← 返回 Skills 市场

Dream Image to Video

Name: Dream Image to Video
Author: hy-1990

作者 hy · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ✓ 安全检测通过

581

总下载

当前安装

版本数

在 OpenClaw 中安装

/install dream-image-to-video

功能描述

Generate videos from images using Image to Video (Wan2.1) API. Automatically generates 4-second videos from text descriptions and images. Powered by Dreamfac...

使用说明 (SKILL.md)

Dream Image to Video (Wan2.1) - Image to Video

Generate 4-second videos from text prompts and images.

Quick Start

1. Get API Key

Before using this skill, you need a DreamAPI API key. Visit https://api.newportai.com/api-reference/get-started to sign up and get your API key.

For more AI tools, please visit: https://tools.dreamfaceapp.com/home

2. Configure API Key

openclaw config patch --json '{"skills": {"entries": {"dream-image-to-video": {"env": {"DREAMIMAGETOVIDEO_API_KEY": "your-api-key-here"}}}}}'```

### 3. Usage

#### Parameters:
- **prompt**: Text description, max 1500 characters
- **image**: Image URL
- **resolution** (optional): "480p" or "720p", default "480p"

## API Details

### 1. Get Upload Policy (for local files)

Upload your local files to OSS first (get upload policy, then upload).

### 2. Image to Video API

POST https://api.newportai.com/api/async/wan/image_to_video/2.1


### 3. Polling for Result

POST https://api.newportai.com/api/getAsyncResult


## Implementation Notes

- Generates 4-second videos
- Prompt max 1500 characters
- Supports 480p and 720p
- Status: 0=pending, 1=processing, 2=processing, 3=completed, 4=timeout

安全使用建议

This skill is coherent with its stated purpose, but it will transmit your images, prompts, and the API key to a third-party endpoint (api.newportai.com / tools.dreamfaceapp.com). Before installing: 1) Verify you trust NewportAI/Dreamface and review their privacy/billing policies. 2) Use a dedicated, limited-scope API key (rotate/revoke if needed). 3) Be cautious about uploading sensitive images or PII. 4) Understand that running the suggested openclaw config patch stores the API key in your agent configuration—confirm who can access that config. If you need stronger guarantees, test with non-sensitive data and confirm the endpoint/domain are legitimate.

功能分析

Type: OpenClaw Skill Name: dream-image-to-video Version: 1.0.1 The skill bundle contains documentation and instructions for an AI agent to interact with a legitimate Image-to-Video API (Wan2.1 via NewportAI/Dreamface). It defines standard parameters, API endpoints (api.newportai.com), and configuration steps for an API key without any evidence of malicious logic, data exfiltration, or prompt injection.

能力评估

✓ Purpose & Capability

Name/description match the declared requirement (DREAMIMAGETOVIDEO_API_KEY) and the SKILL.md describes calls to api.newportai.com image-to-video endpoints. No unrelated credentials, binaries, or install steps are requested.

ℹ Instruction Scope

SKILL.md instructs the agent to call NewportAI endpoints, obtain upload policies for local file uploads, and poll for async results. This is within the expected scope for an image→video API. Note: uploading local files and the openclaw config patch will transmit data (images/prompts and the API key) to external services—expected for this kind of skill but important for privacy.

✓ Install Mechanism

No install spec and no code files are included (instruction-only). That minimizes local code execution risk; nothing is downloaded or written by the skill itself.

✓ Credentials

Only one required env var (DREAMIMAGETOVIDEO_API_KEY) is declared and used as the primary credential, which is proportionate for an external API integration. The SKILL.md does not reference other secrets or system config paths.

✓ Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent or elevated platform privileges. The SKILL.md shows a recommended openclaw config patch to store the API key in agent config — expected but the user should verify config storage/access controls.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install dream-image-to-video
安装完成后，直接呼叫该 Skill 的名称或使用 /dream-image-to-video 触发
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

v1.0.1

- Added a link to more Dreamface AI tools in the Quick Start section. - Clarified local file upload instructions (get upload policy, then upload). - Removed redundant and detailed steps for the upload policy and upload process. - No changes to API usage or parameters.

v1.0.0

Initial release of dream-image-to-video. - Generate 4-second videos from text prompts and images using the Image to Video (Wan2.1) API. - Supports prompt descriptions up to 1500 characters and images via URL. - Offers output video resolution options: 480p (default) and 720p. - Guides for configuring API keys and uploading local files included. - Integration powered by Dreamface—visit https://tools.dreamfaceapp.com/home for more AI tools.

元数据

Slug dream-image-to-video

版本 1.0.1

许可证 MIT-0

累计安装 2

当前安装数 2

历史版本数 2

常见问题