← 返回 Skills 市场

Dream Head Tail to Video

Name: Dream Head Tail to Video
Author: hy-1990

作者 hy · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ✓ 安全检测通过

325

总下载

当前安装

版本数

在 OpenClaw 中安装

/install dream-head-tail-to-video

功能描述

Generate videos from first and last frames using Head Tail to Video (Wan2.1) API. Automatically generates 4-second videos from text descriptions and first/la...

使用说明 (SKILL.md)

Dream Head Tail to Video (Wan2.1) - First/Last Frame to Video

Generate 4-second videos from text prompts and first/last frame 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-head-tail-to-video": {"env": {"DREAMHEADTAILTOVIDEO_API_KEY": "your-api-key-here"}}}}}'```

### 3. Usage

#### Parameters:
- **prompt**: Text description, max 1500 characters
- **firstImage**: First frame image URL
- **lastImage**: Last frame 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. Head Tail to Video API

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


### 3. Polling for Result

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


## Implementation Notes

- Requires uploading first and last frame images
- Auto-generates intermediate frames
- Generates 4-second videos
- Status: 0=pending, 1=processing, 2=processing, 3=completed, 4=timeout

安全使用建议

This skill appears coherent: it will send your first/last-frame images and text prompts to api.newportai.com and requires a single API key. Before installing, verify you trust the service (https://api.newportai.com and https://tools.dreamfaceapp.com), understand their privacy/TOS for uploaded images, and be comfortable storing the API key in your OpenClaw config. If you need tighter control, create a dedicated API key with limited scope or rotate/delete the key after use. If you want additional assurance, ask the publisher for a homepage, official docs, or a link to a known code repository before proceeding.

功能分析

Type: OpenClaw Skill Name: dream-head-tail-to-video Version: 1.0.1 The skill bundle consists of metadata and documentation for a video generation service using the NewportAI API. It contains no executable code, only instructions for configuring an API key and descriptions of the API endpoints (api.newportai.com). The content is consistent with its stated purpose and lacks any indicators of malicious intent or prompt injection.

能力评估

✓ Purpose & Capability

Name/description claim to call the Head Tail to Video API and the skill only requires a single API key (DREAMHEADTAILTOVIDEO_API_KEY) and documents the API endpoints at api.newportai.com — this is coherent with the stated purpose.

ℹ Instruction Scope

SKILL.md instructs obtaining an API key, configuring it in OpenClaw, getting an upload policy and uploading local first/last-frame images, then calling the async endpoint and polling for results. These steps are expected for a remote video-generation API, but note that uploading local image files will transmit user data to the external API (api.newportai.com) and the openclaw config patch stores the API key in agent config.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer. This is the lowest-risk install model.

✓ Credentials

Only one required environment variable (DREAMHEADTAILTOVIDEO_API_KEY) is declared and used as the primary credential; this is proportionate for an API-backed service.

✓ Persistence & Privilege

always is false and disable-model-invocation is default (agent may call autonomously). The skill does ask the user to store the API key in OpenClaw config, which is normal for API-based skills and does not request elevated platform privileges or cross-skill config changes.

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-head-tail-to-video
安装完成后，直接呼叫该 Skill 的名称或使用 /dream-head-tail-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

- Improved documentation to clarify upload steps for using local files. - Added reference link for more AI tools (https://tools.dreamfaceapp.com/home) in Quick Start. - Simplified and reorganized API usage instructions for better readability.

v1.0.0

dream-head-tail-to-video 1.0.0 - Initial release. - Generate 4-second videos from first and last frame images using a text prompt. - Supports easy configuration with DREAMHEADTAILTOVIDEO_API_KEY. - Output resolution options: 480p (default) or 720p. - Integrates with Dreamface platform and Wan2.1 API.

元数据

Slug dream-head-tail-to-video

版本 1.0.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题