AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, 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-imagine' skill offers AI-powered image generation capabilities, integrating multiple APIs such as OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, and Replicate. This skill solves the problem of generating images from text-based prompts, references, and even batch generation from saved prompt files. It supports sequential image generation by default, with the option for parallel batch processing to enable stable multi-image throughput, making it ideal for users who require efficient image generation from multiple prompts.
You can use the command `${BUN_X} {baseDir}/scripts/main.ts --prompt 'A cat' --image out.png` to generate a basic image based on a text prompt.
Yes, you can specify aspect ratios and image quality by using options like `--ar` for aspect ratio and `--quality` for quality, such as `--ar 16:9` and `--quality 2k`.
Yes, you can provide a reference image using the `--ref` option, such as `--ref source.png`, to guide the image generation process.
Batch mode allows you to generate multiple images simultaneously. You can use the `--batchfile` option with a JSON file containing multiple prompts and set the number of jobs with `--jobs`, like `--jobs 4`.
The skill requires the installation of 'bun' or 'npx', with dependencies including various image generation APIs, such as OpenAI and Replicate.
Quick Setup:
.claude/skills/Repository
jimliu/baoyu-skills