What problem does it solve? Generating images through multiple AI image APIs requires juggling different endpoints, model names, size rules, and credential formats. This Skill unifies ten providers behind one CLI so you can generate, edit, and batch-produce images without learning each API's quirks. ## Core Features & Use Cases - Multi-provider text-to-image: Generate images through OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI, MiniMax, Jimeng, Seedream, or Replicate with automatic provider detection from available API keys. - Reference-image editing: Pass reference images for supported providers to perform edits, style transfer, or subject-consistent generation. - Batch parallel generation: Run multi-image jobs from a JSON batch file with configurable worker counts, per-provider rate limits, and automatic retries. - Use Case: You have an article outline with saved prompt files for ten illustrations. Use the build-batch script to assemble a batch.json, then run batch mode to generate all images in parallel with throttling and per-image retry. ## Quick Start Ask the agent to generate an image of your subject and save it to a chosen file, optionally specifying a provider, aspect ratio, or quality level.
