Wan AI Wan 2.6 Flash API | 定價與文件

wan-ai/wan-2-6/flash/image-to-video

從單張圖片生成動作自然、音畫同步且具有電影敘事感的影片，適合工作室、行銷團隊和創意開發者快速製作內容。

1. 快速開始

使用 RunComfy 的 API 執行 wan-ai/wan-2-6/flash/image-to-video。可接受的輸入與輸出請參閱模型的資料結構說明。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/flash/image-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A quiet, cinematic two-shot scene in a warm, softly lit bedroom bathroom. Nostalgic, intimate, slightly comedic tone. Photorealistic, shallow depth of field, gentle camera movement. No subtitles.\n\nShot 1 [0–5s]\nContinue from the first frame. Medium two-shot at eye level. Two children sit facing each other in a white bathtub. The girl lifts a small green bar of soap to her mouth like a microphone and whispers as if singing. The boy watches closely, curious and still. Warm tungsten light, cozy bedroom softly visible in the background. Subtle water ripples.\n\nShot 2 [5–10s]\nSlow push-in to a wider side angle revealing more of the room. The girl finishes, lowers the soap, then suddenly laughs. The boy relaxes and smiles back. The tension breaks into quiet laughter. Camera holds steady as the water gently moves. End on a calm, frozen childhood moment.",
    "img_url": "https://playgrounds-storage-public.runcomfy.net/tools/7313/media-files/input-1-1.png"
  }'

2. 身分驗證

將 YOUR_API_TOKEN 環境變數設為您的 API 金鑰（在個人資料中管理金鑰），並在每個請求的 Authorization 標頭中以 Bearer 權杖形式攜帶： Authorization: Bearer $YOUR_API_TOKEN。

3. API 參考

提交請求

提交非同步生成工作後，將立即取得 request_id 以及用於查詢狀態、取得結果與取消的 URL。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/flash/image-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A quiet, cinematic two-shot scene in a warm, softly lit bedroom bathroom. Nostalgic, intimate, slightly comedic tone. Photorealistic, shallow depth of field, gentle camera movement. No subtitles.\n\nShot 1 [0–5s]\nContinue from the first frame. Medium two-shot at eye level. Two children sit facing each other in a white bathtub. The girl lifts a small green bar of soap to her mouth like a microphone and whispers as if singing. The boy watches closely, curious and still. Warm tungsten light, cozy bedroom softly visible in the background. Subtle water ripples.\n\nShot 2 [5–10s]\nSlow push-in to a wider side angle revealing more of the room. The girl finishes, lowers the soap, then suddenly laughs. The boy relaxes and smiles back. The tension breaks into quiet laughter. Camera holds steady as the water gently moves. End on a calm, frozen childhood moment.",
    "img_url": "https://playgrounds-storage-public.runcomfy.net/tools/7313/media-files/input-1-1.png"
  }'

查詢請求狀態

依 request_id 取得目前狀態（「in_queue」、「in_progress」、「completed」或「cancelled」）。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

取得請求結果

取得指定 request_id 的最終輸出與中繼資料；若工作尚未完成，回應會回傳目前狀態，方便繼續輪詢。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

取消請求

透過 request_id 取消排隊中的工作；進行中的工作無法取消。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

4. 檔案輸入

託管檔案（URL）

請提供可公開存取的 HTTPS 位址。確保目標主機允許伺服器端抓取（無需登入或 Cookie）、未被限流或阻擋機器人。建議：圖片 ≤ 50 MB（約 4K），影片 ≤ 100 MB（約 720p 下 2–5 分鐘）。私人資產請使用穩定或預先簽署 URL。

5. 資料結構

輸入結構

{
  "type": "object",
  "title": "輸入結構",
  "required": [
    "prompt",
    "img_url"
  ],
  "properties": {
    "prompt": {
      "title": "提示詞",
      "description": "長度須少於 1500 個字元。",
      "type": "string",
      "default": "A quiet, cinematic two-shot scene in a warm, softly lit bedroom bathroom. Nostalgic, intimate, slightly comedic tone. Photorealistic, shallow depth of field, gentle camera movement. No subtitles.\n\nShot 1 [0–5s]\nContinue from the first frame. Medium two-shot at eye level. Two children sit facing each other in a white bathtub. The girl lifts a small green bar of soap to her mouth like a microphone and whispers as if singing. The boy watches closely, curious and still. Warm tungsten light, cozy bedroom softly visible in the background. Subtle water ripples.\n\nShot 2 [5–10s]\nSlow push-in to a wider side angle revealing more of the room. The girl finishes, lowers the soap, then suddenly laughs. The boy relaxes and smiles back. The tension breaks into quiet laughter. Camera holds steady as the water gently moves. End on a calm, frozen childhood moment."
    },
    "img_url": {
      "title": "圖片",
      "description": "圖片格式須為 jpg、jpeg、png、bmp 或 webp，檔案大小須小於 10 MB。",
      "type": "string",
      "validations": [
        {
          "validation_rule": "width_pixels>",
          "validation_value": 360,
          "validation_error": "上傳圖片的寬度與高度均須超過 360 像素。"
        },
        {
          "validation_rule": "height_pixels>",
          "validation_value": 360,
          "validation_error": "上傳圖片的寬度與高度均須超過 360 像素。"
        },
        {
          "validation_rule": "width_pixels<",
          "validation_value": 2000,
          "validation_error": "上傳圖片的寬度與高度均不得超過 2000 像素。"
        },
        {
          "validation_rule": "height_pixels<",
          "validation_value": 2000,
          "validation_error": "上傳圖片的寬度與高度均不得超過 2000 像素。"
        }
      ],
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7313/media-files/input-1-1.png"
    },
    "audio_url": {
      "title": "音訊",
      "description": "音訊格式須為 wav 或 mp3，時長須在 3–30 秒之間，檔案大小須小於 15 MB。",
      "type": "string"
    },
    "duration": {
      "title": "時長",
      "description": "",
      "type": "integer",
      "enum": [
        5,
        10,
        15
      ],
      "default": 5
    },
    "resolution": {
      "title": "解析度",
      "description": "",
      "type": "string",
      "enum": [
        "720P",
        "1080P"
      ],
      "default": "720P"
    },
    "shot_type": {
      "title": "鏡頭類型",
      "description": "shot_type 的優先順序高於 prompt。例如，將 shot_type 設為 single 後，即使提示詞要求多鏡頭，模型仍會生成單鏡頭影片。",
      "type": "string",
      "enum": [
        "multi",
        "single"
      ],
      "default": "multi"
    },
    "negative_prompt": {
      "title": "負向提示詞",
      "description": "",
      "type": "string"
    },
    "seed": {
      "title": "隨機種子",
      "description": "",
      "type": "integer",
      "maximum": 2147483647,
      "minimum": 0
    },
    "prompt_extend": {
      "title": "擴展提示詞",
      "description": "是否自動增強影片生成提示詞。",
      "type": "boolean",
      "default": true
    },
    "audio": {
      "title": "生成音訊",
      "description": "",
      "type": "boolean",
      "default": true
    }
  }
}

輸出結構

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "單張圖片 URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "單一影片 URL"
      },
      "images": {
        "type": "array",
        "description": "多張圖片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "多個影片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

RunComfy

RunComfy 是首選的 ComfyUI 平台，提供 ComfyUI 在線環境和服務，以及 ComfyUI 工作流程具有驚豔的視覺效果。 RunComfy還提供 AI Models, 幫助藝術家利用最新的AI工具創作出令人驚艷的藝術作品。

1. 快速開始

使用 RunComfy 的 API 執行 wan-ai/wan-2-6/flash/image-to-video。可接受的輸入與輸出請參閱模型的資料結構說明。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/flash/image-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A quiet, cinematic two-shot scene in a warm, softly lit bedroom bathroom. Nostalgic, intimate, slightly comedic tone. Photorealistic, shallow depth of field, gentle camera movement. No subtitles.\n\nShot 1 [0–5s]\nContinue from the first frame. Medium two-shot at eye level. Two children sit facing each other in a white bathtub. The girl lifts a small green bar of soap to her mouth like a microphone and whispers as if singing. The boy watches closely, curious and still. Warm tungsten light, cozy bedroom softly visible in the background. Subtle water ripples.\n\nShot 2 [5–10s]\nSlow push-in to a wider side angle revealing more of the room. The girl finishes, lowers the soap, then suddenly laughs. The boy relaxes and smiles back. The tension breaks into quiet laughter. Camera holds steady as the water gently moves. End on a calm, frozen childhood moment.",
    "img_url": "https://playgrounds-storage-public.runcomfy.net/tools/7313/media-files/input-1-1.png"
  }'

3. API 參考

提交請求

提交非同步生成工作後，將立即取得 request_id 以及用於查詢狀態、取得結果與取消的 URL。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/flash/image-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A quiet, cinematic two-shot scene in a warm, softly lit bedroom bathroom. Nostalgic, intimate, slightly comedic tone. Photorealistic, shallow depth of field, gentle camera movement. No subtitles.\n\nShot 1 [0–5s]\nContinue from the first frame. Medium two-shot at eye level. Two children sit facing each other in a white bathtub. The girl lifts a small green bar of soap to her mouth like a microphone and whispers as if singing. The boy watches closely, curious and still. Warm tungsten light, cozy bedroom softly visible in the background. Subtle water ripples.\n\nShot 2 [5–10s]\nSlow push-in to a wider side angle revealing more of the room. The girl finishes, lowers the soap, then suddenly laughs. The boy relaxes and smiles back. The tension breaks into quiet laughter. Camera holds steady as the water gently moves. End on a calm, frozen childhood moment.",
    "img_url": "https://playgrounds-storage-public.runcomfy.net/tools/7313/media-files/input-1-1.png"
  }'

查詢請求狀態

依 request_id 取得目前狀態（「in_queue」、「in_progress」、「completed」或「cancelled」）。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

取得請求結果

取得指定 request_id 的最終輸出與中繼資料；若工作尚未完成，回應會回傳目前狀態，方便繼續輪詢。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

取消請求

透過 request_id 取消排隊中的工作；進行中的工作無法取消。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

4. 檔案輸入

託管檔案（URL）

5. 資料結構

輸入結構

{
  "type": "object",
  "title": "輸入結構",
  "required": [
    "prompt",
    "img_url"
  ],
  "properties": {
    "prompt": {
      "title": "提示詞",
      "description": "長度須少於 1500 個字元。",
      "type": "string",
      "default": "A quiet, cinematic two-shot scene in a warm, softly lit bedroom bathroom. Nostalgic, intimate, slightly comedic tone. Photorealistic, shallow depth of field, gentle camera movement. No subtitles.\n\nShot 1 [0–5s]\nContinue from the first frame. Medium two-shot at eye level. Two children sit facing each other in a white bathtub. The girl lifts a small green bar of soap to her mouth like a microphone and whispers as if singing. The boy watches closely, curious and still. Warm tungsten light, cozy bedroom softly visible in the background. Subtle water ripples.\n\nShot 2 [5–10s]\nSlow push-in to a wider side angle revealing more of the room. The girl finishes, lowers the soap, then suddenly laughs. The boy relaxes and smiles back. The tension breaks into quiet laughter. Camera holds steady as the water gently moves. End on a calm, frozen childhood moment."
    },
    "img_url": {
      "title": "圖片",
      "description": "圖片格式須為 jpg、jpeg、png、bmp 或 webp，檔案大小須小於 10 MB。",
      "type": "string",
      "validations": [
        {
          "validation_rule": "width_pixels>",
          "validation_value": 360,
          "validation_error": "上傳圖片的寬度與高度均須超過 360 像素。"
        },
        {
          "validation_rule": "height_pixels>",
          "validation_value": 360,
          "validation_error": "上傳圖片的寬度與高度均須超過 360 像素。"
        },
        {
          "validation_rule": "width_pixels<",
          "validation_value": 2000,
          "validation_error": "上傳圖片的寬度與高度均不得超過 2000 像素。"
        },
        {
          "validation_rule": "height_pixels<",
          "validation_value": 2000,
          "validation_error": "上傳圖片的寬度與高度均不得超過 2000 像素。"
        }
      ],
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7313/media-files/input-1-1.png"
    },
    "audio_url": {
      "title": "音訊",
      "description": "音訊格式須為 wav 或 mp3，時長須在 3–30 秒之間，檔案大小須小於 15 MB。",
      "type": "string"
    },
    "duration": {
      "title": "時長",
      "description": "",
      "type": "integer",
      "enum": [
        5,
        10,
        15
      ],
      "default": 5
    },
    "resolution": {
      "title": "解析度",
      "description": "",
      "type": "string",
      "enum": [
        "720P",
        "1080P"
      ],
      "default": "720P"
    },
    "shot_type": {
      "title": "鏡頭類型",
      "description": "shot_type 的優先順序高於 prompt。例如，將 shot_type 設為 single 後，即使提示詞要求多鏡頭，模型仍會生成單鏡頭影片。",
      "type": "string",
      "enum": [
        "multi",
        "single"
      ],
      "default": "multi"
    },
    "negative_prompt": {
      "title": "負向提示詞",
      "description": "",
      "type": "string"
    },
    "seed": {
      "title": "隨機種子",
      "description": "",
      "type": "integer",
      "maximum": 2147483647,
      "minimum": 0
    },
    "prompt_extend": {
      "title": "擴展提示詞",
      "description": "是否自動增強影片生成提示詞。",
      "type": "boolean",
      "default": true
    },
    "audio": {
      "title": "生成音訊",
      "description": "",
      "type": "boolean",
      "default": true
    }
  }
}

輸出結構

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "單張圖片 URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "單一影片 URL"
      },
      "images": {
        "type": "array",
        "description": "多張圖片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "多個影片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

從單張圖片生成動作自然、音畫同步且具有電影敘事感的影片，適合工作室、行銷團隊和創意開發者快速製作內容。

目錄

1. 快速開始

2. 身分驗證

3. API 參考

提交請求

查詢請求狀態

取得請求結果

取消請求

4. 檔案輸入

託管檔案（URL）

5. 資料結構

輸入結構

輸出結構

從單張圖片生成動作自然、音畫同步且具有電影敘事感的影片，適合工作室、行銷團隊和創意開發者快速製作內容。

目錄

1. 快速開始

2. 身分驗證

3. API 參考

提交請求

查詢請求狀態

取得請求結果

取消請求

4. 檔案輸入

託管檔案（URL）

5. 資料結構

輸入結構

輸出結構

Wan 2.6 Flash：快速生成動作與音畫同步的寫實圖像轉影片 | RunComfy

從單張圖片生成動作自然、音畫同步且具有電影敘事感的影片，適合工作室、行銷團隊和創意開發者快速製作內容。

目錄

1. 快速開始

2. 身分驗證

3. API 參考

提交請求

查詢請求狀態

取得請求結果

取消請求

4. 檔案輸入

託管檔案（URL）

5. 資料結構

輸入結構

輸出結構

Wan 2.6 Flash：快速生成動作與音畫同步的寫實圖像轉影片 | RunComfy

從單張圖片生成動作自然、音畫同步且具有電影敘事感的影片，適合工作室、行銷團隊和創意開發者快速製作內容。

目錄

1. 快速開始

2. 身分驗證

3. API 參考

提交請求

查詢請求狀態

取得請求結果

取消請求

4. 檔案輸入

託管檔案（URL）

5. 資料結構

輸入結構

輸出結構