skills.rest
runcomfy-com
runcomfy-comOFFICIAL
Explore all skills by this author →
Website𝕏@runcomfyaiGitHub

ai-image-generation

Generate and edit images from natural-language prompts via RunComfy endpoints.

12|2|Updated May 18, 2026
Search Tags:#image editing#AI art#model routing#generate#text-to-image#image-to-image#RunComfy
One-click install
npx skills add https://github.com/runcomfy-com/skills --skill ai-image-generation-runcomfy-com
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-image-generation
Source: https://github.com/runcomfy-com/skills/tree/main/ai-image-generation
Command: npx skills add https://github.com/runcomfy-com/skills --skill ai-image-generation-runcomfy-com

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of turning image ideas, prompts, and reference-based edits into high-quality generated images without manually picking and learning the right model endpoint.

Core Features & Use Cases

  • Text-to-image routing across 11+ models: Choose the best model automatically for photoreal portraits, typography, illustration, and fast ideation.
  • Image-to-image editing options: Support one-shot background/identity-preserving edits and precise single-instruction changes.
  • RunComfy CLI execution: Use a single workflow that classifies intent (t2i vs i2i) and invokes the correct runcomfy endpoint with the right JSON schema.

Quick Start

Tell your agent: generate an image of a small purple cat on a moss-covered stone at golden hour with shallow depth of field, using RunComfy to produce the output.

Frequently Asked Questions about ai-image-generation

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

FAQPage Schema
How do I generate AI art from text prompts without choosing a model manually?▼

Image-to-image editing supports one-shot background and identity-preserving edits, as well as precise single-instruction changes, by passing reference images with specific modification instructions to the routing workflow.

What is the best way to edit a reference image using AI models?▼

Image-to-image editing supports one-shot background and identity-preserving edits, as well as precise single-instruction changes, by passing reference images with specific modification instructions to the routing workflow.

Can I use natural language prompts for AI image generation?▼

The RunComfy workflow classifies your intent as either text-to-image or image-to-image and invokes the correct endpoint using a strict JSON schema with safe prompt handling boundaries.

How does model routing work for text-to-image and image-to-image tasks?▼

The RunComfy workflow classifies your intent as either text-to-image or image-to-image and invokes the correct endpoint using a strict JSON schema with safe prompt handling boundaries.

Do I need to manually select an AI model for different image styles?▼

You can generate high-quality images by simply telling your agent to produce the output using RunComfy, without manually picking or learning the right model endpoint.

What are the limitations of using automated model routing for image generation?▼

Automated model routing requires strict JSON input schemas and execution via runcomfy run, meaning you must adhere to safe prompt handling boundaries and supported vendor endpoints for successful generation.

Related Skills

Explore More Design & Creative Skills→
runcomfy-comruncomfy-com
12

flux-2-klein

Generate images from prompts via the RunComfy Model API using Flux 2 Klein variants.

Official
Intermediate
syncfusionsyncfusion
3

syncfusion-react-image-editor

Automate image editing workflows for React applications with Syncfusion.

Official
Advanced
prime-skillsprime-skills
31

ai-image-generation

Generate and edit images through RunComfy with automatic model selection.

Official
Advanced
aayushsoamaayushsoam
1

ascii-art

Convert text and images into ASCII art using pyfiglet, cowsay, and boxes.

Community
Advanced