skills.rest
QwenCloud
QwenCloudOFFICIAL
Explore all skills by this author →
Website𝕏@qwen_cloudGitHub

qwencloud-video-generation

Generate videos via DashScope API using Wan models with async polling.

36|Updated Mar 11, 2026
Search Tags:#automation#asynchronous#prompting#video-editing#video-generation#dashscope#wan
One-click install
npx skills add https://github.com/QwenCloud/qwencloud-ai --skill qwencloud-video-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qwencloud-video-generation
Source: https://github.com/QwenCloud/qwencloud-ai/tree/main/skills/video/qwencloud-video-generation
Command: npx skills add https://github.com/QwenCloud/qwencloud-ai --skill qwencloud-video-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The skill provides a comprehensive, async path to generate videos using Wan models (t2v, i2v, kf2v, r2v, vace) via the DashScope API, enabling rapid creation and editing of video content from prompts, frames, or references.

Core Features & Use Cases

  • Asynchronous submission and polling for video tasks across all modes (text-to-video, image-to-video, first+last frame, reference-based, and VACE editing).
  • Flexible model support and payload construction for Wan model variations (wan2.6/wan2.7) with per-mode parameters like size vs resolution, durations, multi-shot prompts, and VACE operations.
  • Use cases include generating a cinematic scene from a prompt, animating a still image, deriving character-driven videos from references, and post-processing via VACE pipelines.

Quick Start

Run the bundled script with a sample prompt to submit a video task and download the resulting video.

Frequently Asked Questions about qwencloud-video-generation

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

FAQPage Schema
How do I generate video from text using the Wan model asynchronously?▼

To generate video from text using the Wan model, submit an asynchronous text-to-video (t2v) task to the DashScope API and poll for the resulting video output.

Can I use a still image and reference frames to create a video?▼

Yes, you can create a video from a still image or reference frames using image-to-video (i2v), reference-based (r2v), or first and last frame (kf2v) modes via the DashScope API.

What do I need to run DashScope video generation tasks locally?▼

Running DashScope video generation tasks requires Python 3.9 or higher, a valid DashScope API key, and proper URL resolution for local files, with optional OSS uploads configured.

What is the best way to edit an existing video using the Wan model?▼

The best way to edit an existing video using the Wan model is through the VACE pipeline, which supports post-processing and video editing operations via asynchronous DashScope API requests.

Does asynchronous video generation support custom durations and resolutions?▼

Asynchronous video generation supports custom durations and resolutions, allowing flexible payload construction for Wan model variations including per-mode parameters like size and multi-shot prompts.

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
calesthiocalesthio
123

luma-ray-video

Route Luma Ray video generation workflows through the current Luma Agents API.

Community
Advanced
QianWen-AIQianWen-AI
67

qianwen-video-generation

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

Official
Advanced
47thtechcorner47thtechcorner
21

grok-media

Generate and edit images and videos via xAI media endpoints.

Community
Advanced