AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
Detected risks:
The `baoyu-image-gen` skill provides a comprehensive AI-powered image generation solution, leveraging multiple APIs including OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, and Replicate. It allows users to generate images from text prompts, reference images, and saved prompt files while supporting customizable aspect ratios and batch processing. By automating the image creation process across diverse providers, it streamlines workflows for creative professionals, developers, and hobbyists who need rapid, high-quality visual content without manual design effort.
Key features of `baoyu-image-gen` include sequential and batch image generation, the ability to work with multiple providers and models, and support for provider-specific settings such as quality, image size, and batch limits. Users can specify reference images for style transfer or enhancement and configure default preferences through the EXTEND.md file. The skill also provides cross-platform scripts and runtime resolution, ensuring compatibility with macOS, Linux, Windows, and various shell environments, while automatically detecting available runtimes like `bun` or `npx`.
This skill is suitable for developers, designers, and content creators looking to integrate AI image generation into their projects or workflows. Typical use cases include generating concept art, illustrations, promotional images, or visual assets for applications and websites. It also benefits users managing multiple prompts or large-scale image generation tasks, thanks to its batch processing capabilities. However, users must complete the setup via EXTEND.md before generating images, ensuring consistent behavior and provider configuration.
You need to complete the initial setup by creating or loading an EXTEND.md file with your preferred provider, model, quality, and image settings. Once configured, you can run the scripts with your text prompts, reference images, and aspect ratios using the provided command-line options.
The skill supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, and Replicate, allowing you to select different models and providers for specific image generation needs.
Yes, the skill supports batch generation from saved prompt files. By default, generation is sequential, but you can enable parallel batch processing for multiple prompts to improve throughput.
Yes, the skill requires either `bun` or `npx` to execute the main scripts. If neither is installed, the skill will suggest installing `bun` for runtime resolution.
The skill provides scripts compatible with macOS, Linux, WSL, Git Bash, and PowerShell on Windows. It automatically resolves runtime commands and checks for the existence of EXTEND.md in project and user directories.
Quick Setup:
.claude/skills/Repository
jimliu/baoyu-skills