skills.rest
bozhouDev
bozhouDevCOMMUNITY
Explore all skills by this author →
GitHub

image-gen

Generate images via OpenAI, Google Gemini, and DashScope with optional Cloudflare R2 upload.

76|6|Updated Mar 12, 2026
Search Tags:#image#ai#generate#providers#aspect-ratio#reference-images#r2-upload
One-click install
npx skills add https://github.com/bozhouDev/bozhou-skills --skill image-gen-bozhoudev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/bozhouDev/bozhou-skills/tree/main/image-gen
Command: npx skills add https://github.com/bozhouDev/bozhou-skills --skill image-gen-bozhoudev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

AI-driven image generation across multiple providers with optional Cloudflare R2 upload, enabling quick generation of visuals without juggling APIs.

Core Features & Use Cases

  • Supports text-to-image generation via OpenAI, Google Gemini, and DashScope.
  • Allows reference images, aspect ratio controls, and optional Cloudflare R2 uploads for distribution.
  • Use cases include concept art, product visuals, marketing assets, and rapid visual prototyping.

Quick Start

Run the image-gen script with your prompt, and specify the output image path.

Frequently Asked Questions about image-gen

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

FAQPage Schema
How do I generate AI images across multiple providers like OpenAI and Gemini?▼

AI image generation across multiple providers is handled by routing prompts to OpenAI, Google Gemini, or DashScope with automatic provider detection. You simply run the generation script with your prompt and specify an output path.

Can I use reference images and control the aspect ratio for AI image generation?▼

Reference images and aspect ratio controls are fully supported for AI image generation. You can supply reference images alongside text prompts and define specific aspect ratios to guide the visual output.

How do I upload AI generated images directly to Cloudflare R2?▼

Uploading AI generated images to Cloudflare R2 is supported as an optional built-in feature. Once configured, the script can automatically distribute and upload your generated visuals to your R2 storage.

Do I need API keys to use OpenAI, Gemini, and DashScope for text-to-image generation?▼

API keys are required for text-to-image generation across OpenAI, Gemini, and DashScope. The script workflow utilizes environment-based key loading to securely authenticate requests to your chosen provider.

Can I generate images in parallel across different providers?▼

Parallel image generation across different providers is available upon request, while sequential generation is the default behavior. This allows you to optimize for speed when generating visuals across multiple APIs.

What is the best way to automate rapid visual prototyping with AI image generation?▼

Automating rapid visual prototyping is best achieved using script-based workflows that validate inputs and process text-to-image prompts sequentially. This approach quickly yields concept art and marketing assets.

Related Skills

Explore More Design & Creative Skills→
GPTtangGPTtang
4

image-gen

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

Community
Intermediate
abcnutsabcnuts
60

file-upload-system

Automate S3/R2 file uploads with presigned URLs and image optimization.

Community
Intermediate
yikartyikart
24.9k

editing-images

Overlays logos and QR codes onto images using the Sharp library.

Official
Intermediate
jackspacejackspace
16

multi-repository-orchestrator

Orchestrate synchronized branching and batch commits across multiple Git repositories.

Community
Advanced