← Back to Skills Marketplace
582
Downloads
0
Stars
2
Active Installs
4
Versions
Install in OpenClaw
/install vidu
Description
Generate AI videos using Vidu — featuring text-to-video, image-to-video, reference-to-video, and start-end-to-video with up to 1080p resolution, anime style...
Usage Guidance
This skill appears to do what it claims: it calls Atlas Cloud (api.atlascloud.ai) to generate videos and requires only your ATLASCLOUD_API_KEY. Before installing, confirm you trust Atlas Cloud and understand billing: the API key is account-scoped (no fine-grained scopes) so any use will bill your account. Keep your key secret, review the included script if you want to verify behavior, and avoid sharing the key with third parties. If you need limited-risk testing, create a dedicated Atlas Cloud account/key with minimal funding.
Capability Analysis
Type: OpenClaw Skill
Name: vidu
Version: 1.0.3
The skill provides a legitimate interface for AI video generation using the Vidu models via the Atlas Cloud API (api.atlascloud.ai). The Python script `scripts/generate_video.py` uses only standard libraries to handle API requests, file uploads, and video downloads, with no evidence of data exfiltration, obfuscation, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description (Vidu video generation) align with the provided Python script and SKILL.md. The only required credential is ATLASCLOUD_API_KEY, which is appropriate for calling the Atlas Cloud API; required binaries and config paths are none.
Instruction Scope
SKILL.md and the script clearly instruct the agent/user to send prompts, images, and uploaded media to api.atlascloud.ai. The runtime instructions and script do not attempt to read unrelated system files or environment variables, nor do they direct data to endpoints other than the declared Atlas Cloud API.
Install Mechanism
No install spec; the skill is instruction-only with a small standalone Python script that uses only the standard library. No downloads from third-party URLs or archive extraction are present.
Credentials
Only ATLASCLOUD_API_KEY is required and is the primary credential — this is proportional. Note: SKILL.md explicitly states Atlas Cloud does not support scoped keys, so the key grants access to all models and billing on the account; users should be aware of billing/exposure risk if the key is shared.
Persistence & Privilege
The skill does not request permanent/always-on privileges, does not modify other skills or system settings, and relies on the agent/user to invoke the included script. Autonomous invocation remains platform-default but is not combined with any unusual privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install vidu - After installation, invoke the skill by name or use
/vidu - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
**Python script for video generation added with CLI examples.**
- Added `scripts/generate_video.py` for video generation, model listing, and file upload.
- New CLI examples for generating videos and uploading files using the script.
- No external dependencies required for the script.
- Updated documentation to show script usage alongside API methods.
- Added metadata for environment variable requirements.
v1.0.2
- Updated API polling endpoint from `/result/{prediction-id}` to `/prediction/{prediction-id}` in workflow examples.
- No functional or parameter changes; documentation adjustment only.
- Users should now poll results using the new endpoint for job status and outputs.
v1.0.1
- Upgraded references from "Vidu Q3" to "Vidu Q3-Pro" to reflect the latest flagship model throughout the documentation.
- Updated API model names and example requests to use `q3-pro` instead of `q3`.
- Clarified feature lists and capability descriptions for Q3-Pro.
- Updated pricing table and references to point to the Q3-Pro model and relevant documentation sources.
- No code or functional changes; documentation and description update only.
v1.0.0
Initial release of the "vidu" skill — AI video generation via Vidu on Atlas Cloud.
- Generate AI videos from text, images, reference images, or start/end frames, with up to 1080p resolution.
- Supports Vidu Q3 (latest) and Vidu 2.0 models across 6 variants, including anime style and synchronized audio/BGM options.
- Offers advanced features like character consistency, cinematic motion, movement amplitude control, and multiple aspect ratios.
- Available through the Atlas Cloud API with 15% savings over standard pricing.
- Suitable for creating product demos, marketing videos, social media reels, animated or cinematic content, and more.
Metadata
Frequently Asked Questions
What is Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0?
Generate AI videos using Vidu — featuring text-to-video, image-to-video, reference-to-video, and start-end-to-video with up to 1080p resolution, anime style... It is an AI Agent Skill for Claude Code / OpenClaw, with 582 downloads so far.
How do I install Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0?
Run "/install vidu" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0 free?
Yes, Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0 support?
Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Vidu — AI Video Generation - Vidu Q3 & Vidu 2.0?
It is built and maintained by MikeWang (@xixihhhh); the current version is v1.0.3.
More Skills