skillfed

aliyun-wan-videoedit

This skill harnesses Alibaba's Wan 2.7 video editing model to transform video appearance through style transfer (clay, anime, etc.) or content-aware edits guided by text prompts and optional reference images. It handles async task creation, polling, and media validation across multiple aspect ratios and resolutions.

Aliyun Wan VideoEdit applies style transfer and instruction-based video edits using the Wan 2.7 model.

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

397 34 MIT updated by cinience

Install

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

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

Frequently asked questions

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

How to edit videos with Wan 2.7?

aliyun-wan-videoedit uses Alibaba's Wan 2.7 model to edit videos through text prompts and optional reference images. You submit a video with editing instructions, and the skill handles async task creation and polling via DashScope's video-synthesis API. Results support multiple resolutions and aspect ratios.

What video style transfers does aliyun-wan-videoedit support?

aliyun-wan-videoedit can convert videos to different artistic styles including clay, anime, and other visual transformations. The skill applies style transfer through Wan 2.7's instruction-based editing, allowing you to specify desired artistic effects via text prompts.

Can aliyun-wan-videoedit modify video resolution and aspect ratio?

Yes, aliyun-wan-videoedit supports modifying video resolution, aspect ratio, and duration during the editing process. These adjustments are handled as part of the async video editing workflow through DashScope's API integration.

How does instruction-based video editing with reference images work?

aliyun-wan-videoedit accepts text instructions paired with optional reference images to guide video edits. The skill sends these to Wan 2.7 via DashScope's async API, which processes the content-aware edits and returns the transformed video.

What is the DashScope async video editing API integration?

aliyun-wan-videoedit integrates Alibaba's DashScope async video-synthesis API to handle long-running video transformations. The skill manages task creation, polling for completion, and media validation, enabling seamless workflow integration for batch or real-time video processing.

What license does aliyun-wan-videoedit use?

aliyun-wan-videoedit is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim

Wan 2.7 Video Editing

Validation

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

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

Output And Evidence

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

Prerequisites

  • Install SDK (recommended in a venv):
python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope
  • Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.

Critical model names

  • wan2.7-videoedit — supports style transfer and instruction-based video editing

Capabilities

|

(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-videoedit/SKILL.md
skills/ai/video/aliyun-wan-videoedit/references/api_reference.md
skills/ai/video/aliyun-wan-videoedit/references/sources.md
skills/ai/video/aliyun-wan-videoedit/scripts/edit_video.py

Related skills

Tags

async-video-processing style-transformation prompt-driven-editing reference-image-support dashscope-integration video-synthesis-api multi-modal-editing aspect-ratio-control