Happyhorse HappyHorse 1.0 Reference to Video API | 定价与文档

happyhorse/happyhorse-1.0/reference-to-video

HappyHorse 1.0 参考视频融合了多达 9 个参考图像和文本提示，可在 RunComfy 上生成 3-15 秒的 720P/1080P 剪辑 - 使用角色 1/角色 2 标签锁定角色、服装和道具。

1. 快速开始

使用 RunComfy 的 API 运行 happyhorse/happyhorse-1.0/reference-to-video。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/happyhorse/happyhorse-1.0/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "image_url_1": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png",
    "prompt": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look."
  }'

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/happyhorse/happyhorse-1.0/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "image_url_1": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png",
    "prompt": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look."
  }'

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": [
    "image_url_1",
    "prompt"
  ],
  "properties": {
    "image_url_1": {
      "title": "参考图像 1（角色 1）",
      "description": "第一个参考图像。在提示中将此主题标记为“character1”。格式：JPEG、JPG、PNG 或 WEBP。短边≥400px，建议720P或更高，最大10MB。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png"
    },
    "image_url_2": {
      "title": "参考图像 2（字符 2）",
      "description": "可选的第二个参考图像。在提示中将此主题标记为“character2”。格式：JPEG、JPG、PNG 或 WEBP。留空可跳过。",
      "type": "string"
    },
    "image_url_3": {
      "title": "参考图像 3（角色 3）",
      "description": "可选的第三个参考图像。在提示中将此主题标记为“character3”。格式：JPEG、JPG、PNG 或 WEBP。留空可跳过。",
      "type": "string"
    },
    "image_url_4": {
      "title": "参考图像 4（字符 4）",
      "description": "可选的第四个参考图像。在提示中将此主题标记为“character4”。留空可跳过。",
      "type": "string"
    },
    "image_url_5": {
      "title": "参考图像 5（字符 5）",
      "description": "可选的第五个参考图像。在提示中将此主题标记为“character5”。留空可跳过。",
      "type": "string"
    },
    "image_url_6": {
      "title": "参考图像 6（字符 6）",
      "description": "可选的第六参考图像。在提示中将此主题标记为“character6”。留空可跳过。",
      "type": "string"
    },
    "image_url_7": {
      "title": "参考图像 7（字符 7）",
      "description": "可选的第七个参考图像。在提示中将此主题标记为“character7”。留空可跳过。",
      "type": "string"
    },
    "image_url_8": {
      "title": "参考图像 8（字符 8）",
      "description": "可选的第八个参考图像。在提示中将此主题标记为“character8”。留空可跳过。",
      "type": "string"
    },
    "image_url_9": {
      "title": "参考图像 9（字符 9）",
      "description": "可选的第九个参考图像。在提示中将此主题标记为“character9”。留空可跳过。",
      "type": "string"
    },
    "prompt": {
      "title": "提示词",
      "description": "描述场景、动作、摄像机和灯光。按照上面出现的顺序，使用字符 1、字符 2、字符 3 ... 来引用每个参考图像。最多 2500 个中文/5000 个非中文字符。",
      "type": "string",
      "default": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look.",
      "maxLength": 5000
    },
    "aspect_ratio": {
      "title": "纵横比（宽：高）",
      "description": "输出视频宽高比。",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1",
        "4:3",
        "3:4"
      ],
      "default": "16:9"
    },
    "resolution": {
      "title": "分辨率",
      "description": "输出视频分辨率。该模型支持 720P 或 1080P。",
      "type": "string",
      "enum": [
        "720P",
        "1080P"
      ],
      "default": "1080P"
    },
    "duration": {
      "title": "时长",
      "description": "输出视频持续时间（以秒为单位）。允许值：3–15。",
      "type": "integer",
      "enum": [
        3,
        4,
        5,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
      ],
      "default": 5
    },
    "seed": {
      "title": "种子",
      "description": "可繁殖世代的可选种子。使用 0 让提供者随机化。",
      "type": "integer",
      "minimum": 0,
      "maximum": 2147483647,
      "default": 0
    },
    "watermark": {
      "title": "水印",
      "description": "是否在生成的视频上保留提供商水印。",
      "type": "boolean",
      "default": false
    }
  }
}

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 happyhorse/happyhorse-1.0/reference-to-video。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/happyhorse/happyhorse-1.0/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "image_url_1": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png",
    "prompt": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look."
  }'

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/happyhorse/happyhorse-1.0/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "image_url_1": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png",
    "prompt": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look."
  }'

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": [
    "image_url_1",
    "prompt"
  ],
  "properties": {
    "image_url_1": {
      "title": "参考图像 1（角色 1）",
      "description": "第一个参考图像。在提示中将此主题标记为“character1”。格式：JPEG、JPG、PNG 或 WEBP。短边≥400px，建议720P或更高，最大10MB。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7347/media-files/ref-promo-1.png"
    },
    "image_url_2": {
      "title": "参考图像 2（字符 2）",
      "description": "可选的第二个参考图像。在提示中将此主题标记为“character2”。格式：JPEG、JPG、PNG 或 WEBP。留空可跳过。",
      "type": "string"
    },
    "image_url_3": {
      "title": "参考图像 3（角色 3）",
      "description": "可选的第三个参考图像。在提示中将此主题标记为“character3”。格式：JPEG、JPG、PNG 或 WEBP。留空可跳过。",
      "type": "string"
    },
    "image_url_4": {
      "title": "参考图像 4（字符 4）",
      "description": "可选的第四个参考图像。在提示中将此主题标记为“character4”。留空可跳过。",
      "type": "string"
    },
    "image_url_5": {
      "title": "参考图像 5（字符 5）",
      "description": "可选的第五个参考图像。在提示中将此主题标记为“character5”。留空可跳过。",
      "type": "string"
    },
    "image_url_6": {
      "title": "参考图像 6（字符 6）",
      "description": "可选的第六参考图像。在提示中将此主题标记为“character6”。留空可跳过。",
      "type": "string"
    },
    "image_url_7": {
      "title": "参考图像 7（字符 7）",
      "description": "可选的第七个参考图像。在提示中将此主题标记为“character7”。留空可跳过。",
      "type": "string"
    },
    "image_url_8": {
      "title": "参考图像 8（字符 8）",
      "description": "可选的第八个参考图像。在提示中将此主题标记为“character8”。留空可跳过。",
      "type": "string"
    },
    "image_url_9": {
      "title": "参考图像 9（字符 9）",
      "description": "可选的第九个参考图像。在提示中将此主题标记为“character9”。留空可跳过。",
      "type": "string"
    },
    "prompt": {
      "title": "提示词",
      "description": "描述场景、动作、摄像机和灯光。按照上面出现的顺序，使用字符 1、字符 2、字符 3 ... 来引用每个参考图像。最多 2500 个中文/5000 个非中文字符。",
      "type": "string",
      "default": "Cinematic medium close-up. The young woman (character1) with natural blonde hair, blue eyes, and light freckles sits in a bright European-style café by a window, warm morning light on her face. She glances up from her book, gives a warm candid smile toward camera, then returns her gaze to the page. Slow dolly-in, shallow depth of field, identity-locked face and freckle pattern from the reference, soft background bokeh, 8K film look.",
      "maxLength": 5000
    },
    "aspect_ratio": {
      "title": "纵横比（宽：高）",
      "description": "输出视频宽高比。",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1",
        "4:3",
        "3:4"
      ],
      "default": "16:9"
    },
    "resolution": {
      "title": "分辨率",
      "description": "输出视频分辨率。该模型支持 720P 或 1080P。",
      "type": "string",
      "enum": [
        "720P",
        "1080P"
      ],
      "default": "1080P"
    },
    "duration": {
      "title": "时长",
      "description": "输出视频持续时间（以秒为单位）。允许值：3–15。",
      "type": "integer",
      "enum": [
        3,
        4,
        5,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
      ],
      "default": 5
    },
    "seed": {
      "title": "种子",
      "description": "可繁殖世代的可选种子。使用 0 让提供者随机化。",
      "type": "integer",
      "minimum": 0,
      "maximum": 2147483647,
      "default": 0
    },
    "watermark": {
      "title": "水印",
      "description": "是否在生成的视频上保留提供商水印。",
      "type": "boolean",
      "default": false
    }
  }
}

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"
        }
      }
    }
  }
}

HappyHorse 1.0 参考视频融合了多达 9 个参考图像和文本提示，可在 RunComfy 上生成 3-15 秒的 720P/1080P 剪辑 - 使用角色 1/角色 2 标签锁定角色、服装和道具。

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

HappyHorse 1.0 参考视频融合了多达 9 个参考图像和文本提示，可在 RunComfy 上生成 3-15 秒的 720P/1080P 剪辑 - 使用角色 1/角色 2 标签锁定角色、服装和道具。

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

HappyHorse 1.0 参考视频：多图像主题到视频 AI 模型 | Models and API | RunComfy

HappyHorse 1.0 参考视频融合了多达 9 个参考图像和文本提示，可在 RunComfy 上生成 3-15 秒的 720P/1080P 剪辑 - 使用角色 1/角色 2 标签锁定角色、服装和道具。

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

HappyHorse 1.0 参考视频：多图像主题到视频 AI 模型 | Models and API | RunComfy

HappyHorse 1.0 参考视频融合了多达 9 个参考图像和文本提示，可在 RunComfy 上生成 3-15 秒的 720P/1080P 剪辑 - 使用角色 1/角色 2 标签锁定角色、服装和道具。

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