skills.rest
AceDataCloud
AceDataCloudOFFICIAL
Explore all skills by this author →
Website𝕏@acedatacloudGitHub

wan-video

Generate AI videos from text, images, or reference videos via the /wan/videos API.

13|1|Updated Mar 22, 2026
Search Tags:#text to video#image to video#ai video generation#wan#reference video transfer#video resolution#optional audio
One-click install
npx skills add https://github.com/AceDataCloud/Skills --skill wan-video-acedatacloud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wan-video
Source: https://github.com/AceDataCloud/Skills/tree/main/skills/wan-video
Command: npx skills add https://github.com/AceDataCloud/Skills --skill wan-video-acedatacloud

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Wan-video removes the gap between your creative idea and a finished AI video by letting you generate video directly from prompts, images, or reference footage.

Core Features & Use Cases

  • Text-to-Video & Image-to-Video: Turn a description into a video clip or animate a still image into motion (e.g., turn a product photo into a short promo video).
  • Reference Video Transfer (R2V): Extract characters or timbres from a reference video and transfer them into a new generation (e.g., match a character’s look and motion style).
  • Quality Controls & Options: Choose models, resolutions (480P/720P/1080P), durations (5/10/15 seconds), and optionally enable audio generation.

Quick Start

Create a 5-second dolphin clip from a text prompt by sending a text2video request to the Wan videos endpoint using your ACEDATACLOUD_API_TOKEN.

Frequently Asked Questions about wan-video

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

FAQPage Schema
How do I generate AI video from a text prompt or image?▼

You generate AI video from text or images by sending an authenticated POST request to the /wan/videos API with your prompt, model, and optional image_url to produce clips.

What is reference video transfer and how does it work for character animation?▼

Reference video transfer (R2V) extracts characters or timbres from a provided reference video and transfers them into a new generation, allowing you to match a character's look and motion style.

Can I generate audio along with my AI video generation?▼

Yes, you can optionally enable audio generation during the AI video generation process by specifying the audio field in your POST request to the /wan/videos API endpoint.

Does AI video generation support 1080P resolution and longer durations?▼

AI video generation supports resolutions of 480P, 720P, and 1080P, along with durations of 5, 10, or 15 seconds, allowing you to choose quality settings for your marketing assets.

What limitations should I expect when animating a still image into motion?▼

When animating a still image into motion, you must select from supported durations of 5, 10, or 15 seconds and resolutions up to 1080P, and provide a valid image_url for the API request.

Related Skills

Explore More Design & Creative Skills→
AceDataCloudAceDataCloud
13

luma-video

Generate AI videos from text prompts, reference images, or existing video IDs.

Official
Intermediate
vm0-aivm0-ai
76

runway

Generate AI videos from images, text, or existing videos via the Runway API.

Official
Advanced
yangyixxxxyangyixxxx
13

gptnb-image

Generate images, layered assets, and videos via the gptnb.ai middleware API.

Community
Advanced
Moh-TayyabMoh-Tayyab

ai-video-generation

Automate AI video creation with 40+ models via the inference.sh CLI.

Community
Advanced