← Back to Skills Marketplace
316
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install dreamact
Description
Video-driven face animation using DreamAct API. Animate multiple input images with expressions, lip movements, and head poses from a driving video. Powered b...
README (SKILL.md)
DreamAct - Video-Driven Face Animation
Animate faces in images with expressions, lip movements, and head poses from a driving video.
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": {"dreamact": {"env": {"DREAMACT_API_KEY": "your-api-key-here"}}}}}'```
### 3. Usage
#### Parameters:
- **video**: Driving video URL (mp4, max 1 minute)
- **images**: Face image URL array (jpg, jpeg, png, webp, gif)
- **seed** (optional): Random seed, default 42
## API Details
### 1. Get Upload Policy (for local files)
Upload your local files to OSS first (get upload policy, then upload).
### 3. DreamAct API
POST https://api.newportai.com/api/async/wan/dreamact/2.1
### 4. Polling for Result
POST https://api.newportai.com/api/getAsyncResult
## Implementation Notes
- Extracts expressions, lip movements, head poses from driving video
- Supports multiple face images
- Video duration max 1 minute
- seed parameter for reproducible results
- Status: 0=pending, 1=processing, 2=processing, 3=completed, 4=timeout
- This task may take longer to process (executionTime may exceed 3 minutes)
Usage Guidance
This skill asks only for a DreamAct API key and then calls api.newportai.com endpoints; verify the API provider (api.newportai.com / tools.dreamfaceapp.com) and read their privacy and terms before sending face images or videos. Only provide an API key you control (preferably with limited scope/quotas), test with non-sensitive images first, and ensure you are comfortable with the legal and ethical implications of animating faces. The SKILL.md is somewhat vague about the 'upload policy/OSS' step — if you need to upload local files, confirm where files are sent and how long they are retained before using real personal data.
Capability Analysis
Type: OpenClaw Skill
Name: dreamact
Version: 1.0.1
The skill bundle provides instructions for an AI agent to interact with the DreamAct API for face animation. It defines standard parameters (video, images, seed) and points to legitimate-looking API endpoints at api.newportai.com. No malicious code, data exfiltration, or prompt injection attempts were identified in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
Name/description (video-driven face animation) aligns with the required environment variable (DREAMACT_API_KEY) and the API endpoints documented in SKILL.md. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to call api.newportai.com endpoints and to obtain an upload policy for local files (upload to OSS) but is somewhat high-level/vague about the upload steps. It does not instruct the agent to read unrelated files or access other environment variables. The vagueness about how to obtain/use the upload policy is a clarity/usability concern, not an outright security mismatch.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded by the skill itself. That minimizes install-time risk.
Credentials
Only a single API key (DREAMACT_API_KEY) is required, which is proportional for a cloud API integration. No other secrets or unrelated environment variables are requested.
Persistence & Privilege
always is false and the skill does not request persistent or system-wide configuration changes. It is user-invocable and can be invoked autonomously by default, which is the platform norm.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install dreamact - After installation, invoke the skill by name or use
/dreamact - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added a link to the Dreamface AI tools home page for more resources.
- Clarified instructions on uploading local files to OSS (get upload policy, then upload).
- Minor formatting and copy improvements for better readability.
v1.0.0
Initial release of dreamact – video-driven face animation.
- Animate multiple face images using expressions, lip movements, and head poses from a driving video.
- Powered by DreamAct API and integrates with Dreamface's AI tools.
- Supports various image formats and videos up to 1-minute duration.
- Includes reproducible results with an optional seed parameter.
- Step-by-step guide for API usage and authentication.
Metadata
Frequently Asked Questions
What is DreamAct?
Video-driven face animation using DreamAct API. Animate multiple input images with expressions, lip movements, and head poses from a driving video. Powered b... It is an AI Agent Skill for Claude Code / OpenClaw, with 316 downloads so far.
How do I install DreamAct?
Run "/install dreamact" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is DreamAct free?
Yes, DreamAct is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does DreamAct support?
DreamAct is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created DreamAct?
It is built and maintained by hy (@hy-1990); the current version is v1.0.1.
More Skills