What problem does it solve? Generating images through multiple AI provider APIs requires juggling different endpoints, authentication schemes, model names, and parameter formats. This Skill unifies text-to-image and reference-based image generation across ten providers behind one CLI with consistent flags, retries, and batch processing. ## Core Features & Use Cases - Multi-Provider Generation: Generate images through OpenAI GPT Image 2, Azure OpenAI, Google Gemini, OpenRouter, DashScope, Z.AI, MiniMax, Jimeng, Seedream, and Replicate with automatic provider detection from available API keys. - Reference-Image Identity Preservation: Pass reference images to supported providers with prompting guidance that preserves subject identity instead of synthesizing lookalikes. - Batch Parallel Generation: Run multi-image jobs from a JSON batch file with configurable worker counts, per-provider rate limits, and up to 3 automatic retries per image. - Use Case: A content team saves illustration prompts as Markdown files, builds a batch.json with build-batch.ts, and generates all article images in parallel through Replicate with a single command. ## Quick Start Ask the AI to generate an image of your subject using baoyu-imagine and save it to a specified output path, optionally naming a provider, model, or aspect ratio.
