gpt-image-2
Generate GPT Image 2 Images on RunComfy
Image teams need precise visuals with readable text and stable edits. This skill guides GPT Image 2 generation and editing through RunComfy.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "gpt-image-2" from https://skillstore.io/skills/doany-ai-gpt-image-2.md and its manifest at https://skillstore.io/api/skills/doany-ai-gpt-image-2/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 "gpt-image-2". A user requests a square e-commerce product visual with short label text.
Expected outcome:
The skill prepares a GPT Image 2 generation request and saves the resulting image files in the selected output folder.
Using "gpt-image-2". A user provides a product image URL and asks for a background change.
Expected outcome:
The skill uses the edit endpoint, preserves the product, and downloads the completed RunComfy result.
Using "gpt-image-2". A user asks whether GPT Image 2 is the right model for multilingual signage.
Expected outcome:
The skill explains that GPT Image 2 is suited for short embedded text, layout precision, and brand mockups.
Security Audit
Medium RiskMost static detections are Markdown formatting false positives, including code fences, inline literals, and abbreviated URL paths. The confirmed static issue is expected RunComfy network egress, and one semantic provenance issue needs correction. No prompt injection attempt was found.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (41)
🌐 Network access (6)
📁 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/doany-ai-gpt-image-2/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-gpt-image-2?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-gpt-image-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-gpt-image-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-gpt-image-2.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
doany-ai. (2026). gpt-image-2 security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-gpt-image-2/audits/4BibTeX citation
@techreport{doany-ai-doany-ai-gpt-image-2-2026,
author = {doany-ai},
title = {gpt-image-2 security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-gpt-image-2/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: "gpt-image-2 security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/doany-ai-gpt-image-2/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-gpt-image-2:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
4 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
runcomfy-com-gpt-image-2
2026-08-21
doany-ai-gpt-image-2
2026-08-21
agentspace-so-gpt-image-2
2026-08-21
prime-skills-gpt-image-2
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Create Product Listing Images
Generate clean product visuals with short label text and consistent studio lighting.
Localize Brand Assets
Adapt signs, posters, and package mockups with short multilingual text.
Refine Existing Visuals
Edit backgrounds, composition, or text while preserving the main subject.
Try These Prompts
Generate a square product image with GPT Image 2. Use a clean studio setting, one short label, and soft light.
Edit this reference image with GPT Image 2. Keep the subject identity and pose unchanged, but replace the background with a bright studio.
Create a cafe sign concept. Render the exact text "OPEN STUDIO" and make the typography clear at normal viewing size.
Use image 1 as the product and image 2 as the lighting reference. Keep packaging text unchanged and match the room perspective.
Best Practices
- Use short exact text when asking for labels, signs, or packaging.
- Change one visual attribute per edit when preserving composition matters.
- Use size auto for edits unless the user asks for a new frame.
Avoid
- Do not send private images or prompts unless RunComfy processing is acceptable.
- Do not combine many unrelated style directions in one prompt.
- Do not expect exact control-layer behavior from multi-reference edits.