jimliu/baoyu-skills@baoyu-image-gen

Generate AI images via DALL-E 3, Imagen 3, Tongyi Wanxiang, and Replicate.

2.0k|267|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/openakita/openakita --skill jimliu-baoyu-skills-baoyu-image-gen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jimliu/baoyu-skills@baoyu-image-gen
Source: https://github.com/openakita/openakita/tree/main/skills/baoyu-image-gen
Command: npx skills add https://github.com/openakita/openakita --skill jimliu-baoyu-skills-baoyu-image-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, Pillow, openai, google-genai, dashscope, replicate, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of AI-generated images from text descriptions, overcoming the limitations of single-provider tools and complex prompt engineering.

Core Features & Use Cases

  • Multi-Provider Support: Leverages OpenAI DALL-E 3, Google Imagen 3, DashScope/Tongyi Wanxiang, and Replicate for diverse image generation capabilities.
  • Optimized Prompting: Provides guidance and strategies for crafting effective prompts tailored to each AI model.
  • Flexible Generation: Supports various aspect ratios, quality presets, and batch generation for efficient workflow.
  • Use Case: A marketing team needs a unique banner image for a social media campaign. They describe the concept, and the skill generates multiple options in different styles and aspect ratios, allowing them to choose the best fit.

Quick Start

Use the baoyu-image-gen skill to generate an image of a futuristic city at sunset with a 16:9 aspect ratio.

Frequently Asked Questions about jimliu/baoyu-skills@baoyu-image-gen

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

FAQPage Schema
How do I generate AI images using multiple providers like DALL-E and Imagen?

AI image generation using multiple providers like DALL-E 3 and Imagen 3 is handled by a single skill that routes text descriptions to the selected model, applying optimized prompt engineering and supporting batch generation with various aspect ratios.

What's the best way to craft effective prompts for different AI art models?

Crafting effective prompts for AI art models requires tailored strategies provided by this skill, which automatically optimizes text descriptions for each specific provider like DALL-E 3, Imagen 3, and Replicate to ensure high-quality visual content generation.

Can I generate images in specific aspect ratios and quality presets for social media?

Generating images in specific aspect ratios and quality presets is fully supported, allowing users to output visual content formatted for social media campaigns or marketing banners directly through the batch generation features.

Does this tool support batch image generation with Tongyi Wanxiang and Replicate?

Batch image generation with Tongyi Wanxiang and Replicate is supported, enabling users to request multiple visual content options simultaneously while leveraging provider-specific prompt engineering for optimized results.

Why use a multi-provider approach instead of a single AI image generator?

A multi-provider approach for AI image generation overcomes the limitations of single-provider tools by offering diverse visual content capabilities across DALL-E 3, Imagen 3, and Replicate, allowing users to select the best model for their specific prompt and quality needs.