← 返回 Skills 市场
ghwyever

05 Image To Video

作者 GHwyever · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ✓ 安全检测通过
238
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install 05-image-to-video
功能描述
Convert static images into dynamic video clips with motion and subtle effects using Lingya AI image-to-video technology.
使用说明 (SKILL.md)

图生视频生成技能

功能介绍

将静态图片转为带动态运镜的短视频片段,适配短剧节奏。

输入参数

  • image_url:图片地址(必填)

输出结果

  • video_url:生成视频片段地址

使用场景

  • 静态画面转动态短剧镜头
  • 批量制作视频素材
  • 提升短剧视觉流畅度

技术说明

支持通用图生视频模型,需配置 API_KEY、API_BASE、MODEL_NAME。

安全使用建议
This skill simply forwards the provided image URL to whatever API_BASE you configure and returns the video URL the service responds with. Before installing: 1) Only set API_BASE to an official, trusted Lingya AI (or other) endpoint — a malicious API_BASE can exfiltrate images and your API_KEY. 2) Give the API_KEY minimal permissions and rotate it if possible. 3) Avoid using private or sensitive image URLs unless you trust the service and have reviewed its privacy policy. 4) If you need higher assurance, review the skill.js source yourself (it is short) and verify API_BASE and API responses during testing with non-sensitive images. Note: manifest.json version differs from registry metadata (minor discrepancy) but does not affect behavior.
功能分析
Type: OpenClaw Skill Name: 05-image-to-video Version: 1.0.3 The skill is a standard implementation for an image-to-video conversion tool. The logic in skill.js correctly uses environment variables (API_KEY, API_BASE) to make a legitimate POST request to a configured endpoint, and the SKILL.md documentation accurately reflects the code's functionality without any malicious instructions or prompt injection attempts.
能力评估
Purpose & Capability
Name/description (image → video) match the implementation. The manifest and SKILL.md declare API_KEY, API_BASE, and MODEL_NAME and the code uses exactly those values to call an /img2video endpoint. No unrelated binaries, credentials, or config paths are requested.
Instruction Scope
SKILL.md describes the required input (image_url) and the need to configure API_KEY/API_BASE/MODEL_NAME. The runtime code follows that scope: it sends image_url to API_BASE/img2video and returns data.video_url. It does not read other files, env vars, or system state.
Install Mechanism
There is no install spec and the skill is effectively instruction+small JS wrapper. Nothing is downloaded or written to disk by an installer. The runtime uses fetch to call the external API.
Credentials
The required environment variables (API_KEY, API_BASE, MODEL_NAME) are appropriate for contacting an external image-to-video service and are declared in the manifest. Caution: API_BASE is arbitrary — if you set it to an attacker-controlled endpoint, the skill will send image_url (and the API_KEY in Authorization header) to that endpoint. Ensure the API_KEY has limited scope and that API_BASE points to a trusted provider. Also be careful when passing private or sensitive image URLs, as they will be transmitted to the configured service.
Persistence & Privilege
The skill is not always:true, does not request persistent system privileges, and does not modify other skills or system-wide config. Autonomous invocation is allowed (default) but that is expected for skills and not in itself a security problem.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install 05-image-to-video
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /05-image-to-video 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.3
- Updated SKILL.md for a more concise feature description and clarified usage scenarios. - Simplified technical information; now highlights required environment variables for model configuration. - Removed the _meta.json file.
v1.0.2
- Updated manifest.json with minor changes. - No changes to features or user-facing documentation.
v1.0.1
- Initial metadata file (_meta.json) added to the project. - No changes to skill functionality or documentation.
v1.0.0
- Initial release of the image-to-video skill. - Converts static image keyframes into dynamic video clips with camera movement and motion effects. - Supports image input via URL and returns a generated dynamic video URL. - Enables bulk dynamic video creation for short-form drama content. - Integrates Lingya AI image-to-video models with flexible model selection and effect customization via environment variables.
元数据
Slug 05-image-to-video
版本 1.0.3
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 4
常见问题

05 Image To Video 是什么?

Convert static images into dynamic video clips with motion and subtle effects using Lingya AI image-to-video technology. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 238 次。

如何安装 05 Image To Video?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install 05-image-to-video」即可一键安装,无需额外配置。

05 Image To Video 是免费的吗?

是的,05 Image To Video 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

05 Image To Video 支持哪些平台?

05 Image To Video 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 05 Image To Video?

由 GHwyever(@ghwyever)开发并维护,当前版本 v1.0.3。

💬 留言讨论