Alibaba WAN 2.6

alibaba/wan-2.6/reference-to-video

alibaba/wan-2.6/reference-to-video. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

관련 모델

Alibaba WAN 2.6 관련 모델 1

전체 매개변수, 출력 스키마 및 실시간 요금

AI 모델 API 마켓하나의 플랫폼, 모든 기능가장 인기이용약관이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.
prompt *Prompttextarea—≤ 1500 chars
negative_promptNegative Prompttextarea—≤ 1500 chars
sizeSizeselect1920*10801920*1080 | 1080*1920 | 1440*1440 | 1632*1248 | 1248*1632 | 1280*720 | 720*1280 | 960*960 | …
durationDurationslider52 ~ 10 · step 1
shot_typeShot Typeselectsinglesingle | multi
seedSeednumber—≥ 0

전체 매개변수, 출력 스키마 및 실시간 요금

자세히 보기하나의 플랫폼, 모든 기능이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.
videosarray<string>

API

이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6/reference-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "Replace the background in the video with a vibrant, bustling futuristic cityscape, featuring neon lights and flying cars.",
    "negative_prompt": "Avoid dark or gloomy scenes, and ensure no elements of destruction or chaos are present.",
    "size": "1920*1080",
    "duration": 7,
    "shot_type": "multi",
    "seed": 0
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6/reference-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "Replace the background in the video with a vibrant, bustling futuristic cityscape, featuring neon lights and flying cars.",
            "negative_prompt": "Avoid dark or gloomy scenes, and ensure no elements of destruction or chaos are present.",
            "size": "1920*1080",
            "duration": 7,
            "shot_type": "multi",
            "seed": 0
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.6/reference-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "Replace the background in the video with a vibrant, bustling futuristic cityscape, featuring neon lights and flying cars.",
      "negative_prompt": "Avoid dark or gloomy scenes, and ensure no elements of destruction or chaos are present.",
      "size": "1920*1080",
      "duration": 7,
      "shot_type": "multi",
      "seed": 0
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

API 문서

Alibaba WAN 2.6

Transform References into Videos Effortlessly

Alibaba WAN 2.6 Reference-to-Video model converts character, prop, or scene references—single or multi-view—into new video shots while preserving identity, style, and layout with smooth, coherent motion. It offers a ready-to-use REST inference API with top performance, no cold starts, and affordable pricing.

🚀 Key Features

  • Reference-driven Motion & Style: Mimic camera moves, pacing, and composition from your reference videos while following your prompt.
  • Up to Two Reference Videos: Blend style from one clip and motion from another, or use different angles of the same scene.
  • Cinematic Resolutions: Choose from 720p or 1080p (portrait or landscape).
  • Story-aware Generation: Works with prompt expansion and multishots to build richer, multi-shot sequences.
  • Audio-ready Pipeline: Optional audio field for workflows that need motion aligned to external sound.

🛠️ Technical Specifications

ParameterDescription
Model ArchitectureAlibaba WAN 2.6
Input FormatImage, Prompt, Negative Prompt, Audio (optional)
Output FormatVideo (MP4)
Resolution1280×720, 720×1280, 1920×1080, 1080×1920
Duration5 seconds or 10 seconds
Frame Rate30 FPS
LatencyNo cold start

💰 Pricing

Resolution groupPricing formula
720p sizes (1280720, 7201280, 960960, 8321088, 1088*832)8.7 credits x ceil(total_duration)
1080p/default sizes14.4 credits x ceil(total_duration)

total_duration is the generated duration plus the billed duration of reference video inputs.

💡 Best Use Cases

  • E-commerce: Generate high-quality videos for product showcases.
  • Social Media: Create platform-ready short video content for Reels, TikTok, etc.
  • Film Production: Provide stylized shots and scenes for filmmaking.
  • Advertising: Quickly generate brand-consistent advertisement videos.

🔗 Related Models

  • vidu/reference-to-video-q2: Ideal for anime-style edits, trailers, and storyboards.
  • google/veo3.1/reference-to-video: High-fidelity cinematic motion generation.
  • kwaivgi/kling-video-o1/reference-to-video: Great for copying camera language and pacing from sample clips.
  • bytedance/seedance-v1-lite/reference-to-video: Fast, style-consistent video generation.