baoyu-image-gen

To generate AI images from text prompts, provide a natural-language description and a target filename. The skill handles provider routing, model selection, validation, and deterministic saving of the final image file directly to your project folder.

Yes, you can use one or more reference images to guide edits and multimodal generation. This functionality is supported when the chosen API provider allows image-to-image or multimodal workflows.

Yes, the skill supports provider-aware API routing across major platforms including OpenAI, Google, and Dashscope. It automatically loads environment preferences and applies model overrides for the selected provider.

You can control aspect ratios, size, quality, and image counts for consistent production use. This flexible output control ensures your generated marketing visuals match specific layout ratios and production requirements.

The skill automatically manages provider-aware API routing, environment loading, validation, and retries for you. This removes the friction of manual API handling when generating concept art across major platforms.

Provider-aware API routing is needed because different platforms support varying features like reference image editing and specific output sizes. It ensures the correct model is queried with proper validation and deterministic file saving.