baoyu-image-gen

Generate AI images from text prompts and reference images via CLI.

2|Updated Mar 23, 2026
One-click install
npx skills add https://github.com/neo-unicorn/neo-skills --skill baoyu-image-gen-neo-unicorn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/neo-unicorn/neo-skills/tree/main/baoyu-image-gen
Command: npx skills add https://github.com/neo-unicorn/neo-skills --skill baoyu-image-gen-neo-unicorn

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill centralizes and automates AI image generation across multiple providers so users can produce high-quality images, edits, and reference-based modifications without manually handling different APIs and formats.

Core Features & Use Cases

  • Multi-provider support: Works with Google Gemini, Google Imagen, OpenAI GPT Image, DashScope (阿里通义万象), and Replicate.
  • Reference image edits & prompts: Accepts reference images for multimodal edits, supports aspect ratios, explicit sizes, and quality presets.
  • Configurable preferences and model resolution: Loads EXTEND.md or environment variables, allows CLI overrides, and displays chosen provider/model before generation.
  • Robust CLI workflow: Validates inputs, auto-detects providers, retries transient failures, supports sequential and optional parallel batch generation, and writes output PNG files.

Quick Start

Generate a 2k landscape image of a futuristic city using the Google provider and save it as out.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 AI images from text prompts across different providers like OpenAI and Google Gemini?

This Skill centralizes AI image generation across providers like OpenAI and Google Gemini, allowing you to generate images from text prompts via a CLI workflow that auto-detects the provider and outputs PNG files.

Can I use a reference image for multimodal edits with DashScope?

Yes, you can use a reference image for multimodal edits with DashScope. The CLI workflow accepts reference images alongside text prompts to perform edits and generate new output PNG files.

Does the CLI image generation workflow support batch processing and retries?

Yes, the CLI image generation workflow supports sequential and optional parallel batch generation. It validates inputs and applies retry-on-failure behavior to handle transient API errors during image generation.

Do I need to manually specify the model when generating images through the CLI?

No, you do not need to manually specify the model. The workflow features provider auto-detection, loads preferences from EXTEND.md or environment variables, and displays the chosen provider and model before generating images.

What is the best way to handle aspect ratios and explicit sizes for AI image generation?

The best way to handle aspect ratios and explicit sizes is using a CLI workflow that accepts these parameters as overrides, applying them alongside quality presets to the output PNG files generated by providers like Replicate.