skills.rest
agentspace-so
agentspace-soOFFICIAL
Explore all skills by this author →
GitHub

ai-image-generation

Route text-to-image and image-to-image requests to RunComfy model endpoints.

31|9|Updated Apr 30, 2026
Search Tags:#typography#image generation#image editing#text-to-image#prompt routing#photoreal#runcomfy cli
One-click install
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill ai-image-generation-agentspace-so
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-image-generation
Source: https://github.com/agentspace-so/runcomfy-agent-skills/tree/main/ai-image-generation
Command: npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill ai-image-generation-agentspace-so

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the friction of choosing the right image model and crafting the correct input for generating or editing images.

Core Features & Use Cases

  • Unified text-to-image and edit routing: Converts requests like “make a picture” or “change the background” into the appropriate RunComfy model endpoint.
  • Model-specific prompting patterns: Ships guidance for high-performing approaches (e.g., typography-precise in-image text vs photoreal portraits).
  • Practical guardrails for safe execution: Uses a restricted allowed tool and emphasizes token handling, input boundaries, and download constraints.
  • Common use cases: Posters and multilingual headlines, photoreal product/portrait renders, and one-shot edits like background swaps or umbrella/color changes.

Quick Start

Ask the AI to generate a photoreal product poster with exact headline text using the ai-image-generation skill for RunComfy.

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 photoreal portrait and product images with exact typography?▼

To generate photoreal images with exact typography, this skill routes your text-to-image request to the appropriate RunComfy model endpoint, applying model-specific prompting patterns for precise in-image text and realistic renders.

How do I edit an existing image to change the background or colors?▼

To edit an existing image, the skill routes your image-to-image intent to the proper RunComfy endpoint, enabling one-shot edits like background swaps or color changes while optionally using grounded web references.

Do I need RunComfy CLI authentication to generate images?▼

Yes, you need authenticated RunComfy CLI usage to execute image generation, requiring deterministic JSON prompt inputs via the --input field and specifying an --output-dir to save the generated results.

What is the best way to create multilingual posters with in-image text?▼

The best way to create multilingual posters is using model-specific prompting patterns that ensure typography-precise in-image text, routing your request through the unified text-to-image generation workflow.

Can I use grounded web references for one-shot image edits?▼

Yes, you can optionally enable grounded web references when performing one-shot image edits like background changes, allowing the RunComfy model to use external context for modifying your images.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

ai-image-generation

Generate and edit images through RunComfy with automatic model selection.

Official
Advanced
michaelboedingmichaelboeding
24

video-generation

Generate AI videos from prompts and reference media via Vertex AI or AI Studio.

Community
Advanced
daniel-carreondaniel-carreon
13

replicate-integration

Generate images and manage predictions via the Replicate API.

Community
Intermediate
doany-aidoany-ai
5

ai-image-generation

Generate and edit images across multiple model endpoints via the RunComfy CLI.

Official
Advanced