baoyu-image-gen

Generate images from text prompts using OpenAI, Gemini, and DashScope APIs.

Updated Feb 15, 2026

Search Tags:#image generation #openai #text-to-image #ai art #dashscope #google gemini

Ready to run

npx skills add https://github.com/sksdwl/shudan --skill baoyu-image-gen-sksdwl

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/sksdwl/shudan/tree/main/workspace/skills/baoyu-image-gen
Command: npx skills add https://github.com/sksdwl/shudan --skill baoyu-image-gen-sksdwl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of images from text descriptions using advanced AI models, eliminating the need for manual design or complex software.

Core Features & Use Cases

Text-to-Image Generation: Create unique images from detailed text prompts.
Multi-Provider Support: Leverages OpenAI, Google (Gemini), and DashScope (Aliyun Tongyi Xiang) APIs for diverse results.
Reference Image Input: Modify or generate images based on existing visual references.
Use Case: Generate a series of marketing images for a new product launch, each with a specific aspect ratio and style, directly from a product description.

Quick Start

Use the baoyu-image-gen skill to generate an image of a cat with the output saved to cat.png.

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 prompts using OpenAI or Google Gemini?▼

To generate images from text prompts, you provide a text description to the Skill, which then uses OpenAI, Google Gemini, or DashScope APIs to produce the image and save it to a specified file like cat.png.

Can I use a reference image to modify or generate new AI art?▼

Yes, you can use existing visual references as input. The Skill supports reference image input to modify or generate new images based on those existing visuals alongside text prompts.

How do I customize the aspect ratio for text-to-image generation?▼

You customize the aspect ratio by specifying your desired dimensions in the prompt instructions. The Skill supports aspect ratio customization to ensure the generated image fits specific layout requirements.

Do I need API keys to use DashScope and Gemini for AI image generation?▼

Yes, you need valid API keys. The Skill leverages OpenAI, Google Gemini, and DashScope APIs for processing, requiring you to configure your credentials in the EXTEND.md preference file.

What is the best way to automate generating marketing images with different styles?▼

The best way to automate marketing image generation is using this Skill's deterministic scripts. You can generate a series of images with specific aspect ratios and styles directly from a product description.

Why does my text-to-image generation task fail to execute deterministically?▼

Text-to-image generation tasks may fail if the preference configuration in EXTEND.md is incorrect or if the API credentials for OpenAI, Gemini, or DashScope are missing or invalid.