skills.rest
QianWen-AI
QianWen-AIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

qianwen-video-generation

Automate video generation with Wan models across t2v, i2v, kf2v, r2v, and vace modes.

67|4|Updated May 9, 2026
Search Tags:#asynchronous#i2v#video-generation#t2v#wan#r2v#vace
One-click install
npx skills add https://github.com/QianWen-AI/qianwen-ai --skill qianwen-video-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qianwen-video-generation
Source: https://github.com/QianWen-AI/qianwen-ai/tree/main/skills/video/qianwen-video-generation
Command: npx skills add https://github.com/QianWen-AI/qianwen-ai --skill qianwen-video-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables end-to-end video generation using Wan models across multiple modes (t2v, i2v, kf2v, r2v, and VACE), accelerating production and reducing manual steps in crafting video content.

Core Features & Use Cases

  • Multi-mode support: text-to-video, image-to-video, first+last frame transitions, reference-based roles, and video editing.
  • Asynchronous execution: submit tasks, poll for results, and download the final video.
  • Reference assets and automation: bundled references and helper scripts for common workflows; supports local file uploads and online resources.

Quick Start

Provide a minimal JSON request with a prompt to generate a video using the default t2v path.

Frequently Asked Questions about qianwen-video-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate video from text using Wan models?▼

To generate video from text using Wan models, submit a minimal JSON request with a prompt via DashScope. The skill handles asynchronous task submission, polling, and final video retrieval automatically.

Can I convert an image to video with first and last frame transitions?▼

Yes, you can convert images to video with first and last frame transitions using the kf2v mode. This allows you to submit reference frames to generate a smooth video transition between your specified start and end images.

Do I need a QianWen API key to automate video generation?▼

Yes, a valid QianWen API key is required to automate video generation. Your environment must also have Python 3.9 or higher and curl installed to execute the asynchronous submission and polling workflows.

How does asynchronous video generation handle polling and final file retrieval?▼

Asynchronous video generation submits tasks to DashScope and polls the status until completion. Once processing finishes, the workflow automatically retrieves and downloads the final generated video file for your local use.

What are the limitations of using Wan models for video editing?▼

Limitations of using Wan models for video editing include per-second pricing and model availability constraints on DashScope. You should monitor these factors and ensure your Python environment meets the 3.9+ requirement before running vace workflows.

Related Skills

Explore More Design & Creative Skills→
QianWen-AIQianWen-AI
67

qianwen-text

Enable OpenAI-compatible chat, text generation, and tool calling for Qwen models.

Official
Intermediate
locdinh209locdinh209

media-processing

Convert and process multimedia files using FFmpeg and ImageMagick.

Community
Advanced
TencentTencent
76

workrally

Manage AIGC video production workflows via a CLI toolset.

Official
Advanced
missyouangeledmissyouangeled

creaa-ai

Generate images and videos from the terminal via the Creaa AI API.

Community
Advanced