logo
RunComfy
  • ComfyUI
  • 训练器新
  • 模型
  • API
  • 定价
discord logo
模型
探索
所有模型
资源库
生成记录
模型 API
API 文档
API 密钥
账户
使用情况

Kling 3.0 Standard Image to Video(标准图生视频):模型界面与 API 上的物理感知图生视频 | Models and API | RunComfy

kling/kling-3.0/standard/image-to-video

通过物理感知运动、摄像机控制和原生音频将静态图像动画化为高保真视频,以实现快速、电影般的品牌视觉故事讲述。

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

1. 快速开始

使用 RunComfy 的 API 运行 kling/kling-3.0/standard/image-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/kling/kling-3.0/standard/image-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Bring this still photograph to life with cinematic motion. The young American woman in a flowing white linen sundress stands on a sunlit Pacific Coast cliff at golden hour: her chestnut hair drifts gently in the ocean breeze, the hem of her dress flutters, and she turns her head and breaks into a soft smile as warm sunlight catches her freckles. Behind her, foamy turquoise waves roll and crash against the rocks below, seabirds glide past, and tall coastal grass sways. The camera slowly dollies in from a wide shot to a tender medium close-up, a subtle parallax revealing the depth of the cliffside. Natural ambient sound: gentle Pacific surf, distant gulls, a soft breeze through the grass, faint acoustic guitar in the background. Photoreal skin and fabric textures, hair strand detail, realistic water physics, golden-hour rim lighting, lens flare, shot on Arri Alexa 35, 50mm anamorphic, shallow depth of field, premium cinematic color grade.",
    "start_image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7349/media-files/input.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/kling/kling-3.0/standard/image-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Bring this still photograph to life with cinematic motion. The young American woman in a flowing white linen sundress stands on a sunlit Pacific Coast cliff at golden hour: her chestnut hair drifts gently in the ocean breeze, the hem of her dress flutters, and she turns her head and breaks into a soft smile as warm sunlight catches her freckles. Behind her, foamy turquoise waves roll and crash against the rocks below, seabirds glide past, and tall coastal grass sways. The camera slowly dollies in from a wide shot to a tender medium close-up, a subtle parallax revealing the depth of the cliffside. Natural ambient sound: gentle Pacific surf, distant gulls, a soft breeze through the grass, faint acoustic guitar in the background. Photoreal skin and fabric textures, hair strand detail, realistic water physics, golden-hour rim lighting, lens flare, shot on Arri Alexa 35, 50mm anamorphic, shallow depth of field, premium cinematic color grade.",
    "start_image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7349/media-files/input.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",
    "start_image_url"
  ],
  "properties": {
    "prompt": {
      "title": "提示词",
      "description": "",
      "type": "string",
      "default": "Bring this still photograph to life with cinematic motion. The young American woman in a flowing white linen sundress stands on a sunlit Pacific Coast cliff at golden hour: her chestnut hair drifts gently in the ocean breeze, the hem of her dress flutters, and she turns her head and breaks into a soft smile as warm sunlight catches her freckles. Behind her, foamy turquoise waves roll and crash against the rocks below, seabirds glide past, and tall coastal grass sways. The camera slowly dollies in from a wide shot to a tender medium close-up, a subtle parallax revealing the depth of the cliffside. Natural ambient sound: gentle Pacific surf, distant gulls, a soft breeze through the grass, faint acoustic guitar in the background. Photoreal skin and fabric textures, hair strand detail, realistic water physics, golden-hour rim lighting, lens flare, shot on Arri Alexa 35, 50mm anamorphic, shallow depth of field, premium cinematic color grade."
    },
    "multi_prompt": {
      "title": "多段 prompt",
      "description": "提供多个场景切换提示片段。所有片段持续时间的总和必须等于视频总持续时间。",
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string",
            "format": "str"
          },
          "duration": {
            "type": "integer",
            "format": "int_slider_with_range",
            "minimum": 3,
            "maximum": 15,
            "default": 5
          }
        }
      },
      "maxItems": 20,
      "minItems": 0
    },
    "start_image_url": {
      "title": "起始图像",
      "description": "视频的起始图像。支持 jpg、jpeg、png、bmp、webp 格式。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7349/media-files/input.png"
    },
    "duration": {
      "title": "时长",
      "description": "生成的视频的总持续时间(以秒为单位)。",
      "type": "integer",
      "minimum": 3,
      "maximum": 15,
      "default": 10
    },
    "generate_audio": {
      "title": "生成音频",
      "description": "启用此选项可为视频生成音频。",
      "type": "boolean",
      "default": true
    },
    "elements": {
      "title": "元素",
      "description": "用于生成的输入资源,包括参考图像和视频片段。",
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "frontal_image_url": {
            "type": "string",
            "format": "image_uri",
            "description": "主题的正面图像参考。"
          },
          "reference_image_urls": {
            "type": "array",
            "format": "image_uris",
            "items": {
              "type": "string",
              "format": "image_uri"
            },
            "description": "用于指导渲染的附加参考图像 URL。"
          },
          "video_url": {
            "type": "string",
            "format": "video_uri",
            "description": "用于运动参考的可选源视频。"
          }
        }
      },
      "minItems": 0,
      "maxItems": 3
    },
    "shot_type": {
      "title": "镜头类型",
      "description": "定义如何处理相机镜头或场景取景。",
      "type": "string",
      "enum": [
        "customize"
      ],
      "default": "customize"
    },
    "negative_prompt": {
      "title": "否定提示",
      "description": "",
      "type": "string"
    },
    "cfg_scale": {
      "title": "指导量表",
      "description": "无分类器指导尺度控制对提示的遵守。",
      "type": "float",
      "minimum": 0,
      "maximum": 1,
      "default": 0.5
    }
  }
}

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"
        }
      }
    }
  }
}
关注我们
  • 领英
  • Facebook
  • Instagram
  • Twitter
支持
  • Discord
  • 电子邮件
  • 系统状态
  • 附属
视频模型
  • Wan 2.6 Flash
  • Kling Video O3 Pro Image To Video
  • Wan 2.6
  • Seedance 2.0 Fast
  • Hailuo 2.3 Fast Standard
  • Kling 3.0
  • 查看所有模型 →
图像模型
  • seedream 4.0
  • Nano Banana 2 Edit
  • Flux 2 Dev
  • Nano Banana Pro
  • GPT Image 2 Image Edit
  • FLUX.1 Schnell
  • 查看所有模型 →
法律
  • 服务条款
  • 隐私政策
  • Cookie 政策
RunComfy
版权 2026 RunComfy. 保留所有权利。

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。