ai-image-generation

Generate and edit images through RunComfy with automatic model selection.

31|9|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill ai-image-generation-prime-skills
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-image-generation
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/ai-image-generation
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill ai-image-generation-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the complexity of choosing, configuring, and invoking image-generation models for text-to-image creation and image-to-image editing through RunComfy.

Core Features & Use Cases

  • Smart Model Routing: Selects suitable RunComfy models for typography, photorealism, speed, illustration, open-weights workflows, and multi-reference styling.
  • Image Creation and Editing: Supports text-to-image generation, identity-preserving edits, layout changes, background replacement, and model-specific refinement workflows.
  • Prompt and CLI Guidance: Provides documented prompting patterns, input schemas, model endpoints, output handling, authentication guidance, and troubleshooting information.
  • Use Case: Create a multilingual product poster with exact headline text, generate photorealistic campaign portraits, or produce multiple storyboard concepts for rapid iteration.

Quick Start

Ask the AI to generate or edit an image with RunComfy, specifying the subject, desired style, dimensions, references, or exact in-image text.

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 photorealistic images with exact text without manually configuring AI models?

Smart model routing automatically selects the suitable RunComfy model for typography or photorealism, eliminating manual configuration. You simply specify the subject, desired style, dimensions, and exact in-image text.

Can I use image-to-image editing to change backgrounds and layouts while preserving identity?

Yes, image-to-image editing supports identity-preserving edits, layout changes, and background replacement. It applies model-specific refinement workflows through RunComfy to alter existing images while maintaining core visual identity.

Do I need the RunComfy CLI and authentication to create text-to-image AI art?

Yes, creating text-to-image AI art requires the RunComfy CLI, valid authentication, and model-specific JSON inputs. These prerequisites ensure secure handling of reference URLs and generated output files during the generation process.

What is the best way to rapidly iterate storyboard concepts using AI image generation?

The best way to rapidly iterate storyboard concepts is using the smart model routing feature for speed and illustration. It handles multiple reference styling and open-weights workflows to produce varied concepts quickly.

Why does my AI image generation workflow require safe handling of reference URLs?

Safe handling of reference URLs is required to securely process multi-reference styling inputs during image-to-image editing. This ensures that external assets are managed correctly within the RunComfy CLI environment.