skills.rest
zhangdszq
zhangdszqCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

baoyu-image-gen

Generate images via OpenAI, Google Gemini, or DashScope with prompts and optional reference images.

1|2|Updated Feb 28, 2026
Search Tags:#ai#multimodal#image-generation#providers#prompt#reference-images
One-click install
npx skills add https://github.com/zhangdszq/vk-skills --skill baoyu-image-gen-zhangdszq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/zhangdszq/vk-skills/tree/main/baoyu-image-gen
Command: npx skills add https://github.com/zhangdszq/vk-skills --skill baoyu-image-gen-zhangdszq

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

AI-based image generation across multiple providers (OpenAI, Google Gemini, and DashScope) can be complex to orchestrate; this Skill unifies those workflows into a single, cohesive tool.

Core Features & Use Cases

  • Multi-provider image generation: generate visuals using OpenAI, Google Gemini, or DashScope without switching tools.
  • Prompt + controls: support prompts with aspect ratios and output size/quality, plus optional reference images to guide results.
  • Real-world scenarios: accelerate marketing visuals, UI/UX mockups, and creative concepting with consistent outputs.

Quick Start

Provide a prompt and an output path to generate an image.

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 images using multiple AI providers like OpenAI and Gemini from one tool?▼

Multi-provider image generation coordinates OpenAI, Google Gemini, and DashScope APIs within a single unified skill. It automatically detects the provider, applies model defaults, and manages error handling to produce a final image file from your prompt.

Can I use reference images to guide AI image generation across different platforms?▼

Yes, AI image generation supports optional reference images alongside text prompts to guide visual results. You can supply reference images while specifying aspect ratios and output sizes to achieve consistent, customized marketing or UI/UX mockups.

How do I configure environment variables for parallel image generation across providers?▼

Parallel image generation accepts configuration via environment variables and an EXTEND.md file to coordinate provider selection. This setup allows simultaneous requests to OpenAI, Google Gemini, and DashScope, applying specific model defaults and output sizes.

What is the best way to handle aspect ratios and output sizes for AI-generated marketing visuals?▼

Specify aspect ratios and output size parameters directly within your text prompt when generating marketing visuals. The skill processes these controls alongside provider auto-detection to deliver correctly formatted image files for your creative concepting.

Does DashScope work with OpenAI for unified multimodal image generation?▼

Yes, DashScope functions alongside OpenAI and Google Gemini for unified multimodal image generation. The skill orchestrates these distinct providers, applying individual model defaults and error handling to reliably output a generated image file.

Why does multi-provider image generation fail when environment variables are missing?▼

Multi-provider image generation requires valid environment variables and API configurations to select and authenticate providers. Missing configuration prevents the skill from coordinating provider defaults and executing parallel generation, causing image output failures.

Related Skills

Explore More Design & Creative Skills→
bahayonghangbahayonghang
16

gemini-image

Generate images from text prompts or reference images via the Gemini API.

Community
Basic
AcosmiAcosmi
6

image

Generate, edit, analyze, and convert images via configured vision models.

Community
Advanced
dmccrearydmccreary
90

microsim-generator

Route MicroSim creation requests to the best-matching specialized generator.

Community
Advanced
TTAWDTTTTAWDTT
5

imagegen

Generate and edit images via Google Gemini and OpenAI GPT-Image APIs.

Community
Intermediate