Alicloud Ai Video Wan R2v

Name: Alicloud Ai Video Wan R2v
Author: cinience

cinience/alicloud-skills

272 installs
396 repo stars
Updated July 18, 2026
cinience/alicloud-skills

alicloud-ai-video-wan-r2v is a version 1.0.0 agent skill that connects Alibaba Cloud Wan reference-to-video models to applications for developers who need multi-shot videos from reference images or clips with consistent

About

alicloud-ai-video-wan-r2v is a version 1.0.0 Cinience agent skill for Alibaba Cloud Model Studio Wan reference-to-video (R2V) generation—distinct from single-image i2v flows. It supports two exact model strings, wan2.6-r2v-flash for lower latency and wan2.6-r2v, via the dashscope Python SDK with DASHSCOPE_API_KEY authentication. The normalized video.generate_reference interface accepts prompt, reference_video, optional reference_image, duration, fps, size, and seed, returning video_url and task_id for async jobs. Developers reach for this skill when building products or agents that create video from reference material while preserving character style across shots. A prepare_r2v_request.py helper validates request JSON, async polling runs at 15–20 second intervals until SUCCEEDED, and outputs land in output/aliyun-wan-r2v/videos/. Validation uses py_compile on bundled scripts with evidence snapshots saved for reproducibility.

WAN reference-to-video API setup
Async job submit and polling
Reference media upload patterns
Generated clip retrieval
Pipeline hook examples

Alicloud Ai Video Wan R2v by the numbers

272 all-time installs (skills.sh)
Ranked #534 of 1,335 Generative Media skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-video-wan-r2v

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/cinience/alicloud-skills/alicloud-ai-video-wan-r2v.svg)](https://skillselion.com/skills/cinience/alicloud-skills/alicloud-ai-video-wan-r2v)

Installs	272
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

How do you generate video from reference clips on Alibaba Cloud?

Connect Alibaba Cloud WAN reference-to-video generation into products or agents that create video from reference images, clips, or prompts using managed generative APIs.

Who is it for?

Developers integrating Alibaba Wan R2V into agents or content pipelines that need style-consistent video from reference images or clips.

Skip if: Single-image-to-video without reference material should use aliyun-wan-i2v or aliyun-wan-video skills instead of R2V.

When should I use this skill?

User needs reference-to-video generation with Wan models, character style preservation, or multi-shot video from reference media.

What you get

Normalized R2V request JSON, async task_id, polled video_url, and evidence files under output/aliyun-wan-r2v/.

Normalized R2V request JSON
Generated video_url output
Polling evidence in output/aliyun-wan-r2v/

By the numbers

Version 1.0.0 skill supporting 2 Wan R2V model strings
Async polling at 15-20 second intervals until terminal status

Files

SKILL.mdMarkdownGitHub ↗

Category: provider

Model Studio Wan R2V

Validation

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

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

Output And Evidence

Save reference input metadata, request payloads, and task outputs in output/alicloud-ai-video-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 environment:

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.

Normalized interface (video.generate_reference)

Request

prompt (string, required)
reference_video (string | bytes, required)
reference_image (string | bytes, optional)
duration (number, optional)
fps (number, optional)
size (string, optional)
seed (int, optional)

Response

video_url (string)
task_id (string, when async)
request_id (string)

Async handling

Prefer async submission for production traffic.
Poll task result with 15-20s intervals.
Stop polling when SUCCEEDED or terminal failure status is returned.

Local helper script

Prepare a normalized request JSON and validate response schema:

.venv/bin/python skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py \
  --prompt "Generate a short montage with consistent character style" \
  --reference-video "https://example.com/reference.mp4"

Output location

Default output: output/alicloud-ai-video-wan-r2v/videos/
Override base dir with OUTPUT_DIR.

Workflow

1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating. 2) Run one minimal read-only query first to verify connectivity and permissions. 3) Execute the target operation with explicit parameters and bounded scope. 4) Verify results and save output/evidence files.

References

references/sources.md

interface:
  display_name: "Alibaba Cloud AI Video Wan R2V"
  short_description: "Wan reference-to-video workflows"
  default_prompt: "Use $alicloud-ai-video-wan-r2v to complete this ai/video reference-based generation task on Alibaba Cloud."

#!/usr/bin/env python3
"""Prepare and validate normalized request/response for Wan R2V."""

from __future__ import annotations

import argparse
import json
import sys
from pathlib import Path


def _load_json(path: str) -> dict:
    return json.loads(Path(path).read_text(encoding="utf-8"))


def main() -> None:
    parser = argparse.ArgumentParser(description="Prepare video.generate_reference request and validate response shape")
    parser.add_argument("--prompt", required=True)
    parser.add_argument("--reference-video", required=True)
    parser.add_argument("--reference-image")
    parser.add_argument("--duration", type=float)
    parser.add_argument("--fps", type=float)
    parser.add_argument("--size")
    parser.add_argument("--seed", type=int)
    parser.add_argument("--output", default="output/ai-video-wan-r2v/request.json")
    parser.add_argument("--validate-response", help="Path to JSON response file")
    args = parser.parse_args()

    req = {
        "prompt": args.prompt,
        "reference_video": args.reference_video,
    }
    if args.reference_image:
        req["reference_image"] = args.reference_image
    if args.duration is not None:
        req["duration"] = args.duration
    if args.fps is not None:
        req["fps"] = args.fps
    if args.size:
        req["size"] = args.size
    if args.seed is not None:
        req["seed"] = args.seed

    out = Path(args.output)
    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_text(json.dumps(req, ensure_ascii=False, indent=2), encoding="utf-8")

    result = {"ok": True, "request_path": str(out)}

    if args.validate_response:
        resp = _load_json(args.validate_response)
        if "video_url" not in resp and "task_id" not in resp:
            print(json.dumps({"ok": False, "error": "missing video_url and task_id"}, ensure_ascii=False))
            sys.exit(1)
        result["response_valid"] = True

    print(json.dumps(result, ensure_ascii=False))


if __name__ == "__main__":
    main()

Related skills

Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k

Ai Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665

Ai Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665

Ai Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665

Remotion RenderRender videos programmatically using React components and Remotion framework441k665

Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665

How it compares

Use alicloud-ai-video-wan-r2v when reference clips or images drive style; choose aliyun-wan-i2v for single-image-to-video without reference material.

FAQ

Which models does alicloud-ai-video-wan-r2v support?

alicloud-ai-video-wan-r2v supports two exact Wan R2V model strings: wan2.6-r2v-flash for lower latency and cost, and wan2.6-r2v for the standard reference-to-video endpoint.

How is alicloud-ai-video-wan-r2v different from i2v?

alicloud-ai-video-wan-r2v handles reference-to-video from reference video or image material for multi-shot style consistency, while i2v generates video from a single still image without reference clips.

How do you handle async results in alicloud-ai-video-wan-r2v?

alicloud-ai-video-wan-r2v prefers async submission, polling dashscope task endpoints every 15-20 seconds until task_status returns SUCCEEDED, then downloads output.video_url.

Generative Mediallmautomation