ai-image-generation
Generate RunComfy Images from Prompts
Choosing image models and command syntax slows creative work. This skill routes generation and edits to RunComfy models with practical prompt guidance.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ai-image-generation" from https://skillstore.io/skills/runcomfy-com-ai-image-generation.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-ai-image-generation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "ai-image-generation". Generate a fast moodboard set for a ceramic mug campaign.
Expected outcome:
- Recommended Nano Banana 2 for quick 4-up exploration.
- Suggested a concise product prompt with warm light, top-down framing, and draft resolution.
- Directed output to a local project folder for review.
Using "ai-image-generation". Create a poster with an exact multilingual headline.
Expected outcome:
- Recommended GPT Image 2 because the request depends on accurate in-image text.
- Used layout language for headline placement, script handling, and aspect ratio.
- Flagged that each language should be generated as a separate pass.
Using "ai-image-generation". Edit an existing portrait while preserving identity.
Expected outcome:
- Recommended Nano Banana 2 Edit for identity-preserving image-to-image work.
- Structured the prompt with preservation goals first and the requested background change last.
- Kept web search disabled unless the user explicitly requested real-world grounding.
Security Audit
SafeThe static findings are overwhelmingly Markdown formatting, command examples, catalog links, and placeholder URLs in SKILL.md. I found no prompt-injection attempt, hidden install script, credential exfiltration, or malicious filesystem behavior. The skill still depends on the RunComfy CLI and external RunComfy services, which are disclosed in the documentation.
Risk Factors
⚙️ External commands (122)
🌐 Network access (51)
📁 Filesystem access (5)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/runcomfy-com-ai-image-generation/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/runcomfy-com-ai-image-generation?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/runcomfy-com-ai-image-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runcomfy-com-ai-image-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/runcomfy-com-ai-image-generation.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
runcomfy-com. (2026). ai-image-generation security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-ai-image-generation/audits/4BibTeX citation
@techreport{runcomfy-com-runcomfy-com-ai-image-generation-2026,
author = {runcomfy-com},
title = {ai-image-generation security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/runcomfy-com-ai-image-generation/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-image-generation security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "runcomfy-com"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/runcomfy-com-ai-image-generation/audits/4"
identifiers:
- type: other
value: "skillstore:runcomfy-com-ai-image-generation:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
23 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
tool-belt-ai-image-generation
2026-08-21
runcomfy-com-ai-image-generation
2026-08-21
inference-shell-ai-image-generation
2026-08-21
tul-sh-ai-image-generation
2026-08-21
inferen-sh-ai-image-generation
2026-08-21
infsh-skills-ai-image-generation
2026-08-21
inference-skills-ai-image-generation
2026-08-21
inference-sh-skills-ai-image-generation
2026-08-21
skillssh-ai-image-generation
2026-08-21
doany-ai-ai-image-generation
2026-08-21
qu-skills-ai-image-generation
2026-08-21
genmedia-labs-ai-image-generation
2026-08-21
toolshell-ai-image-generation
2026-08-21
skills-shell-ai-image-generation
2026-08-21
101-skills-ai-image-generation
2026-08-21
prime-skills-ai-image-generation
2026-08-21
agentspace-so-ai-image-generation
2026-08-21
halt-catch-fire-ai-image-generation
2026-08-21
inference-sh-ai-image-generation
2026-08-21
inference-sh-9-ai-image-generation
2026-08-21
inference-sh-8-ai-image-generation
2026-08-21
skills-collective-ai-image-generation
2026-08-21
danielgwilson-ai-image-generation
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Draft Product Concepts
Create quick visual options for product shots, moodboards, or campaign directions before final design work.
Prepare Launch Creative
Choose models that handle exact headlines, multilingual text, and consistent layout for marketing assets.
Prototype Image Pipelines
Map prompts, model choices, and CLI runs for repeatable generation or edit workflows.
Try These Prompts
Generate a square product image of a ceramic coffee mug on a marble counter with warm morning light.
Create four quick concept images for a minimalist desk lamp, using a neutral studio background and soft shadows.
Create a landscape launch poster where the headline reads exactly "AURORA Spring 2026" with a clean premium layout.
Generate a photoreal fashion portrait, then create an edit plan to keep the person unchanged while replacing the background.
Best Practices
- Start with the subject, then describe scene, composition, lighting, and final style.
- Choose the model for the hard requirement, such as exact text, photorealism, speed, or reference preservation.
- Keep web search and third-party reference URLs opt-in when real-world grounding is necessary.
Avoid
- Do not use high-resolution settings for early ideation when draft settings are sufficient.
- Do not rely on general image models for exact typography when a text-focused model is available.
- Do not pass unreviewed reference URLs or tokens into prompts, logs, or shared output.
Frequently Asked Questions
Does this skill create images locally?
Which tools can use this skill?
Which model should I use for exact text in an image?
Can it edit existing images?
Does it support mask-based inpainting?
What credentials are required?
Developer Details
Author
runcomfy-comLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
19 downloads · 0 views
File structure
📄 SKILL.md