skills.rest
guanyang
guanyangCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

baoyu-imagine

Generate images from text prompts across multiple providers.

947|163|Updated Jan 13, 2026
Search Tags:#debugging#cli#ai#prompts#image-generation#batch-processing#provider-agnostic
One-click install
npx skills add https://github.com/guanyang/open-agent-hub --skill baoyu-imagine-guanyang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-imagine
Source: https://github.com/guanyang/open-agent-hub/tree/main/skills/baoyu-imagine
Command: npx skills add https://github.com/guanyang/open-agent-hub --skill baoyu-imagine-guanyang

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This AI skill orchestrates image generation across multiple providers from prompts, enabling unified workflows for visuals across backends.

Core Features & Use Cases

  • Generate images from text prompts using Google, OpenAI, Azure, OpenRouter, DashScope, Z.A.I, MiniMax, Replicate, and more.
  • Support batch generation via saved prompts/outlines with provider-specific sizing, aspect ratios, and reference handling.
  • Manage prompts, references, and outputs across diverse models, with config extension via EXTEND.md and first-time setup flows.

Quick Start

Provide a text prompt and optional reference images to generate images across supported providers.

Frequently Asked Questions about baoyu-imagine

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

FAQPage Schema
How do I generate images from text prompts across multiple AI providers?▼

Multi-provider AI image generation from prompts automates visual creation across backends like Google, OpenAI, Azure, and Replicate. You provide a text prompt and optional reference images, and the skill handles provider-specific sizing and outputs.

Can I use reference images for AI image generation with different models?▼

Yes, reference-image support allows you to ingest existing images into the generation workflow. The skill manages reference ingestion alongside prompt construction to produce consistent visuals across diverse models.

How do I process batch image generation from saved prompts?▼

Batch processing automates image generation from saved prompts and outlines. The skill handles batch file processing, applying provider-specific aspect ratios and sizing rules to each item in the batch.

Does this image generation tool work with OpenRouter and DashScope?▼

Yes, the tool supports provider-agnostic image generation with OpenRouter, DashScope, Z.A.I, MiniMax, and others. It manages prompts and outputs across these diverse models using a unified workflow.

How do I configure default settings for cross-provider prompt workflows?▼

You configure defaults and first-time setup flows using config extension via EXTEND.md. This integration manages prompts, references, and outputs across diverse models within your generation workflows.

Related Skills

Explore More Software Engineering Skills→
lihanghanglihanghang

baoyu-image-gen

Generate images from text prompts across Google, OpenAI, DashScope, or Replicate.

Community
Advanced
ISAQQSAIISAQQSAI

image-cog

Generate and edit AI images with CellCog for design pipelines.

Community
Advanced
markpittmarkpitt
22

genaiscript

Create and orchestrate GenAIScript scripts for LLM prompts and AI workflows.

Community
Advanced
ViewWayViewWay

AI Image Generation

Generate and edit images across GPT Image, Gemini, Imagen, and FLUX.

Community
Advanced