A comprehensive AI generation skill for Openclaw Skills that enables text-to-image, video synthesis, and digital human creation via the Volcengine Jimeng API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jimeng
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install jimeng using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Jimeng AI (Volcengine) Video and Image Generation Skill?
Jimeng AI is a robust suite of creative tools developed by ByteDance Volcengine, now fully integrated into the Openclaw Skills ecosystem. This skill provides developers with the ability to harness state-of-the-art models for visual content creation, including the latest v4.0 image generation and high-definition video synthesis.
By utilizing this skill within Openclaw Skills, users can automate complex creative workflows, from generating simple character portraits to creating sophisticated 10-second cinematic videos and interactive digital human avatars. It bridges the gap between raw API calls and actionable AI agent workflows, providing a standardized interface for one of the most powerful visual AI engines available.
Jimeng AI (Volcengine) Video and Image Generation Skill Use Cases
- Creating marketing visuals and concept art using the text-to-image v4.0 model.
- Transforming existing photos into diverse artistic styles or anime versions through image-to-image editing.
- Generating cinematic 5 to 10-second videos for social media or presentations using text-to-video.
- Building interactive digital humans or virtual avatars for customer service and entertainment via Dream Actor.
- Automating batch image production for e-commerce or gaming assets using the Openclaw Skills CLI.
How Jimeng AI (Volcengine) Video and Image Generation Skill Works
- The user provides a text prompt or an image source through the CLI interface within the Openclaw Skills framework.
- The skill authenticates with Volcengine using the provided access keys and secret keys stored in environment variables.
- A generation task is initiated, specifying parameters like model version (e.g., v3.0, v3.1, or v4.0), aspect ratio, or frame count.
- The script monitors the task progress and handles any potential content risk audits for text and images.
- Once completed, the skill returns a structured JSON response containing the generated asset URLs and metadata for the AI agent to utilize.
Jimeng AI (Volcengine) Video and Image Generation Skill Setup
To use this within Openclaw Skills, first configure your Volcengine environment variables:
export VOLC_ACCESS_KEY="<your-access-key>"
export VOLC_SECRET_KEY="<your-secret-key>"
Then, navigate to the skill directory and install the necessary dependencies:
cd <skill-path>
npm install
Jimeng AI (Volcengine) Video and Image Generation Skill Data Schema & Taxonomy
The skill outputs a consistent JSON structure for all generation tasks to ensure compatibility across different Openclaw Skills integrations:
| Field | Type | Description |
|---|---|---|
| success | boolean | Indicates if the task completed successfully. |
| taskId | string | Unique identifier for the generation task. |
| images | array | List of objects containing image URLs, width, and height. |
| videoUrl | string | URL of the generated video file for video/avatar tasks. |
| usage | object | Contains metadata like requestId for tracking. |
| error | object | Detailed error code and message if success is false. |
Jimeng AI (Volcengine) Video and Image Generation Skill Advanced Features
- Support for high-end Dream Actor M20 digital human models with complex expressions and gestures.
- Fine-grained control over generation using seeds for reproducible creative results.
- Multi-frame video support (up to 241 frames) for longer, more stable AI video generation.
- Built-in debug mode to inspect raw API traffic and troubleshoot lifecycle events in Openclaw Skills.
- Integrated content safety filters to ensure all generated media passes mandatory risk audits.
SKILL.md
Loading
Related Openclaw Skills
Jimeng AI (jimeng-ai)
A professional AI content generation skill for creating high-quality images and 1080P videos from text prompts using the Volcano Engine Jimeng AI API.
ssh-agentd-control
A specialized tool for managing persistent SSH sessions and remote command execution via a systemd-backed daemon and REST API.
My Tesla
A comprehensive Tesla vehicle control and monitoring skill for macOS utilizing the Tesla Owner API.
Apple Media Control
A powerful workflow wrapper for discovering and controlling Apple TVs, HomePods, and AirPlay devices directly from your macOS environment.
Bankr
Bankr is an AI-powered crypto trading agent and LLM gateway that allows users to manage DeFi operations and access multiple AI models using natural language.
Desktop Mouse Control
A specialized Linux utility for programmatic mouse control via the host gateway using a ydotool wrapper.
Featured*
