Aliyun Wan R2v

Name: Aliyun Wan R2v
Author: cinience

cinience/alicloud-skills

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

Generates reference-based multi-shot videos from reference video or image material with Alibaba Cloud Model Studio Wan R2V models.

About

This skill builds reference-to-video requests for Model Studio Wan R2V models, preserving character or style from reference media. A developer uses it to produce multi-shot videos anchored to reference input, distinct from single-image i2v.

Models wan2.6-r2v-flash and wan2.6-r2v, flash favored for lower latency
Async submission with reference_video required and optional reference_image

Aliyun Wan R2v by the numbers

52 all-time installs (skills.sh)
Ranked #884 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 aliyun-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/aliyun-wan-r2v.svg)](https://skillselion.com/skills/cinience/alicloud-skills/aliyun-wan-r2v)

Installs	52
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

What it does

Generates reference-based multi-shot videos from reference video or image material with Alibaba Cloud Model Studio Wan R2V models.

Files

SKILL.mdMarkdownGitHub ↗

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 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/aliyun-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/aliyun-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 $aliyun-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()