skills.rest
Functionhx
FunctionhxCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

image-generation

Generate and edit images from text prompts using multiple AI providers.

Updated Jun 21, 2026
Search Tags:#image generation#image editing#AI art#AI models#text-to-image
One-click install
npx skills add https://github.com/Functionhx/weiyang --skill image-generation-functionhx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/Functionhx/weiyang/tree/main/CowAgent/skills/image-generation
Command: npx skills add https://github.com/Functionhx/weiyang --skill image-generation-functionhx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, Pillow, base64, uuid, re, pathlib, urllib, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation and editing of images based on text descriptions, using various AI models to generate visual content.

Core Features & Use Cases

  • Image Generation: Automatically generate images from text prompts using OpenAI, Gemini, Seedream, Qwen, and MiniMax models.
  • Image Editing: Modify existing images using AI to add effects, change elements, or combine multiple images.
  • Use Case: Imagine you want to create a sci-fi illustration or combine multiple photos. This Skill can take a text description and produce the corresponding visual.

Quick Start

Generate an image from the prompt 'An abstract painting of a futuristic cityscape at night' using the default model.

Frequently Asked Questions about image-generation

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

FAQPage Schema
How do I generate images from text using AI models?▼

To generate images from text, this Skill processes your text prompts using AI models like OpenAI, Gemini, Seedream, Qwen, and MiniMax to produce corresponding visual content automatically. It handles the image creation within specified size and quality parameters.

Can I edit existing images or combine multiple photos with AI?▼

Yes, you can edit existing images or combine multiple photos using AI. This Skill modifies images by adding effects or changing elements based on your text prompts, leveraging supported providers to handle the image editing tasks.

Do I need API keys to use text-to-image generation?▼

Yes, you need API keys for different providers to use text-to-image generation. The Skill requires valid API keys for AI providers like OpenAI, Gemini, Seedream, Qwen, and MiniMax to authenticate and process your image creation requests.

What is the best way to create a sci-fi illustration from a text description?▼

The best way to create a sci-fi illustration from a text description is to provide a detailed text prompt to the default AI model. The Skill automates the creation of visual content, taking your text description and producing the corresponding sci-fi image.

Does image editing with AI work with default models or do I need to specify one?▼

Image editing with AI works with both user-specified or default models. You can modify existing images by letting the Skill handle the task using a default model, or you can specify a particular AI provider like OpenAI or Gemini for customized results.

Related Skills

Explore More Content & Communication Skills→
flashfoxerflashfoxer

baoyu-image-gen

Generate images from text or reference images via multiple AI APIs.

Community
Advanced
pacphipacphi
14

imagemagick

Automate image format conversion, resizing, and batch processing via ImageMagick MCP.

Community
Advanced
lxh755818-botlxh755818-bot

minimax-image-generation

Generate images via the MiniMax Image-01 API using Python urllib.

Community
Advanced
AceDataCloudAceDataCloud
13

seedream-image

Generate and edit images from text prompts via the AceDataCloud API.

Official
Intermediate