baoyu-image-gen

To generate images with prompts across multiple AI providers, this Skill orchestrates requests to OpenAI, Google Gemini, DashScope, and Replicate, handling text-to-image creation, reference images, and aspect ratios. It manages provider selection and saves the resulting image to your specified path.

Yes, AI image generation with reference images and aspect ratios is fully supported. The Skill applies your prompts and reference images to the selected provider, handling image sizes and output dimensions to produce visuals suitable for rapid prototyping and design workflows.

Yes, this image generation tool supports OpenAI, Google Gemini, DashScope, and Replicate. It provides a unified interface to orchestrate cross-provider image generation, ensuring consistent results from prompts across these different AI engines.

The best way to handle cross-provider image generation for UI mockups is using a unified orchestration tool. This Skill streamlines visual creation by applying prompts to multiple AI engines, supporting consistent style outputs and rapid prototyping for marketing visuals.

To save generated images and JSON metadata, the Skill loads preferences, selects a provider, applies prompts, and saves the resulting image to the specified output path. Optional JSON metadata can be included alongside the visual output.

When using prompt-files for text-to-image generation, the Skill processes the text to yield images from your selected AI engine. It handles aspect ratios and image sizes, but outputs depend on provider capabilities and the prompt structure provided.