baoyu-image-gen

Generate and edit images from text prompts across multiple provider APIs.

2|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill baoyu-image-gen-augustscl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/augustscl/awesome-xiawang-skills/tree/main/baoyu-image-gen
Command: npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill baoyu-image-gen-augustscl

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provide a unified, configurable CLI workflow to generate and edit images from text prompts and reference images across multiple provider APIs, removing the friction of switching providers, resolving models, and managing output settings.

Core Features & Use Cases

  • Multi-provider support: Works with Google (Gemini/Imagen), OpenAI (GPT Image), DashScope (阿里通义万象), and Replicate with consistent CLI behavior.
  • Flexible inputs: Accepts direct prompts, prompt files, and reference images for edits or multimodal generation.
  • Preferences & model management: Uses EXTEND.md and environment variables to persist default provider, model, quality, aspect ratio, and image size with clear precedence rules.
  • Robust execution: Validates inputs, selects providers automatically, retries transient failures once, supports sequential default generation and optional parallel batches for large jobs.
  • Use case: Quickly produce cover illustrations, social graphics, or batch art assets with consistent sizing and provider fallback.

Quick Start

Use the baoyu-image-gen skill to generate a 2k aspect 16:9 image from the prompt "A serene mountain lake at sunset" and save it as output.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 high-quality images from text prompts across multiple provider APIs?

Generate high-quality images from text prompts by using a unified CLI workflow that supports OpenAI, Google Gemini, DashScope, and Replicate APIs, automatically resolving models and managing output settings like aspect ratios and quality presets.

Can I use reference images to edit or guide text-to-image generation?

Yes, you can use reference images for edits or multimodal text-to-image generation, passing them alongside direct prompts or prompt files to guide the visual output across supported providers.

How do I configure default provider, model, and aspect ratio for batch image generation?

Configure default provider, model, quality, aspect ratio, and image size by setting preferences in EXTEND.md and environment variables, which apply clear precedence rules for consistent batch generation.

Does this CLI workflow support parallel batch generation for large image jobs?

The CLI workflow supports sequential default generation and optional parallel batches for large jobs, automatically retrying transient failures once to ensure robust execution across provider APIs.

What API keys do I need to generate images with OpenAI, Google Gemini, DashScope, or Replicate?

You need appropriate API keys for your selected provider to generate images, resolving provider selection and model resolution automatically via CLI, EXTEND.md, or environment variables.

How do I resolve model selection when switching between OpenAI and Google Gemini for image generation?

Model resolution is handled automatically via CLI, EXTEND.md, or environment variables, allowing seamless switching between OpenAI, Google Gemini, DashScope, and Replicate with consistent CLI behavior.