Does this skill support image-to-image generation?

Yes, when using Google's multimodal models, you can use the --ref flag to provide reference images that guide the generation process.

Which AI providers are supported by this skill?

The skill supports official APIs from both OpenAI (DALL-E models) and Google (Imagen and multimodal models).

Can I generate images with specific aspect ratios?

Yes, the skill supports various aspect ratios such as 16:9, 1:1, 4:3, and more using the --ar flag, which automatically maps to the closest supported provider dimensions.

How do I set up my API keys for image generation?

You can provide API keys via environment variables (OPENAI_API_KEY, GOOGLE_API_KEY) or by placing them in a .env file within your project or home directory.

What is the maximum resolution supported?

The skill includes a '2k' quality preset that targets 2048px for OpenAI and 2K image sizes for Google, ideal for covers and high-quality illustrations.

AI Image Generation Pipeline

Name: AI Image Generation Pipeline
Author: Jst-Well-Dan

byJst-Well-Dan

•

콘텐츠 관리

Generates professional-grade images using official OpenAI and Google APIs directly through the Claude Code interface.

The baoyu-image-gen skill enables seamless image creation within your development workflow by leveraging the power of OpenAI's DALL-E and Google's Imagen models. It moves beyond simple text-to-image prompts by offering granular control over aspect ratios, quality presets up to 2K, and multi-modal reference image support. Designed for developers and content creators, it provides a robust command-line interface and configuration system via EXTEND.md, allowing for automated asset generation, UI prototyping, and high-quality visual content creation without leaving the terminal.

주요 기능

01Advanced aspect ratio management including 16:9, 9:16, 4:3, and 2.35:1

02Support for multi-modal reference images with Google providers

03High-resolution quality presets (Normal and 2K) for various use cases

046 GitHub stars

05Flexible configuration through environment variables and local EXTEND.md files

06Dual provider support for OpenAI and Google Gemini/Imagen APIs

사용 사례

01Prototyping visual concepts using image-to-image reference workflows

02Automating the creation of blog and social media assets from Markdown prompt files

03Generating high-fidelity UI placeholders and hero images during frontend development

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jst-well-dan/skill-box baoyu-image-gen

For use in Claude.ai and ChatGPT

Download Skill