qwen-image-2
Generate Images With Qwen-Image 2
Design teams need fast ways to create and edit visual concepts. This skill guides Claude, Codex, and Claude Code to run Qwen-Image 2 through inference.sh.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "qwen-image-2" from https://skillstore.io/skills/inference-shell-qwen-image-2.md and its manifest at https://skillstore.io/api/skills/inference-shell-qwen-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 "qwen-image-2". Prompt: A serene mountain landscape at sunset.
Expected outcome:
The skill returns a generated PNG image and metadata with dimensions and count.
Using "qwen-image-2". Prompt: Summer sale poster with a beach background.
Expected outcome:
The skill returns a poster image designed for stronger text rendering with the Pro model.
Using "qwen-image-2". Prompt: Edit three reference images into one fashion mockup.
Expected outcome:
The skill produces an edited PNG that combines the requested person, outfit, and pose.
Security Audit
SafeI reviewed SKILL.md and found no prompt injection, hidden scripts, or malicious intent. The static findings are Markdown code fences, inline option names, documentation links, and placeholder image URLs. The skill depends on users intentionally running the inference.sh CLI.
Risk Factors
โ๏ธ External commands (38)
๐ Network access (8)
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/inference-shell-qwen-image-2/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-shell-qwen-image-2?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-shell-qwen-image-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-shell-qwen-image-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-shell-qwen-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 ยท BibTeX ยท CFF)
APA citation
inference-shell. (2026). qwen-image-2 security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-shell-qwen-image-2/audits/4BibTeX citation
@techreport{inference-shell-inference-shell-qwen-image-2-2026,
author = {inference-shell},
title = {qwen-image-2 security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-shell-qwen-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: "qwen-image-2 security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-shell"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-shell-qwen-image-2/audits/4"
identifiers:
- type: other
value: "skillstore:inference-shell-qwen-image-2:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
inference-shell-qwen-image-2
2026-08-21
inferen-sh-qwen-image-2
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Explore Visual Concepts
Generate several image directions from a short creative brief.
Create Text-Heavy Posters
Use the Pro model for promotional artwork with clear, controlled text.
Prototype Image Editing Flows
Test reference-image editing prompts before building a production workflow.
Try These Prompts
Create one image of a serene mountain landscape at sunset. Use realistic lighting and a calm composition.
Create four logo concepts for a coffee shop. Use a minimalist style, warm colors, and no text in the image.
Create a poster with the headline Summer Sale. Use bold red text, a blue subtitle, and a bright beach background.
Edit these three reference images. Put the person in image one into the outfit from image two and the pose from image three.
Best Practices
- Use Qwen-Image 2 Pro when exact text placement matters.
- Set a seed when you need reproducible visual iterations.
- Use clear dimensions that respect the documented pixel limits.
Avoid
- Do not include private images unless they can be sent to inference.sh.
- Do not expect local generation without the hosted service.
- Do not rely on vague prompts for precise poster text.
Frequently Asked Questions
What does this skill use to generate images?
Does it support image editing?
When should I use the Pro model?
Can it create multiple images at once?
Does it require an external account?
Is it compatible with Claude Code and Codex?
Developer Details
Author
inference-shellLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
4 downloads ยท 187 views
File structure
๐ SKILL.md