baoyu-image-gen

Generate images from text or reference images via multiple AI APIs.

Updated May 1, 2026
One-click install
npx skills add https://github.com/flashfoxer/openclaw-my-skills --skill baoyu-image-gen-flashfoxer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/flashfoxer/openclaw-my-skills/tree/main/baoyu-image-gen
Command: npx skills add https://github.com/flashfoxer/openclaw-my-skills --skill baoyu-image-gen-flashfoxer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun, npx, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of generating images using a variety of AI APIs, providing a seamless and efficient way to create images from text descriptions or reference images.

Core Features & Use Cases

  • Text-to-Image Generation: Convert text descriptions into images using various AI models.
  • Reference Image Editing: Modify existing images with different styles or elements.
  • Aspect Ratio and Size Customization: Adjust the aspect ratio and size of the generated images.
  • Batch Generation: Generate multiple images in parallel for efficient throughput.
  • Use Case: If you need to create a series of promotional images for a product, you can use this Skill to generate multiple images from a batch file containing text descriptions and reference images.

Quick Start

Generate an image from a text description: use baoyu-image-gen to generate an image from "A landscape with mountains and a lake" with reference image "mountains-ref.jpg" and aspect ratio 16:9.

Frequently Asked Questions about baoyu-image-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text descriptions using multiple AI APIs?

You can generate images from text descriptions by routing your prompts to multiple AI APIs like OpenAI, Google, DashScope, and Replicate. Simply provide a text prompt and select your desired provider to get the generated image.

Can I use a reference image to modify existing pictures with AI?

Yes, you can modify existing pictures by providing a reference image file alongside your text description. The AI APIs use the reference image to apply different styles or elements while generating the new output.

What is the best way to batch generate multiple AI images in parallel?

Batch generation of multiple AI images is handled by processing a batch file containing your text descriptions and reference images. This allows you to generate multiple images in parallel for efficient throughput using your selected AI APIs.

Do I need API keys to use different text-to-image generation providers?

Yes, you need appropriate API keys for the selected providers to perform text-to-image generation. You must supply the correct credentials for APIs like OpenAI, Azure OpenAI, MiniMax, or Z.AI to authenticate your image generation requests.

Does this image generation tool support custom aspect ratios and sizes?

Yes, this image generation tool supports custom aspect ratios and sizes. You can adjust the aspect ratio, such as specifying 16:9, and customize the output size to fit your specific formatting needs when generating images from text or reference images.