ai-image-generation
Generate and Edit Images with RunComfy
Choosing an image model and its parameters can slow creative work. This skill routes requests to suitable RunComfy models and provides focused prompts and commands.
自分のエージェントでインストール
このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。
Review the Skillstore skill "ai-image-generation" from https://skillstore.io/skills/genmedia-labs-ai-image-generation.md and its manifest at https://skillstore.io/api/skills/genmedia-labs-ai-image-generation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。
エージェントが読めるリソース
AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。
テストする
「ai-image-generation」を使用しています。 Create a landscape launch poster with the exact headline "AURORA Spring 2026".
期待される結果:
Selected GPT Image 2 for precise typography. Produced a landscape poster with the requested headline, centered composition, and saved output location.
「ai-image-generation」を使用しています。 Create four quick square concepts for a ceramic mug in warm morning light.
期待される結果:
Selected Nano Banana 2 for rapid iteration. Produced four low-resolution square concepts with a reusable seed and consistent product framing.
「ai-image-generation」を使用しています。 Keep the person unchanged but replace the background with a rainy city street.
期待される結果:
Selected Nano Banana 2 Edit for identity preservation. Produced an edited image that retains the subject while changing the background.
セキュリティ監査
中リスクAll 199 static matches are false positives caused by Markdown formatting, documentation links, placeholder URLs, standard configuration paths, or model-selection prose. The contextual review found expected third-party data transmission and unpinned package setup commands, with no prompt injection or covert behavior.
確認済みのセキュリティ上の懸念 (2)
リスク要因
⚙️ 外部コマンド (50)
🌐 ネットワークアクセス (50)
📁 ファイルシステムへのアクセス (5)
このレポートを共有・引用
バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。
レポートリンクをコピー
https://skillstore.io/skills/genmedia-labs-ai-image-generation/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/genmedia-labs-ai-image-generation?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/genmedia-labs-ai-image-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/genmedia-labs-ai-image-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/genmedia-labs-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>学術引用 (APA · BibTeX · CFF)
APA形式の引用
genmedia-labs. (2026). ai-image-generation security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/genmedia-labs-ai-image-generation/audits/1BibTeX形式の引用
@techreport{genmedia-labs-genmedia-labs-ai-image-generation-2026,
author = {genmedia-labs},
title = {ai-image-generation security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/genmedia-labs-ai-image-generation/audits/1},
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 1)"
version: "unspecified"
type: report
authors:
- name: "genmedia-labs"
date-released: "2026-08-13"
url: "https://skillstore.io/skills/genmedia-labs-ai-image-generation/audits/1"
identifiers:
- type: other
value: "skillstore:genmedia-labs-ai-image-generation:audit:1"
description: "Skillstore immutable audit report identifier"
バリアントを比較
インストール可能なバリアント 23 件各作者のスキルは個別のインストール項目として維持されます。推奨バリアントは Skillstore の証拠で順位付けされます。
このバリアントが首位の理由
tool-belt-ai-image-generation
2026-09-09
runcomfy-com-ai-image-generation
2026-09-09
inference-shell-ai-image-generation
2026-09-09
inferen-sh-ai-image-generation
2026-09-09
infsh-skills-ai-image-generation
2026-09-09
inference-skills-ai-image-generation
2026-09-09
inference-sh-skills-ai-image-generation
2026-09-09
qu-skills-ai-image-generation
2026-09-09
genmedia-labs-ai-image-generation
2026-09-09
toolshell-ai-image-generation
2026-09-09
skills-shell-ai-image-generation
2026-09-09
101-skills-ai-image-generation
2026-09-09
prime-skills-ai-image-generation
2026-09-09
agentspace-so-ai-image-generation
2026-09-09
halt-catch-fire-ai-image-generation
2026-09-09
inference-sh-ai-image-generation
2026-09-09
inference-sh-9-ai-image-generation
2026-09-09
inference-sh-8-ai-image-generation
2026-09-09
skills-collective-ai-image-generation
2026-09-09
danielgwilson-ai-image-generation
2026-09-09
Skillstore スコア
このスコアの理由 証拠の信頼度: 中作成できるもの
Create Campaign Visuals
Generate posters and advertisements with precise layout, quoted headlines, and multilingual text guidance.
Develop Product Concepts
Produce fast image batches, compare directions, and refine selected concepts at higher resolution.
Automate Creative Production
Select image endpoints and prepare repeatable RunComfy commands for scripted generation workflows.
これらのプロンプトを試す
Generate an image of [subject] in [setting]. Use [style], [lighting], and a [aspect ratio] composition. Save the result in [output folder].
Create a [orientation] poster with the exact headline "[text]" in [script and type style]. Use [palette], [subject], and [layout].
Edit [reference image URL]. Preserve [identity, pose, clothing, and layout]. Change only [specific element] to [desired result].
Design a RunComfy workflow for [goal]. Compare suitable models by quality, speed, cost, typography, and reference support. Generate drafts, select a seed, then refine.
ベストプラクティス
- State the subject first, then describe the scene, composition, lighting, and style.
- Use low-resolution batches for exploration, then increase quality only for selected results.
- Provide only approved reference URLs and request web grounding explicitly when it is necessary.
回避
- Do not send confidential prompts, personal images, or private asset URLs without approval.
- Do not request arbitrary dimensions from models that support only fixed size options.
- Do not combine many unrelated edits in one instruction when identity preservation matters.
よくある質問
What do I need before using this skill?
Which model does the skill choose by default?
Can it generate text inside images?
Can it edit an existing image?
Where are generated files saved?
Does this skill process data locally?
開発者情報
作成者
genmedia-labsライセンス
MIT
Skillstore リビジョン
r1
バージョンに関する注意
作者はバージョンを宣言していません。
参照
9aec8a0368e9f91eaff93b746339683b0542ea3e
メンテナンスの新しさ
2026/8/13
利用状況
0 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md