What problem does it solve? Choosing the right image generation model for each request is difficult: photorealistic human photos need one engine, while illustrations, edits, and upscaling need another. This Skill automatically detects the type of image requested and routes it to the appropriate backend, so you get the right output without learning each model's quirks. ## Core Features & Use Cases - Automatic Model Routing: A decision matrix sends realistic human/influencer photos to ai-studio-image (Gemini 2.0 Flash) and art, illustration, editing, inpainting, background removal, and upscaling to stability-ai (SD3.5 Large). - Prompt Engineering per Model: Provides optimized prompt structures for each backend, including humanization layers for realistic photos and style/negative prompts for artistic generation. - Fallback Handling: If one backend fails (daily limits, insufficient credits), it retries with the other model or produces a detailed prompt for manual use. - Use Case: Ask for a LinkedIn headshot and get a humanized photo via Gemini; ask for a YouTube thumbnail and get a high-impact digital artwork via Stability AI ultra mode. ## Quick Start Ask the assistant to generate an image, for example: create a professional LinkedIn headshot photo of a person in a blue suit with studio lighting.
