skills.rest
zephyrwang6
zephyrwang6COMMUNITY
Explore all skills by this author →
GitHub

baoyu-image-gen

Generate AI images from text prompts and reference images across OpenAI, Google, and DashScope.

14|4|Updated Mar 31, 2026
Search Tags:#image generation#openai#text-to-image#reference images#dashscope#google gemini#aspect ratio
One-click install
npx skills add https://github.com/zephyrwang6/allSkills --skill baoyu-image-gen-zephyrwang6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/zephyrwang6/allSkills/tree/main/baoyu-image-gen
Command: npx skills add https://github.com/zephyrwang6/allSkills --skill baoyu-image-gen-zephyrwang6

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes the friction of generating high-quality images by turning simple prompts, prompt files, and reference images into finished outputs without manual editing.

Core Features & Use Cases

  • Multi-provider generation: Create images through OpenAI, Google, or DashScope with automatic provider selection or explicit overrides.
  • Prompt and reference support: Generate from a text prompt, combine multiple prompt files, or guide edits with reference images when the provider supports it.
  • Production controls: Adjust aspect ratio, size, quality, model, and image count for tasks like concept art, product mockups, social visuals, and illustration drafts.

Quick Start

Use the baoyu-image-gen skill to create an image from your prompt and save it to the output path you specify.

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 using OpenAI or Google?▼

Generate AI images from text prompts by submitting your desired description and selecting either OpenAI or Google as the provider. The skill processes the text prompt, applies aspect ratio and quality controls, and saves the finished visual output directly to your specified path.

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

Reference images can guide text-to-image generation when using a supported provider. You supply the source text alongside the reference image, and the skill applies the visual guidance to edit and generate the final output image.

What is the best way to batch generate concept art from multiple prompt files?▼

Batch generate concept art by combining multiple prompt files into a single workflow. The skill processes the prompt-file driven generation in sequence, applying deterministic output saving with retry and validation logic to ensure all images are produced.

Does this image generation skill support DashScope and aspect ratio controls?▼

DashScope is fully supported as a provider for image generation, alongside OpenAI and Google. The skill includes explicit aspect ratio, size, and quality controls, allowing you to tailor the output dimensions for product mockups or social visuals.

Do I need an API key to create images from text and reference images?▼

An API key is required to authenticate with your chosen provider and create images from text. The skill uses API key-based provider selection to route generation requests to OpenAI, Google, or DashScope automatically.

Related Skills

Explore More Design & Creative Skills→
tentacle-protentacle-pro
4

baoyu-image-gen

Generate single or batch images from text prompts and reference images via CLI.

Community
Advanced
OrionUEOrionUE
16

splash-image-conversion

Convert source images into cropped Unreal Engine splash PNG and BMP assets.

Official
Intermediate
superfhpsuperfhp

baoyu-infographic

Generate custom infographics from text using selected layouts and styles.

Community
Intermediate
DaddyElonMusk69DaddyElonMusk69

stable-diffusion-image-generation

Generate and modify images from text prompts using HuggingFace Diffusers.

Community
Advanced