aliyun-vidu-video

This skill wraps Alibaba Cloud's DashScope Vidu video-synthesis API, enabling text-to-video, image-to-video, keyframe interpolation, and reference-subject generation. It handles async task creation, polling, and result retrieval across multiple Vidu model variants (Q3 Pro/Turbo, Q2) with configurable resolution, duration, audio, and watermark options.

Aliyun Vidu Video generates videos from text, images, or keyframes using DashScope's Vidu models.

AI-generated summary based on this skill's SKILL.md

★ 397 ⁮ 34 MIT updated 2026-07-18 by cinience

Install

cinience/alicloud-skills/aliyun-vidu-video · repository language: Python

Manual (git clone) CLI (skillfed)

git clone https://github.com/cinience/alicloud-skills
cp -r alicloud-skills/skills/ai/video/aliyun-vidu-video ~/.claude/skills/aliyun-vidu-video

npx skillfed install cinience/alicloud-skills/aliyun-vidu-video

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What is aliyun-vidu-video and what can it do?

aliyun-vidu-video is a skill that wraps Alibaba Cloud's DashScope Vidu video-synthesis API. It enables you to generate videos from text prompts, convert images to video sequences, interpolate video between keyframe images, and embed reference subjects into prompted video scenes. The skill handles async task creation, polling, and result retrieval across multiple Vidu model variants including Q3 Pro, Turbo, and Q2, with configurable resolution, duration, audio, and watermark options.

Can aliyun-vidu-video generate video from text prompt?

Yes. aliyun-vidu-video's primary capability is generating videos from text prompts using Alibaba Vidu models. You provide a text description of the video you want to create, and the skill leverages the DashScope API to synthesize video content matching your prompt. The skill manages the async API workflow, including task submission, polling for completion, and retrieving the generated video results.

How does image to video conversion work in aliyun-vidu-video?

aliyun-vidu-video converts images to video sequences with optional motion prompts. You can supply an image and describe the motion or action you want to see in the resulting video. The skill also supports keyframe interpolation, where you provide first and last frame images and the system generates smooth video transitions between them, optionally guided by motion descriptions.

What does reference to video synthesis mean in aliyun-vidu-video?

aliyun-vidu-video can embed reference subjects into prompted video scenes. This means you can provide a reference image (such as a person, object, or character) and include it in your text prompt, allowing the Vidu model to generate video content that incorporates your reference subject into the described scene while maintaining consistency with the prompt.

How do I integrate aliyun-vidu-video into my application?

aliyun-vidu-video integrates the DashScope async video synthesis API into applications through a skill interface. The skill handles the complexity of async task management—submitting video generation requests, polling for task completion, and retrieving results—so you can focus on your application logic rather than managing API polling and error handling directly.

What is the license for aliyun-vidu-video?

aliyun-vidu-video is released under the MIT license, which permits free use, modification, and distribution with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim

Vidu Video Generation

Validation

mkdir -p output/aliyun-vidu-video
python -m py_compile skills/ai/video/aliyun-vidu-video/scripts/generate_vidu_video.py &amp;&amp; echo "py_compile_ok" &gt; output/aliyun-vidu-video/validate.txt

Pass criteria: command exits 0 and output/aliyun-vidu-video/validate.txt is generated.

Output And Evidence

Save task IDs, polling responses, and final video URLs to output/aliyun-vidu-video/.
Keep at least one end-to-end run log for troubleshooting.

Prerequisites

Set DASHSCOPE_API_KEY in your environment (Beijing region key required).
Region: China Mainland (Beijing) only. Model, Endpoint URL, and API Key must belong to the same region.
Enable Vidu models in the Alibaba Cloud Model Studio console before first use.

Critical model names

Text-to-video

vidu/viduq3-pro_text2video
vidu/viduq3-turbo_text2video
vidu/viduq2_text2video

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 4 files

skills/ai/video/aliyun-vidu-video/SKILL.md
skills/ai/video/aliyun-vidu-video/references/api_reference.md
skills/ai/video/aliyun-vidu-video/references/sources.md
skills/ai/video/aliyun-vidu-video/scripts/generate_vidu_video.py

All skills by cinience →