Wan AI Wan 2.6 Image to Image API | 定价与文档

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

使用Wan 2.6 Image-to-Image通过精确的指令式编辑转换图像，同时保留风格和结构，实现无缝的视觉品牌重塑、产品重新设计和角色场景编辑，具备可扩展的浏览器AI性能。

1. 快速开始

使用 RunComfy 的 API 运行 wan-ai/wan-2-6/image-to-image。可接受的输入与输出请参阅模型的数据结构说明。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/image-to-image \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "On the left sits a monster, and on the right sits another monster. The two of them are like radio hosts, wearing headphones and sitting in a recording studio, discussing a topic.",
    "image_urls": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-1.png",
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-2.png"
    ]
  }'

2. 身份验证

将 YOUR_API_TOKEN 环境变量设置为您的 API 密钥（在个人资料中管理密钥），并在每个请求的 Authorization 标头中以 Bearer 令牌形式携带： Authorization: Bearer $YOUR_API_TOKEN。

3. API 参考

提交请求

提交异步生成任务，将立即获得 request_id 以及用于查询状态、获取结果和取消的 URL。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/image-to-image \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "On the left sits a monster, and on the right sits another monster. The two of them are like radio hosts, wearing headphones and sitting in a recording studio, discussing a topic.",
    "image_urls": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-1.png",
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-2.png"
    ]
  }'

查询请求状态

根据 request_id 获取当前状态（"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>"

获取请求结果

获取指定 request_id 的最终输出与元数据；若任务未完成，响应会返回当前状态，便于继续轮询。

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

取消请求

通过 request_id 取消排队中的任务；进行中的任务无法取消。

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

4. 文件输入

托管文件（URL）

请提供可公网访问的 HTTPS 地址。确保目标主机允许服务端拉取（无需登录或 Cookie）、未被限流或拦截爬虫。建议：图片 ≤ 50 MB（约 4K），视频 ≤ 100 MB（约 720p 下 2–5 分钟）。私有资源请使用稳定或预签名 URL。

5. 数据结构

输入结构

{
  "type": "object",
  "title": "输入结构",
  "required": [
    "prompt",
    "image_urls"
  ],
  "properties": {
    "prompt": {
      "title": "提示词",
      "description": "描述所需图像的文本提示词。应少于2000个字符。",
      "type": "string",
      "default": "On the left sits a monster, and on the right sits another monster. The two of them are like radio hosts, wearing headphones and sitting in a recording studio, discussing a topic."
    },
    "image_urls": {
      "title": "参考图像",
      "description": "用于编辑的参考图像。顺序很重要：在提示词中按\"图像1\"、\"图像2\"、\"图像3\"引用。",
      "type": "array",
      "items": {
        "type": "string",
        "format": "image_uri"
      },
      "minItems": 1,
      "maxItems": 3,
      "default": [
        "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-1.png",
        "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-2.png"
      ],
      "validations": [
        {
          "validation_rule": "file_size_mb<",
          "validation_value": 10,
          "validation_error": "文件大小必须小于10 MB。"
        },
        {
          "validation_rule": "width_pixels>",
          "validation_value": 384,
          "validation_error": "每个图像边至少需要384像素。"
        },
        {
          "validation_rule": "height_pixels>",
          "validation_value": 384,
          "validation_error": "每个图像边至少需要384像素。"
        },
        {
          "validation_rule": "width_pixels<",
          "validation_value": 5000,
          "validation_error": "每个图像边最多5000像素。"
        },
        {
          "validation_rule": "height_pixels<",
          "validation_value": 5000,
          "validation_error": "每个图像边最多5000像素。"
        }
      ]
    },
    "negative_prompt": {
      "title": "负面提示词",
      "description": "生成图像中需要避免的内容。",
      "type": "string",
      "default": "low resolution, error, worst quality, low quality, deformed, extra fingers",
      "maxLength": 500
    },
    "image_size": {
      "title": "宽高比（宽:高）",
      "description": "",
      "type": "string",
      "enum": [
        "1024*1024 (1:1)",
        "800*1200 (2:3)",
        "1200*800 (3:2)",
        "960*1280 (3:4)",
        "1280*960 (4:3)",
        "720*1280 (9:16)",
        "1280*720 (16:9)",
        "1344*576 (21:9)"
      ],
      "default": "1024*1024 (1:1)"
    },
    "seed": {
      "title": "种子",
      "description": "用于可复现性的随机种子。相同的种子产生更一致的结果。",
      "type": "integer",
      "minimum": 0,
      "maximum": 2147483647,
      "default": 0
    },
    "prompt_extend": {
      "title": "魔法提示词",
      "description": "是否扩展提示词。如果启用，提示词将通过魔法提示词扩展。",
      "type": "boolean",
      "default": true
    }
  }
}

输出结构

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "单张图片 URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "单个视频 URL"
      },
      "images": {
        "type": "array",
        "description": "多张图片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "多个视频 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

RunComfy

RunComfy 是首选的 ComfyUI 平台，提供 ComfyUI 在线环境和服务，以及 ComfyUI 工作流具有惊艳的视觉效果。 RunComfy还提供 AI Models, 帮助艺术家利用最新的AI工具创作出令人惊叹的艺术作品。

1. 快速开始

使用 RunComfy 的 API 运行 wan-ai/wan-2-6/image-to-image。可接受的输入与输出请参阅模型的数据结构说明。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/image-to-image \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "On the left sits a monster, and on the right sits another monster. The two of them are like radio hosts, wearing headphones and sitting in a recording studio, discussing a topic.",
    "image_urls": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-1.png",
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-2.png"
    ]
  }'

3. API 参考

提交请求

提交异步生成任务，将立即获得 request_id 以及用于查询状态、获取结果和取消的 URL。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-6/image-to-image \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "On the left sits a monster, and on the right sits another monster. The two of them are like radio hosts, wearing headphones and sitting in a recording studio, discussing a topic.",
    "image_urls": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-1.png",
      "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-2.png"
    ]
  }'

查询请求状态

根据 request_id 获取当前状态（"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>"

获取请求结果

获取指定 request_id 的最终输出与元数据；若任务未完成，响应会返回当前状态，便于继续轮询。

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

取消请求

通过 request_id 取消排队中的任务；进行中的任务无法取消。

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

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

{
  "type": "object",
  "title": "输入结构",
  "required": [
    "prompt",
    "image_urls"
  ],
  "properties": {
    "prompt": {
      "title": "提示词",
      "description": "描述所需图像的文本提示词。应少于2000个字符。",
      "type": "string",
      "default": "On the left sits a monster, and on the right sits another monster. The two of them are like radio hosts, wearing headphones and sitting in a recording studio, discussing a topic."
    },
    "image_urls": {
      "title": "参考图像",
      "description": "用于编辑的参考图像。顺序很重要：在提示词中按\"图像1\"、\"图像2\"、\"图像3\"引用。",
      "type": "array",
      "items": {
        "type": "string",
        "format": "image_uri"
      },
      "minItems": 1,
      "maxItems": 3,
      "default": [
        "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-1.png",
        "https://playgrounds-storage-public.runcomfy.net/tools/7305/media-files/input-1-2.png"
      ],
      "validations": [
        {
          "validation_rule": "file_size_mb<",
          "validation_value": 10,
          "validation_error": "文件大小必须小于10 MB。"
        },
        {
          "validation_rule": "width_pixels>",
          "validation_value": 384,
          "validation_error": "每个图像边至少需要384像素。"
        },
        {
          "validation_rule": "height_pixels>",
          "validation_value": 384,
          "validation_error": "每个图像边至少需要384像素。"
        },
        {
          "validation_rule": "width_pixels<",
          "validation_value": 5000,
          "validation_error": "每个图像边最多5000像素。"
        },
        {
          "validation_rule": "height_pixels<",
          "validation_value": 5000,
          "validation_error": "每个图像边最多5000像素。"
        }
      ]
    },
    "negative_prompt": {
      "title": "负面提示词",
      "description": "生成图像中需要避免的内容。",
      "type": "string",
      "default": "low resolution, error, worst quality, low quality, deformed, extra fingers",
      "maxLength": 500
    },
    "image_size": {
      "title": "宽高比（宽:高）",
      "description": "",
      "type": "string",
      "enum": [
        "1024*1024 (1:1)",
        "800*1200 (2:3)",
        "1200*800 (3:2)",
        "960*1280 (3:4)",
        "1280*960 (4:3)",
        "720*1280 (9:16)",
        "1280*720 (16:9)",
        "1344*576 (21:9)"
      ],
      "default": "1024*1024 (1:1)"
    },
    "seed": {
      "title": "种子",
      "description": "用于可复现性的随机种子。相同的种子产生更一致的结果。",
      "type": "integer",
      "minimum": 0,
      "maximum": 2147483647,
      "default": 0
    },
    "prompt_extend": {
      "title": "魔法提示词",
      "description": "是否扩展提示词。如果启用，提示词将通过魔法提示词扩展。",
      "type": "boolean",
      "default": true
    }
  }
}

输出结构

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "单张图片 URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "单个视频 URL"
      },
      "images": {
        "type": "array",
        "description": "多张图片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "多个视频 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

使用Wan 2.6 Image-to-Image通过精确的指令式编辑转换图像，同时保留风格和结构，实现无缝的视觉品牌重塑、产品重新设计和角色场景编辑，具备可扩展的浏览器AI性能。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构

使用Wan 2.6 Image-to-Image通过精确的指令式编辑转换图像，同时保留风格和结构，实现无缝的视觉品牌重塑、产品重新设计和角色场景编辑，具备可扩展的浏览器AI性能。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构

Wan 2.6 Image-to-Image：高精度视觉编辑与风格迁移 | RunComfy

使用Wan 2.6 Image-to-Image通过精确的指令式编辑转换图像，同时保留风格和结构，实现无缝的视觉品牌重塑、产品重新设计和角色场景编辑，具备可扩展的浏览器AI性能。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构

Wan 2.6 Image-to-Image：高精度视觉编辑与风格迁移 | RunComfy

使用Wan 2.6 Image-to-Image通过精确的指令式编辑转换图像，同时保留风格和结构，实现无缝的视觉品牌重塑、产品重新设计和角色场景编辑，具备可扩展的浏览器AI性能。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构