skills.rest
tentacle-pro
tentacle-proCOMMUNITY
Explore all skills by this author →
GitHub

baoyu-image-gen

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

4|1|Updated Mar 2, 2026
Search Tags:#cli#ai#openai#image-generation#replicate#dashscope#google-gemini
One-click install
npx skills add https://github.com/tentacle-pro/skills --skill baoyu-image-gen-tentacle-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-image-gen
Source: https://github.com/tentacle-pro/skills/tree/main/baoyu-image-gen
Command: npx skills add https://github.com/tentacle-pro/skills --skill baoyu-image-gen-tentacle-pro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Generating high-quality images from text prompts and reference images can be fragmented across different provider APIs, CLI tools, and model conventions, making it hard for creators and developers to produce consistent outputs quickly. This Skill unifies provider selection, model resolution, aspect ratio handling, quality presets, reference-image editing, and output file management into a single CLI-driven workflow so users can generate or batch-produce images reliably.

Core Features & Use Cases

  • Multi-provider support: Works with Google (Gemini/Imagen), OpenAI (GPT Image / DALL·E), DashScope (阿里通义万象), and Replicate with provider auto-detection.
  • Reference images and edits: Accepts reference images for multimodal edits when supported (Google multimodal, OpenAI GPT Image edits, Replicate).
  • Flexible sizing & aspect ratios: Aspect ratio parsing, quality presets (normal/2k), and provider-specific size mappings.
  • Batch and single-image workflows: Sequential default generation with optional parallel/concurrent generation for large batches; retries and polling for robustness.
  • Use Case: Produce a 2K cover illustration for a blog post, edit an existing image with a prompt and mask, or generate a batch of thumbnails across providers while saving outputs to disk.

Quick Start

Generate a high-resolution 16:9 illustration of "a futuristic city at dusk" and save it to out.png using the baoyu-image-gen skill with your preferred provider and API key.

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 across different AI providers like OpenAI and Google Gemini?▼

You can generate images across OpenAI, Google, DashScope, and Replicate by running a CLI workflow that unifies provider selection, aspect ratio handling, and quality presets, requiring the respective provider API keys to produce outputs.

Can I use reference images for multimodal edits with this image generation CLI?▼

Reference images are supported for multimodal edits when using Google, OpenAI GPT Image, and Replicate, allowing you to modify existing images using text prompts and masks directly through the command line.

What do I need to batch generate AI images via the command line?▼

Batch image generation requires provider API keys and supports sequential or concurrent processing, utilizing built-in retry and polling mechanisms to reliably save multiple generated images to disk.

Does this AI image generation tool support specific aspect ratios and 2K quality presets?▼

The tool includes aspect ratio parsing and quality presets like normal and 2K, mapping provider-specific sizes to ensure generated images match your required dimensions and resolution.

What is the best way to manage different API keys for AI image generation across providers?▼

Managing API keys involves setting environment variables such as OPENAI_API_KEY, GOOGLE_API_KEY, DASHSCOPE_API_KEY, and REPLICATE_API_TOKEN, which the CLI uses for provider auto-detection and authentication.

Are there limitations when using DashScope or Replicate for image generation?▼

Provider auto-detection requires valid API keys for each service, and reference image edits are limited to Google, OpenAI, and Replicate, meaning DashScope currently supports single-image generation without multimodal reference inputs.

Related Skills

Explore More Design & Creative Skills→
XY121718XY121718
101

baoyu-image-gen

Generate images via OpenAI, Google Gemini, DashScope, and Replicate APIs.

Community
Intermediate
frostantfrostant
42

image-enhancer

Upscale resolution, reduce artifacts, and enhance sharpness in images.

Community
Intermediate
shenxingyshenxingy
8

banana

Generate and edit images via prompt-engineered Gemini Nano Banana requests.

Community
Advanced
guanyangguanyang
947

baoyu-image-gen

Generate images across multiple AI providers from a single prompt.

Community
Advanced