image-to-video
Animate Images with RunComfy Model Routing
Different animation tasks need different models and input formats. This skill selects a RunComfy route and supplies model-specific prompting guidance and CLI examples.
Установить с помощью моего Агента
Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.
Review the Skillstore skill "image-to-video" from https://skillstore.io/skills/gencraft-labs-image-to-video.md and its manifest at https://skillstore.io/api/skills/gencraft-labs-image-to-video/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.
Ресурсы для AI-агентов
Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.
Протестировать
Использование «image-to-video». Prepare a five-second portrait animation with subtle motion.
Ожидаемый результат:
- Selected route: HappyHorse 1.0 I2V.
- Motion prompt: Gentle camera drift, subtle breathing, stable facial features, and soft natural light.
- Settings: five seconds, 1080P, and the source image aspect ratio.
- Pending: an approved image URL and confirmation before remote submission.
Использование «image-to-video». Plan a vertical talking-head clip using my twelve-second voiceover.
Ожидаемый результат:
- Selected route: Wan 2.7 text-to-video with custom audio.
- Shot prompt: Medium close-up, locked camera, soft key light, and minimal body movement.
- Settings: twelve seconds and vertical 9:16 framing.
- Boundary: this route generates a described subject; the documented input does not accept an existing portrait.
Использование «image-to-video». Combine my subject image, cafe scene video, and voice reference in an eight-second clip.
Ожидаемый результат:
- Selected route: Seedance 2.0 Pro.
- Reference plan: subject from image 1, scene from video 1, and voice tone from audio 1.
- Settings: eight seconds and 720p.
- Validation: reference video and audio must each last 2 to 15 seconds; reference audio must be smaller than 15MB.
Аудит безопасности
БезопасноAll 67 static findings are false positives involving Markdown, placeholder URLs, ordinary CLI usage, or documented credential storage. No evidence found of malicious intent, unauthorized credential access, or prompt injection in SKILL.md. External CLI behavior and provider security claims cannot be verified from this documentation-only skill.
Факторы риска
⚙️ Внешние команды (50)
🌐 Доступ к сети (8)
📁 Доступ к файловой системе (7)
Поделиться и цитировать этот отчет
Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.
Копировать ссылку на отчёт
https://skillstore.io/skills/gencraft-labs-image-to-video/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportЗначок Markdown
[](https://skillstore.io/skills/gencraft-labs-image-to-video?utm_source=security_passport_badge)Значок HTML
<a href="https://skillstore.io/skills/gencraft-labs-image-to-video?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/gencraft-labs-image-to-video/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Встраиваемая карточка
<iframe src="https://skillstore.io/embed/skills/gencraft-labs-image-to-video.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Академические ссылки (APA · BibTeX · CFF)
Цитата APA
gencraft-labs. (2026). image-to-video security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/gencraft-labs-image-to-video/audits/1Цитата BibTeX
@techreport{gencraft-labs-gencraft-labs-image-to-video-2026,
author = {gencraft-labs},
title = {image-to-video security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/gencraft-labs-image-to-video/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: "image-to-video security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "gencraft-labs"
date-released: "2026-10-07"
url: "https://skillstore.io/skills/gencraft-labs-image-to-video/audits/1"
identifiers:
- type: other
value: "skillstore:gencraft-labs-image-to-video:audit:1"
description: "Skillstore immutable audit report identifier"
Сравнить варианты
10 устанавливаемых вариантовНавык каждого автора остаётся отдельным устанавливаемым вариантом. Рекомендуемый вариант ранжируется по данным Skillstore.
Почему этот вариант первый
runcomfy-com-image-to-video
2026-09-09
gencraft-labs-image-to-video
2026-10-11
prime-skills-image-to-video
2026-10-24
genmedia-labs-image-to-video
2026-09-09
101-skills-image-to-video
2026-10-12
halt-catch-fire-image-to-video
2026-09-09
skills-collective-image-to-video
2026-09-09
doany-ai-image-to-video
2026-09-09
agentspace-so-image-to-video
2026-10-22
inference-sh-9-image-to-video
2026-09-09
Оценка Skillstore
Почему такая оценка Достоверность доказательств: СреднийЧто вы можете построить
Product Motion Previews
Prepare a short HappyHorse animation from a product image, with one camera movement and explicit packaging preservation goals.
Localized Talking-Head Clips
Use Wan with different approved voiceover tracks to generate language variants of a described talking-head shot.
Reference-Based Scene Concepts
Use Seedance to combine a subject image, a scene reference video, and an audio reference in one short clip.
Попробуйте эти промпты
Prepare a five-second animation from [image URL], with subtle breathing and a gentle camera drift. Preserve facial features. Show the plan before submitting.
Prepare a HappyHorse animation from [product image URL] at 1080P for eight seconds. Use a slow orbit and preserve packaging. Confirm before submission.
Plan Wan talking-head clips using [English audio URL] and [Spanish audio URL]. Use vertical framing and a shared seed. Explain source-image limitations before submission.
Plan an eight-second Seedance clip using [subject image URL], [scene video URL], and [voice audio URL]. Number reference cues and validate media before submission.
Лучшие практики
- Use media you are authorized to share, and confirm provider processing and current charges before remote submission.
- Validate model-specific media limits, duration, resolution, and aspect ratio before invoking the CLI.
- Describe one primary motion, state preservation goals, and reuse seeds when comparing supported variants.
Избегать
- Do not upload confidential media or place credentials in prompts or public media URLs.
- Do not assume the documented Wan route preserves a supplied portrait; it has no source-image field.
- Do not combine incompatible reference styles or request multiple model routes within a single generation call.
Часто задаваемые вопросы
Which model is selected by default?
Can I use my own voiceover?
Can I combine image, video, and audio references?
What setup is required?
Does generation happen on my computer?
What are the documented output limits?
Сведения для разработчиков
Автор
gencraft-labsЛицензия
MIT
Ревизия Skillstore
r1
Примечание о версии
Автор не указал версию.
Репозиторий
https://github.com/gencraft-labs/skills/tree/5d625f59c710d7a33316b50b302b7158cdee5971/image-to-videoСсылка
e406bf64b5db6e514879399e87b346fa7ff7c2fb
Актуальность поддержки
11.10.2026
Использование
0 загрузок · 0 просмотров
Структура файлов
📄 SKILL.md