← Back to Skills Marketplace
5476
Downloads
10
Stars
39
Active Installs
3
Versions
Install in OpenClaw
/install wan-image-video-generation-editting
Description
Image and Video Generation and Editting wiht Wan series models. It offers text2image, image editting(with prompt), text2video, image2video and reference(imag...
Usage Guidance
Install only if you are comfortable sending prompts and selected images or media references to Alibaba DashScope for remote processing. Use a dedicated API key, monitor quota or billing, and avoid submitting sensitive, private, regulated, or unauthorized media.
Capability Analysis
Type: OpenClaw Skill
Name: wan-image-video-generation-editting
Version: 1.0.2
The skill bundle provides a legitimate integration for Alibaba's Wan image and video generation models via the DashScope API. The primary script, `scripts/wan-magic.py`, implements standard wrappers for text-to-image, image editing, and video generation tasks, communicating exclusively with the official `dashscope.aliyuncs.com` endpoint. While the script includes functionality to read and base64-encode local files, this behavior is explicitly documented and required for the stated purpose of processing local images; no evidence of intentional data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The stated purpose is image and video generation/editing with Wan models, and the script implements matching text-to-image, image-edit, text-to-video, image-to-video, and reference-to-video commands.
Instruction Scope
Commands are user-directed. Local image handling is disclosed in SKILL.md as base64 conversion and passing to the model API, though the CLI help and runtime output could make the off-device upload warning more prominent.
Install Mechanism
No installer, package hook, bootstrapper, or dependency mutation was found; the artifact contains documentation, API references, and one Python script.
Credentials
Use of DASHSCOPE_API_KEY and network requests to dashscope.aliyuncs.com is proportionate for this integration, but prompts, selected local images, and media URLs leave the local environment and may consume account quota.
Persistence & Privilege
No credential storage, background worker, autorun, broad local indexing, deletion, or privilege escalation behavior was found; the API key is read from the environment at runtime.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wan-image-video-generation-editting - After installation, invoke the skill by name or use
/wan-image-video-generation-editting - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
No user-visible changes in this version.
- No file changes detected.
- No updates to SKILL.md content except a minor fix: corrected typo in the reference2video options, changing 'character1' to 'character2' for the second file reference.
- No new features or bug fixes introduced.
v1.0.1
- Added support for reference-to-video (reference2video) generation, allowing creation of videos from reference images and/or videos.
- New options for reference2video: reference files (image/video URLs), resolution, and shot type (single or multi).
- Documentation enhanced with usage examples and option descriptions for the new reference2video feature.
- No existing features changed; update adds new capabilities without breaking backward compatibility.
- Added API documentation reference file.
v1.0.0
Initial release of wan-image-video-generation-editting.
- Adds text-to-image, image editing (with prompts), text-to-video, and image-to-video generation using Wan models from Alibaba.
- Supports flexible image and video resolutions, quantity options, and both URL/local file inputs for images.
- Provides detailed CLI instructions for all capabilities.
- Requires a DashScope API key for operation.
Metadata
Frequently Asked Questions
What is Wan Image and Video Generation and Editting?
Image and Video Generation and Editting wiht Wan series models. It offers text2image, image editting(with prompt), text2video, image2video and reference(imag... It is an AI Agent Skill for Claude Code / OpenClaw, with 5476 downloads so far.
How do I install Wan Image and Video Generation and Editting?
Run "/install wan-image-video-generation-editting" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Wan Image and Video Generation and Editting free?
Yes, Wan Image and Video Generation and Editting is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Wan Image and Video Generation and Editting support?
Wan Image and Video Generation and Editting is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Wan Image and Video Generation and Editting?
It is built and maintained by krisyejh (@krisyejh); the current version is v1.0.2.
More Skills