skillfed

aliyun-wan-r2v

This skill harnesses Alibaba Cloud's Wan R2V models to create multi-shot videos from reference video or image inputs while maintaining consistent character styling. It provides a normalized interface for async video generation with polling support and includes validation tooling to verify requests against the official model specifications.

aliyun-wan-r2v generates reference-based videos using Alibaba Cloud's Wan R2V models with character style preservation.

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

397 34 MIT updated by cinience

Install

cinience/alicloud-skills/aliyun-wan-r2v · repository language: Python

git clone https://github.com/cinience/alicloud-skills
cp -r alicloud-skills/skills/ai/video/aliyun-wan-r2v ~/.claude/skills/aliyun-wan-r2v
npx skillfed install cinience/alicloud-skills/aliyun-wan-r2v

Frequently asked questions

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

What is aliyun-wan-r2v and what does it do?

aliyun-wan-r2v harnesses Alibaba Cloud's Wan R2V models to create multi-shot videos from reference video or image inputs while maintaining consistent character styling. It provides a normalized interface for async video generation with polling support and includes validation tooling to verify requests against official model specifications.

How do I generate video from reference material using Alibaba Wan2.6?

aliyun-wan-r2v lets you generate video from reference material by calling the Wan R2V API through the DashScope SDK. You provide a reference video or image as input, and the skill handles the async generation process, polling for task completion and returning your generated multi-shot video while preserving the character style from your reference.

What's the difference between wan2.6-r2v-flash and wan2.6-r2v models?

aliyun-wan-r2v supports both wan2.6-r2v-flash and wan2.6-r2v models. The flash variant is optimized for faster generation, while the standard model may offer enhanced quality. Your choice depends on whether you prioritize speed or output fidelity for your reference-based video creation.

How does aliyun-wan-r2v handle async video generation?

aliyun-wan-r2v manages async video generation by submitting your request to Alibaba Cloud, then polling the task status until completion. It handles task tracking automatically, so you don't need to manually monitor the generation process—the skill waits for your video to be ready.

Can aliyun-wan-r2v create multi-shot videos with consistent characters?

Yes, aliyun-wan-r2v is designed to create multi-shot videos while preserving character style from your reference material. This allows you to generate montages or sequences where the character maintains visual consistency across multiple shots, all derived from your reference input.

How do I set up aliyun-wan-r2v with the DashScope SDK?

aliyun-wan-r2v provides integration with Alibaba Cloud's DashScope SDK for calling the Wan R2V API. The skill normalizes the setup process and includes validation tooling to verify your requests against official model specifications, making it straightforward to configure and deploy.

SKILL.md

rendered from the published skill — quoted content, verbatim

Category: provider

Model Studio Wan R2V

Validation

mkdir -p output/aliyun-wan-r2v
python -m py_compile skills/ai/video/aliyun-wan-r2v/scripts/prepare_r2v_request.py && echo "py_compile_ok" > output/aliyun-wan-r2v/validate.txt

Pass criteria: command exits 0 and output/aliyun-wan-r2v/validate.txt is generated.

Output And Evidence

  • Save reference input metadata, request payloads, and task outputs in output/aliyun-wan-r2v/.
  • Keep at least one polling result snapshot.

Use Wan R2V for reference-to-video generation. This is different from i2v (single image to video).

Critical model names

Use one of these exact model strings: - wan2.6-r2v-flash - wan2.6-r2v

Newer official releases may prefer the flash variant for lower latency and lower cost.

Prerequisites

  • Install SDK in a virtual

(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-wan-r2v/SKILL.md
skills/ai/video/aliyun-wan-r2v/agents/openai.yaml
skills/ai/video/aliyun-wan-r2v/references/sources.md
skills/ai/video/aliyun-wan-r2v/scripts/prepare_r2v_request.py

Related skills

Tags

video-synthesis reference-driven character-consistency alibaba-cloud async-generation multi-shot-video style-preservation api-integration