skills.rest
ElwinLiu
ElwinLiuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

baoyu-image-gen

Generate images from natural-language prompts using OpenAI and Google APIs.

Updated Jan 24, 2026
Search Tags:#OpenAI#multimodal#image-generation#generate#Google#prompt#aspect-ratio
One-click install
npx skills add https://github.com/ElwinLiu/agents --skill baoyu-image-gen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/ElwinLiu/agents/tree/main/skills/baoyu-image-gen
Command: npx skills add https://github.com/ElwinLiu/agents --skill baoyu-image-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ai, @ai-sdk/google, and includes scripts (resource) components.

What problem does it solve?

This Skill enables automated image generation from natural language prompts using official OpenAI and Google APIs, simplifying the creation of visuals for products, marketing, UI mockups, and other creative assets.

Core Features & Use Cases

  • Text-to-image generation with OpenAI and Google multimodal models.
  • Support for aspect ratio handling and quality presets to tailor outputs for social media, websites, and presentations.
  • Optional reference images for style transfer or editing in Google multimodal workflows.

Quick Start

Example: npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A futuristic city skyline" --image 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 images from text prompts using AI APIs?▼

Text-to-image generation converts natural language descriptions into visual content using machine learning models. OpenAI and Google APIs automate this process, letting you create images programmatically by specifying a prompt, desired aspect ratio, and quality settings without manual design work.

Can I generate images with both OpenAI and Google APIs in one workflow?▼

Yes, this Skill supports both OpenAI and Google multimodal APIs, letting you select your preferred provider and model defaults. You can switch between them based on your needs for different image generation tasks.

What aspect ratios and quality options are supported for generated images?▼

The Skill handles aspect ratio configuration and quality presets tailored for different outputs—social media visuals, websites, presentations, and product mockups. You specify these parameters when running the prompt to match your target format.

How do I use reference images with Google's image generation?▼

Google's multimodal workflows support optional reference images for style transfer or editing. You provide a reference image alongside your text prompt to guide the visual direction of the generated output.

Does this Skill handle saving generated images to local files?▼

Yes, the Skill includes robust local file handling for output images. Generated images are automatically saved to your specified file path, making it easy to integrate into content creation pipelines.

Related Skills

Explore More Design & Creative Skills→
GPTtangGPTtang
4

image-gen

Generate images via OpenAI, Google, and DashScope APIs with text prompts.

Community
Intermediate
AcosmiAcosmi
6

image

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

Community
Advanced
haitao2016haitao2016

iterative-image-craft

Manage iterative game asset creation and refinement with Python scripts.

Community
Advanced
jykimjykim
49

image-generation-skill

Generate 1024x1024 images via DALL-E 3 for documents and slide decks.

Community
Advanced