock-ups.