← Back to Skills Marketplace
PixVerse AI Image and Video Generator
by
PixVerse-Official
· GitHub ↗
· v1.5.0
· MIT-0
459
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install pixverse-ai-image-and-video-generator
Description
PixVerse CLI — generate AI videos and images from the command line. Supports PixVerse V6, Veo, Sora, Grok video models; Nano Banana (Gemini), Seedream, Qwen...
Usage Guidance
This skill appears to do what it says: a CLI that interacts with PixVerse cloud services. Before installing or running it, consider: (1) Authentication uses OAuth device flow and tokens are stored in ~/.pixverse/ (or you can supply PIXVERSE_TOKEN) — treat that token like any other credential. (2) Local files passed to commands (e.g., --image ./file.jpg or --video ./my-video.mp4) are uploaded to PixVerse cloud for processing — do not upload sensitive or private files. (3) The included scripts (update.sh, check-update.sh) perform git pulls and curl to GitHub; run them only if you trust the repository and understand they may modify local files. (4) Minor metadata inconsistency: SKILL.md references PIXVERSE_TOKEN but the registry metadata lists no env vars — this is optional but worth noting. If you need higher assurance, inspect the upstream pixverse npm package code before installing or use npx to run without global install.
Capability Analysis
Type: OpenClaw Skill
Name: pixverse-ai-image-and-video-generator
Version: 1.5.0
The skill bundle provides a comprehensive and well-documented interface for the PixVerse AI image and video generation service. It includes detailed capabilities for asset management, authentication via OAuth device flow, and complex generation workflows. The included maintenance scripts (scripts/check-update.sh and scripts/update.sh) are standard utilities for version checking and updating from the official GitHub repository (PixVerseAI/skills). The instructions for the AI agent, including the prompt enhancement logic in capabilities/prompt-enhance.md, are focused on improving output quality while strictly preserving user intent. No evidence of malicious behavior, data exfiltration, or unauthorized execution was found.
Capability Assessment
Purpose & Capability
Name/description (PixVerse CLI for image/video generation) match the instructions and workflows: OAuth device flow, create/download assets, models, pipelines, and asset management. No unrelated credentials or binaries are requested and the provided scripts align with repo maintenance (git/curl).
Instruction Scope
SKILL.md stays on-topic (create/edit/modify assets, check tasks, manage workspaces). It explicitly instructs uploading local files to PixVerse cloud storage (expected for I2V/I2I workflows) and references storing tokens under ~/.pixverse/ and an optional PIXVERSE_TOKEN env var. These behaviors are coherent with the CLI purpose but are privacy-relevant (local files and auth tokens are transmitted/stored).
Install Mechanism
No install spec in the registry (instruction-only). The SKILL.md recommends npm install -g pixverse or npx usage, which is proportionate to a Node CLI. The two included shell scripts only use git and curl against GitHub raw content and are straightforward; no arbitrary binary downloads or obscure hosts are used.
Credentials
Registry metadata lists no required env vars, and the skill does not demand unrelated secrets. SKILL.md references PIXVERSE_TOKEN as an optional override and describes tokens saved under ~/.pixverse/ — the env var is reasonable but it is not declared in the registry metadata, which is a minor inconsistency the user should be aware of.
Persistence & Privilege
always:false and user-invocable (default) — no forced permanent presence. The skill stores its auth token in ~/.pixverse/ (normal for a CLI) but does not request system-wide or other-skills' configuration changes.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pixverse-ai-image-and-video-generator - After installation, invoke the skill by name or use
/pixverse-ai-image-and-video-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.0
PixVerse CLI 1.5.0: Adds Mondo poster workflows, prompt enhancement, and workspace support.
- New workflow for generating Mondo-style posters and covers (`mondo-poster-design`) and two end-to-end pipelines (`mondo-poster-pipeline`, `mondo-poster-to-video-pipeline`).
- Added prompt enhancement capability for better video prompts (`prompt-enhance`).
- Workspace management capability (`workspace`) to list, switch, and view workspace status.
- Updated to use PixVerse V6 as the default video model, extending max duration to 15s.
- Documentation updates reflecting new capabilities and revised model quick reference.
v1.4.0
Version 1.4.0
- Introduced video modification capabilities: added new support for modifying existing videos via prompt.
- Added new workflow for video modification and enhancement.
- Removed Mondo poster workflows and related capabilities.
- Updated model defaults and revised capabilities overview to reflect current supported features.
v1.2.0
Major update:
- Expanded capabilities overview and workflow tables to document new features.
- Updated video model reference with PixVerse V6.
v1.0.1
- Added homepage and source fields to SKILL.md for improved discoverability and transparency.
- No code or CLI changes; documentation only.
v0.1.1
- Added shell scripts for checking and updating the CLI: `scripts/check-update.sh` and `scripts/update.sh`.
- Added a comprehensive Windows PowerShell workflow example for text-to-video generation: `examples/windows/powershell-text-to-video.ps1`.
- Mentioned the PowerShell pipeline example in the Quick Start, making it easier for Windows users to get started.
- Set the skill version to 1.0.0 in SKILL.md.
- No breaking changes to core commands or CLI behavior.
v0.1.0
PixVerse CLI Skill version 0.1.0 — Initial Release
- Launch of the official PixVerse CLI for generating AI videos and images from the command line.
- Supports multiple AI models (PixVerse, Sora, Veo, Kling, Wan, Gemini/Nano Banana, Seedream, Qwen) and effect templates.
- Structured JSON output, deterministic exit codes, and automation-ready commands for AI agents and developers.
- Features include authentication via OAuth device flow, asset management, video/image creation & editing, batch processing, and workflow pipelines.
- Comprehensive documentation on installation, command usage, model references, and workflow skills.
Metadata
Frequently Asked Questions
What is PixVerse AI Image and Video Generator?
PixVerse CLI — generate AI videos and images from the command line. Supports PixVerse V6, Veo, Sora, Grok video models; Nano Banana (Gemini), Seedream, Qwen... It is an AI Agent Skill for Claude Code / OpenClaw, with 459 downloads so far.
How do I install PixVerse AI Image and Video Generator?
Run "/install pixverse-ai-image-and-video-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is PixVerse AI Image and Video Generator free?
Yes, PixVerse AI Image and Video Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does PixVerse AI Image and Video Generator support?
PixVerse AI Image and Video Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created PixVerse AI Image and Video Generator?
It is built and maintained by PixVerse-Official (@pixverse-official); the current version is v1.5.0.
More Skills