image-gen

Generate images from text prompts and reference images via multiple providers.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/dy9759/SkillCollection --skill image-gen-dy9759
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/dy9759/SkillCollection/tree/main/skills/image-gen
Command: npx skills add https://github.com/dy9759/SkillCollection --skill image-gen-dy9759

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, cryptography, and includes scripts (resource) components.

What problem does it solve?

This Skill removes the friction of producing high-quality images from prompts or reference pictures by orchestrating provider selection, secure API key handling, generation, and insertion into WPS notes.

Core Features & Use Cases

  • Secure API key management with AES encryption and note-based storage that derives decryption keys from device ID, note ID, and provider.
  • Unified generation across OpenRouter, DashScope (Aliyun), Ark (Volcengine), and Google Gemini with fixed, validated model names and provider-specific image handling.
  • Supports both text-to-image and image-to-image workflows, automatic saving of outputs, optional CLI integration, and clear user prompts for inserting images into WPS notes.

Quick Start

Request a photorealistic 16:9 image of a futuristic city at dusk from a text prompt and save the generated image into the current WPS note.

Frequently Asked Questions about image-gen

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

FAQPage Schema
How do I generate images from text prompts and insert them into WPS notes?

To generate images from text prompts into WPS notes, use this Skill to send requests via OpenRouter or Google Gemini and save the generated image directly into your current note.

Can I use a reference image for image-to-image generation with Google Gemini?

Yes, you can use a reference image for image-to-image generation with Google Gemini. The Skill supports provider-specific image handling to transform existing pictures based on your text prompts.

How does secure API key management work for text-to-image generation in WPS notes?

Secure API key management uses AES encryption to store keys in WPS notes. Decryption keys are derived uniquely from your device ID, note ID, and the specific provider being used.

Do I need httpx and cryptography dependencies to run text-to-image scripts in WPS?

Yes, you need the httpx and cryptography dependencies to execute text-to-image scripts. Httpx handles network calls to image providers, while cryptography enables secure AES API key encryption.

What is the best way to generate images across multiple providers like DashScope and Ark?

The best way to generate images across multiple providers like DashScope and Ark is using this Skill's unified generation interface, which applies fixed, validated model names for consistent results.