Wan AI Wan 2.1 LoRA API | 定價與文件

wan-ai/wan-2-1/lora

應用一個自訂 Wan 2.1 LoRA，根據文字或圖片產生影片，並設定解析度、長寬比、影格數、取樣、強度與種子。

1. 快速開始

使用 RunComfy 的 API 執行 wan-ai/wan-2-1/lora。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-2-1/lora \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A vast circular library of glowing memory orbs stretches in all directions, with tall curved shelves extending upward. Each orb contains a different memory, glowing in various colors - yellow for joy, blue for sadness, red for anger, purple for fear, and green for disgust. In the foreground, two characters - a small blue figure with glasses and a tall slender yellow figure with bright blue hair - are examining a particularly bright memory orb. Light streams cascade through the enormous room, creating dramatic beams between the shelves. The space has a warm ambient glow with dramatic shadows. Small maintenance worker characters in uniform can be seen in the background, carefully organizing orbs on distant shelves. The rendering features Pixar's characteristic polished surfaces with subtle reflections and depth-of-field blur for distant elements.",
    "lora_url": "https://playgrounds-storage-public.runcomfy.net/models/wan2.1/lora/Remade-AI/Pixar/pixar_10_epochs.safetensors"
  }'

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-2-1/lora \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A vast circular library of glowing memory orbs stretches in all directions, with tall curved shelves extending upward. Each orb contains a different memory, glowing in various colors - yellow for joy, blue for sadness, red for anger, purple for fear, and green for disgust. In the foreground, two characters - a small blue figure with glasses and a tall slender yellow figure with bright blue hair - are examining a particularly bright memory orb. Light streams cascade through the enormous room, creating dramatic beams between the shelves. The space has a warm ambient glow with dramatic shadows. Small maintenance worker characters in uniform can be seen in the background, carefully organizing orbs on distant shelves. The rendering features Pixar's characteristic polished surfaces with subtle reflections and depth-of-field blur for distant elements.",
    "lora_url": "https://playgrounds-storage-public.runcomfy.net/models/wan2.1/lora/Remade-AI/Pixar/pixar_10_epochs.safetensors"
  }'

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",
    "lora_url"
  ],
  "properties": {
    "lora_url": {
      "title": "Wan 2.1 LoRA URL",
      "description": "必填的 Hugging Face 或 Civitai 連結。每次產生只能使用一個 LoRA。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/models/wan2.1/lora/Remade-AI/Pixar/pixar_10_epochs.safetensors"
    },
    "model": {
      "title": "Wan 2.1 基礎模型",
      "description": "可選擇 1.3b 或 14b，預設值為 14b。",
      "type": "string",
      "enum": [
        "1.3b",
        "14b"
      ],
      "default": "14b"
    },
    "prompt": {
      "title": "提示詞",
      "description": "必填。描述影片主體、場景、動作、風格與鏡頭運動。",
      "type": "string",
      "default": "A vast circular library of glowing memory orbs stretches in all directions, with tall curved shelves extending upward. Each orb contains a different memory, glowing in various colors - yellow for joy, blue for sadness, red for anger, purple for fear, and green for disgust. In the foreground, two characters - a small blue figure with glasses and a tall slender yellow figure with bright blue hair - are examining a particularly bright memory orb. Light streams cascade through the enormous room, creating dramatic beams between the shelves. The space has a warm ambient glow with dramatic shadows. Small maintenance worker characters in uniform can be seen in the background, carefully organizing orbs on distant shelves. The rendering features Pixar's characteristic polished surfaces with subtle reflections and depth-of-field blur for distant elements."
    },
    "image": {
      "title": "輸入圖片",
      "description": "可選。用於圖片轉影片的來源圖片；僅根據文字產生時請留空。",
      "type": "string"
    },
    "resolution": {
      "title": "解析度",
      "description": "可選擇 480p 或 720p，預設值為 480p。",
      "type": "string",
      "enum": [
        "480p",
        "720p"
      ],
      "default": "480p"
    },
    "aspect_ratio": {
      "title": "長寬比（寬:高）",
      "description": "可選擇 16:9、1:1 或 9:16，預設值為 16:9。",
      "type": "string",
      "enum": [
        "16:9",
        "1:1",
        "9:16"
      ],
      "default": "16:9"
    },
    "negative_prompt": {
      "title": "負向提示詞",
      "description": "可選。描述不希望出現在影片中的視覺元素。",
      "type": "string",
      "default": ""
    },
    "sample_guide_scale": {
      "title": "提示詞強度",
      "description": "控制輸出遵循提示詞的程度。範圍為 0–10，預設值為 5。",
      "maximum": 10,
      "minimum": 0,
      "type": "float",
      "default": 5
    },
    "lora_strength_model": {
      "title": "LoRA 強度",
      "description": "控制 LoRA 對結果的影響。數值越高，效果越強。範圍為 0–1，預設值為 1。",
      "maximum": 1,
      "minimum": 0,
      "type": "float",
      "default": 1
    },
    "sample_steps": {
      "title": "取樣步數",
      "description": "可設為 1–60，預設值為 30。增加步數會提高積分費用。",
      "type": "integer",
      "default": 30,
      "maximum": 60,
      "minimum": 1
    },
    "seed": {
      "title": "種子",
      "description": "用於重現相近結果或產生不同版本的整數，預設值為 80682279。",
      "type": "integer",
      "default": 80682279
    },
    "frames": {
      "title": "影格數",
      "description": "可選擇 17、33、49、65 或 81 影格。",
      "type": "integer",
      "enum": [
        17,
        33,
        49,
        65,
        81
      ]
    },
    "sample_shift": {
      "title": "取樣偏移",
      "description": "範圍為 0–10 的取樣偏移設定。",
      "maximum": 10,
      "minimum": 0,
      "type": "float"
    },
    "fast_mode": {
      "title": "快速模式",
      "description": "可選擇 Off、Balanced 或 Fast。提高處理速度可能會降低準確度。",
      "type": "string",
      "enum": [
        "Off",
        "Balanced",
        "Fast"
      ]
    }
  }
}

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-2-1/lora。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-2-1/lora \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A vast circular library of glowing memory orbs stretches in all directions, with tall curved shelves extending upward. Each orb contains a different memory, glowing in various colors - yellow for joy, blue for sadness, red for anger, purple for fear, and green for disgust. In the foreground, two characters - a small blue figure with glasses and a tall slender yellow figure with bright blue hair - are examining a particularly bright memory orb. Light streams cascade through the enormous room, creating dramatic beams between the shelves. The space has a warm ambient glow with dramatic shadows. Small maintenance worker characters in uniform can be seen in the background, carefully organizing orbs on distant shelves. The rendering features Pixar's characteristic polished surfaces with subtle reflections and depth-of-field blur for distant elements.",
    "lora_url": "https://playgrounds-storage-public.runcomfy.net/models/wan2.1/lora/Remade-AI/Pixar/pixar_10_epochs.safetensors"
  }'

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-2-1/lora \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "A vast circular library of glowing memory orbs stretches in all directions, with tall curved shelves extending upward. Each orb contains a different memory, glowing in various colors - yellow for joy, blue for sadness, red for anger, purple for fear, and green for disgust. In the foreground, two characters - a small blue figure with glasses and a tall slender yellow figure with bright blue hair - are examining a particularly bright memory orb. Light streams cascade through the enormous room, creating dramatic beams between the shelves. The space has a warm ambient glow with dramatic shadows. Small maintenance worker characters in uniform can be seen in the background, carefully organizing orbs on distant shelves. The rendering features Pixar's characteristic polished surfaces with subtle reflections and depth-of-field blur for distant elements.",
    "lora_url": "https://playgrounds-storage-public.runcomfy.net/models/wan2.1/lora/Remade-AI/Pixar/pixar_10_epochs.safetensors"
  }'

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",
    "lora_url"
  ],
  "properties": {
    "lora_url": {
      "title": "Wan 2.1 LoRA URL",
      "description": "必填的 Hugging Face 或 Civitai 連結。每次產生只能使用一個 LoRA。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/models/wan2.1/lora/Remade-AI/Pixar/pixar_10_epochs.safetensors"
    },
    "model": {
      "title": "Wan 2.1 基礎模型",
      "description": "可選擇 1.3b 或 14b，預設值為 14b。",
      "type": "string",
      "enum": [
        "1.3b",
        "14b"
      ],
      "default": "14b"
    },
    "prompt": {
      "title": "提示詞",
      "description": "必填。描述影片主體、場景、動作、風格與鏡頭運動。",
      "type": "string",
      "default": "A vast circular library of glowing memory orbs stretches in all directions, with tall curved shelves extending upward. Each orb contains a different memory, glowing in various colors - yellow for joy, blue for sadness, red for anger, purple for fear, and green for disgust. In the foreground, two characters - a small blue figure with glasses and a tall slender yellow figure with bright blue hair - are examining a particularly bright memory orb. Light streams cascade through the enormous room, creating dramatic beams between the shelves. The space has a warm ambient glow with dramatic shadows. Small maintenance worker characters in uniform can be seen in the background, carefully organizing orbs on distant shelves. The rendering features Pixar's characteristic polished surfaces with subtle reflections and depth-of-field blur for distant elements."
    },
    "image": {
      "title": "輸入圖片",
      "description": "可選。用於圖片轉影片的來源圖片；僅根據文字產生時請留空。",
      "type": "string"
    },
    "resolution": {
      "title": "解析度",
      "description": "可選擇 480p 或 720p，預設值為 480p。",
      "type": "string",
      "enum": [
        "480p",
        "720p"
      ],
      "default": "480p"
    },
    "aspect_ratio": {
      "title": "長寬比（寬:高）",
      "description": "可選擇 16:9、1:1 或 9:16，預設值為 16:9。",
      "type": "string",
      "enum": [
        "16:9",
        "1:1",
        "9:16"
      ],
      "default": "16:9"
    },
    "negative_prompt": {
      "title": "負向提示詞",
      "description": "可選。描述不希望出現在影片中的視覺元素。",
      "type": "string",
      "default": ""
    },
    "sample_guide_scale": {
      "title": "提示詞強度",
      "description": "控制輸出遵循提示詞的程度。範圍為 0–10，預設值為 5。",
      "maximum": 10,
      "minimum": 0,
      "type": "float",
      "default": 5
    },
    "lora_strength_model": {
      "title": "LoRA 強度",
      "description": "控制 LoRA 對結果的影響。數值越高，效果越強。範圍為 0–1，預設值為 1。",
      "maximum": 1,
      "minimum": 0,
      "type": "float",
      "default": 1
    },
    "sample_steps": {
      "title": "取樣步數",
      "description": "可設為 1–60，預設值為 30。增加步數會提高積分費用。",
      "type": "integer",
      "default": 30,
      "maximum": 60,
      "minimum": 1
    },
    "seed": {
      "title": "種子",
      "description": "用於重現相近結果或產生不同版本的整數，預設值為 80682279。",
      "type": "integer",
      "default": 80682279
    },
    "frames": {
      "title": "影格數",
      "description": "可選擇 17、33、49、65 或 81 影格。",
      "type": "integer",
      "enum": [
        17,
        33,
        49,
        65,
        81
      ]
    },
    "sample_shift": {
      "title": "取樣偏移",
      "description": "範圍為 0–10 的取樣偏移設定。",
      "maximum": 10,
      "minimum": 0,
      "type": "float"
    },
    "fast_mode": {
      "title": "快速模式",
      "description": "可選擇 Off、Balanced 或 Fast。提高處理速度可能會降低準確度。",
      "type": "string",
      "enum": [
        "Off",
        "Balanced",
        "Fast"
      ]
    }
  }
}

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"
        }
      }
    }
  }
}

應用一個自訂 Wan 2.1 LoRA，根據文字或圖片產生影片，並設定解析度、長寬比、影格數、取樣、強度與種子。

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

應用一個自訂 Wan 2.1 LoRA，根據文字或圖片產生影片，並設定解析度、長寬比、影格數、取樣、強度與種子。

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 2.1 LoRA 自訂影片產生器 | RunComfy

應用一個自訂 Wan 2.1 LoRA，根據文字或圖片產生影片，並設定解析度、長寬比、影格數、取樣、強度與種子。

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 2.1 LoRA 自訂影片產生器 | RunComfy

應用一個自訂 Wan 2.1 LoRA，根據文字或圖片產生影片，並設定解析度、長寬比、影格數、取樣、強度與種子。

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