Claude Opus 5 is now live on CometAPI →
Q

Wan2.7

每秒:$0.08
發布時間:May 31, 2026

Wan2.7 是一款面向高品質視覺合成並提升動作一致性的影片生成模型。適用於電影級內容創作與專業影片製作工作流程。

新
商業用途

Wan 2.7 的技術規格

ItemWan 2.7（影片套件）
ProviderAlibaba Tongyi Lab
Model familyWan 2.7 Video Suite
Architecture27B 參數 Mixture-of-Experts (MoE)
Input types文字、圖片、影片、音訊參考
Output types生成/編輯的影片片段（可選音訊）
Supported modes文字轉影片（T2V）、圖片轉影片（I2V）、參考轉影片（R2V）、影片編輯
Resolution720P 與 1080P 輸出
Video duration2–15 秒
Audio support原生音訊生成、語音參考、口型同步工作流程
Reference capability多參考圖片/影片、身份一致性
Character consistency依工作流程支援多個參考主體
Release generationWan 2.6 的主要後繼版本

什麼是 Wan 2.7？

Wan 2.7 是 Alibaba 的旗艦多模態影片生成套件，面向可控的 AI 影片製作工作流程，而非僅僅進行簡單的提示詞到影片生成。該模型家族將生成、編輯、續寫與基於參考的一致性整合為一體，使創作者能打造更強主體保真與場景控制的短片段。

不同於早期主要依賴提示詞品質的影片生成器，Wan 2.7 透過幀錨定、參考輸入、音訊同步與結構化多鏡頭流程來強調可控性。

Wan 2.7 的主要功能

  • Thinking Mode 規劃管線：模型在渲染前規劃場景構圖與運動，提升提示遵從度並降低連貫性失誤。
  • 首幀與末幀控制：使用者可定義開場與結尾幀，系統在兩者之間進行運動內插。
  • 基於參考的身份一致性：在多個鏡頭間維持角色外觀、服飾、物件與風格的一致。
  • 原生多模態工作流程：在同一流程中支援文字、圖片、音訊與影片參考。
  • 整合式音訊生成：可與影像同步生成背景音樂、環境聲與語音。
  • 支援編輯與續寫：可在不從零開始的情況下，延長、轉換或重塑既有影片。

Wan 2.7 的基準表現

相較於文字 LLM，Wan 2.7 的公開基準披露仍較有限，但第三方評估與社群測試顯示，其在運動穩定性、提示遵從度與可控性方面相較 Wan 2.6 有明顯提升。

生態系觀察回饋包括：

  • 相較早期 Wan 版本，運動連貫性更強。
  • 在第三方文字轉影片評測排行榜中的名次更高。
  • 多主體一致性與參考保留能力更佳。
  • 相較許多早期開源影片模型，音訊整合更好。

正式基準的透明度仍有限，因此對效能聲稱應審慎解讀。

Wan 2.7 與其他影片模型比較

FeatureWan 2.7Veo 3.1Seedance 2.0
原生音訊流程強強中等
基於參考的一致性強中等中等
首幀 + 末幀控制是部分有限
影片編輯流程是是有限
最高常見解析度1080P更高端的電影級輸出1080P
多參考支援強調中等中等

Wan 2.7 的限制

  • 與長片製作工具相比，片段時長較短。
  • 最高輸出 1080P，限制了超高解析度工作流程。
  • 快速運動畫面仍可能產生不穩定偽影。
  • 多參考工作流程增加了複雜度與提示工程需求。
  • 公開基準報告相對稀少。

代表性使用場景

  1. 保持角色一致性的短片與分鏡腳本。
  2. 具有音訊同步的行銷短片。
  3. 社群媒體影片生成。
  4. 產品視覺化與概念預告片。
  5. 影片續寫與場景插值工作流程。
  6. 基於參考的頭像與角色動畫。

如何在 CometAPI 中使用 WAN 2.7 影片 API

步驟 1：在 Kie Al Playground 試用 WAN 2.7 影片 API

首先，使用 CometAPI Playground 中的 WAN 2.7 影片 API 測試 WAN 2.7 的功能。上傳圖片、添加提示詞或使用參考，在整合 WAN 2.7 AI 影片至生產工作流程前預覽生成的 WAN 影片。

步驟 2：取得 WAN 2.7 API 金鑰並查閱 API 文件

從 CometAPI 主控台取得 WAN 2.7 API 金鑰並查閱文件。了解 WAN 2.7 影片 API 的端點、驗證與參數，以支援文字轉影片、圖片轉影片與 WAN 影片工作流程。

步驟 3：生成 WAN 2.7 AI 影片並整合至你的工作流程

使用 WAN 2.7 影片 API 透過提示詞、圖片或參考生成 WAN 2.7 AI 影片。將 WAN 2.7 的輸出整合到產品工作流程、內容管線或 AI 影片工具中，以實現可擴展的影片創作。

常見問題

Wan2.7 的定價

探索 Wan2.7 的競爭性定價，專為滿足各種預算和使用需求而設計。我們靈活的方案確保您只需為實際使用量付費，讓您能夠隨著需求增長輕鬆擴展。了解 Wan2.7 如何在保持成本可控的同時提升您的專案效果。

Wan Video Generation Pricing

Pricing (Per Second)

Model720p1080p
wan2.6$0.08$0.12
wan2.7$0.08$0.12

💡 Billed per second. Total cost = price per second × video duration (seconds).

Wan2.7 的範例程式碼和 API

存取完整的範例程式碼和 API 資源，以簡化您的 Wan2.7 整合流程。我們詳盡的文件提供逐步指引，協助您在專案中充分發揮 Wan2.7 的潛力。

# Create a video with wan2.7
# Step 1: Submit the video generation request
echo "Submitting video generation request..."
response=$(curl -s https://api.cometapi.com/v1/videos \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F "model=wan2.7" \
  -F "prompt=Create a cinematic detective sequence with clear timed shots. Shot 1 [0-2s]: a rainy city street at night, neon signs reflected in puddles. Shot 2 [2-4s]: a detective in a dark coat enters an old building. Shot 3 [4-5s]: close-up on a clue lit by a narrow flashlight beam." \
  -F "seconds=5" \
  -F "size=1280x720")

echo "Response: $response"

# Extract video_id from response (handle JSON with spaces like "id": "xxx")
video_id=$(echo "$response" | tr -d '
' | sed 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo "Video ID: $video_id"

# Step 2: Poll for progress until 100%
echo ""
echo "Checking video generation progress..."
while true; do
  status_response=$(curl -s "https://api.cometapi.com/v1/videos/$video_id" \
    -H "Authorization: Bearer $COMETAPI_KEY")

  progress=$(echo "$status_response" | grep -o '"progress"[[:space:]]*:[[:space:]]*"\?[^",}]*"\?' | head -1 | sed 's/.*:[[:space:]]*"\?//;s/"$//')
  status=$(echo "$status_response" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"status"[[:space:]]*:[[:space:]]*"//;s/"$//')

  echo "Progress: $progress, Status: $status"

  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ] || [ "$status" = "error" ]; then
    echo "Video generation failed!"
    exit 1
  fi

  if [ "$progress" = "100%" ] || [ "$progress" = "100" ] || [ "$status" = "completed" ] || [ "$status" = "success" ]; then
    echo "Video generation completed!"
    break
  fi

  sleep 10
done

# Step 3: Download the video to output directory
echo ""
echo "Downloading video to ./output/$video_id.mp4..."
mkdir -p ./output
curl -s "https://api.cometapi.com/v1/videos/$video_id/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "./output/$video_id.mp4"

if [ -f "./output/$video_id.mp4" ]; then
  echo "Video saved to ./output/$video_id.mp4"
  ls -la "./output/$video_id.mp4"
else
  echo "Failed to download video"
  exit 1
fi

cURL Code Example

# Create a video with wan2.7
# Step 1: Submit the video generation request
echo "Submitting video generation request..."
response=$(curl -s https://api.cometapi.com/v1/videos \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F "model=wan2.7" \
  -F "prompt=Create a cinematic detective sequence with clear timed shots. Shot 1 [0-2s]: a rainy city street at night, neon signs reflected in puddles. Shot 2 [2-4s]: a detective in a dark coat enters an old building. Shot 3 [4-5s]: close-up on a clue lit by a narrow flashlight beam." \
  -F "seconds=5" \
  -F "size=1280x720")

echo "Response: $response"

# Extract video_id from response (handle JSON with spaces like "id": "xxx")
video_id=$(echo "$response" | tr -d '\n' | sed 's/.*"id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo "Video ID: $video_id"

# Step 2: Poll for progress until 100%
echo ""
echo "Checking video generation progress..."
while true; do
  status_response=$(curl -s "https://api.cometapi.com/v1/videos/$video_id" \
    -H "Authorization: Bearer $COMETAPI_KEY")
  
  progress=$(echo "$status_response" | grep -o '"progress"[[:space:]]*:[[:space:]]*"\?[^",}]*"\?' | head -1 | sed 's/.*:[[:space:]]*"\?//;s/"$//')
  status=$(echo "$status_response" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"status"[[:space:]]*:[[:space:]]*"//;s/"$//')
  
  echo "Progress: $progress, Status: $status"
  
  if [ "$status" = "FAILURE" ] || [ "$status" = "failed" ] || [ "$status" = "error" ]; then
    echo "Video generation failed!"
    exit 1
  fi
  
  if [ "$progress" = "100%" ] || [ "$progress" = "100" ] || [ "$status" = "completed" ] || [ "$status" = "success" ]; then
    echo "Video generation completed!"
    break
  fi
  
  sleep 10
done

# Step 3: Download the video to output directory
echo ""
echo "Downloading video to ./output/$video_id.mp4..."
mkdir -p ./output
curl -s "https://api.cometapi.com/v1/videos/$video_id/content" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -o "./output/$video_id.mp4"

if [ -f "./output/$video_id.mp4" ]; then
  echo "Video saved to ./output/$video_id.mp4"
  ls -la "./output/$video_id.mp4"
else
  echo "Failed to download video"
  exit 1
fi

Python Code Example

# Create a video with wan2.7 using raw HTTP requests
import os
import time
import requests

api_key = os.environ.get("COMETAPI_KEY")
base_url = "https://api.cometapi.com/v1"
headers = {"Authorization": f"Bearer {api_key}"}

# Step 1: Submit the video generation request
print("Submitting video generation request...")
response = requests.post(
    f"{base_url}/videos",
    headers=headers,
    files={
        "model": (None, "wan2.7"),
        "prompt": (None, "Create a cinematic detective sequence with clear timed shots. Shot 1 [0-2s]: a rainy city street at night, neon signs reflected in puddles. Shot 2 [2-4s]: a detective in a dark coat enters an old building. Shot 3 [4-5s]: close-up on a clue lit by a narrow flashlight beam."),
        "seconds": (None, "5"),
        "size": (None, "1280x720"),
    },
)

result = response.json()
print(f"Response: {result}")

video_id = result.get("id") or result.get("task_id")
print(f"Video ID: {video_id}")

# Step 2: Poll for progress until 100%
print("\nChecking video generation progress...")
while True:
    try:
        status_response = requests.get(f"{base_url}/videos/{video_id}", headers=headers)
        status_result = status_response.json()

        data = status_result.get("data") or status_result
        progress = data.get("progress", "0%")
        status = data.get("status", "unknown")

        print(f"Progress: {progress}, Status: {status}")

        if status in ["FAILURE", "failed", "error"]:
            print("Video generation failed!")
            print(status_result)
            exit(1)

        if progress == "100%" or progress == 100 or status in ["completed", "success"]:
            print("Video generation completed!")
            break
    except Exception as e:
        print(f"Temporary error: {e}, retrying...")

    time.sleep(10)

# Step 3: Download the video to output directory
print(f"\nDownloading video to ./output/{video_id}.mp4...")
os.makedirs("./output", exist_ok=True)

video_response = requests.get(f"{base_url}/videos/{video_id}/content", headers=headers)

output_path = f"./output/{video_id}.mp4"
with open(output_path, "wb") as f:
    f.write(video_response.content)

if os.path.exists(output_path):
    file_size = os.path.getsize(output_path)
    print(f"Video saved to {output_path}")
    print(f"File size: {file_size} bytes")
else:
    print("Failed to download video")
    exit(1)

JavaScript Code Example

// Create a video with wan2.7 using raw HTTP requests
import fs from "fs";
import path from "path";

const apiKey = process.env.COMETAPI_KEY;
const baseUrl = "https://api.cometapi.com/v1";
const headers = { Authorization: `Bearer ${apiKey}` };

function sleep(ms) {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

// Step 1: Submit the video generation request
console.log("Submitting video generation request...");
const formData = new FormData();
formData.append("model", "wan2.7");
formData.append("prompt", "Create a cinematic detective sequence with clear timed shots. Shot 1 [0-2s]: a rainy city street at night, neon signs reflected in puddles. Shot 2 [2-4s]: a detective in a dark coat enters an old building. Shot 3 [4-5s]: close-up on a clue lit by a narrow flashlight beam.");
formData.append("seconds", "5");
formData.append("size", "1280x720");

const submitResponse = await fetch(`${baseUrl}/videos`, {
  method: "POST",
  headers,
  body: formData,
});

const result = await submitResponse.json();
console.log("Response:", JSON.stringify(result, null, 2));

const videoId = result.id || result.task_id;
console.log("Video ID:", videoId);

// Step 2: Poll for progress until 100%
console.log("\nChecking video generation progress...");
while (true) {
  try {
    const statusResponse = await fetch(`${baseUrl}/videos/${videoId}`, { headers });
    const statusResult = await statusResponse.json();
    const data = statusResult.data || statusResult;
    const progress = data.progress || "0%";
    const status = data.status || "unknown";

    console.log(`Progress: ${progress}, Status: ${status}`);

    if (status === "FAILURE" || status === "failed" || status === "error") {
      console.log("Video generation failed!");
      console.log(JSON.stringify(statusResult, null, 2));
      process.exit(1);
    }

    if (progress === "100%" || progress === 100 || status === "completed" || status === "success") {
      console.log("Video generation completed!");
      break;
    }
  } catch (e) {
    console.log(`Temporary error: ${e.message}, retrying...`);
  }

  await sleep(10000);
}

// Step 3: Download the video to output directory
console.log(`\nDownloading video to ./output/${videoId}.mp4...`);
fs.mkdirSync("./output", { recursive: true });

const videoResponse = await fetch(`${baseUrl}/videos/${videoId}/content`, { headers });
const outputPath = path.join("./output", `${videoId}.mp4`);
fs.writeFileSync(outputPath, Buffer.from(await videoResponse.arrayBuffer()));

if (fs.existsSync(outputPath)) {
  const stats = fs.statSync(outputPath);
  console.log(`Video saved to ${outputPath}`);
  console.log(`File size: ${stats.size} bytes`);
} else {
  console.log("Failed to download video");
  process.exit(1);
}

Wan2.7的版本

Wan2.7擁有多個快照的原因可能包括：更新後輸出結果存在差異需保留舊版快照以確保一致性、為開發者提供適應與遷移的過渡期，以及不同快照對應全球或區域端點以優化使用者體驗等潛在因素。各版本間的具體差異請參閱官方文件說明。

Version
wan2.7