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

Z Image Inpainting LoRA:支持 LoRA 的精准局部重绘 | RunComfy

tongyi-mai/z-image/turbo/inpainting/lora

精准编辑蒙版区域,按需叠加最多 3 个 LoRA,并尽量保持原图的光影、材质和构图一致。

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 tongyi-mai/z-image/turbo/inpainting/lora。 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/tongyi-mai/z-image/turbo/inpainting/lora \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Replace the girl’s current top with a short red polka-dot swimsuit top. Keep the girl’s face, hairstyle, body proportions, and pose unchanged. The lighting should be natural and consistent with a beach environment, with realistic colors and details.",
    "image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7294/media-files/input-1-1.png",
    "mask_image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7294/media-files/mask.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/tongyi-mai/z-image/turbo/inpainting/lora \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Replace the girl’s current top with a short red polka-dot swimsuit top. Keep the girl’s face, hairstyle, body proportions, and pose unchanged. The lighting should be natural and consistent with a beach environment, with realistic colors and details.",
    "image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7294/media-files/input-1-1.png",
    "mask_image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7294/media-files/mask.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_url",
    "mask_image_url"
  ],
  "properties": {
    "prompt": {
      "title": "提示词",
      "description": "",
      "type": "string",
      "default": "Replace the girl’s current top with a short red polka-dot swimsuit top. Keep the girl’s face, hairstyle, body proportions, and pose unchanged. The lighting should be natural and consistent with a beach environment, with realistic colors and details."
    },
    "image_url": {
      "title": "图片",
      "description": "用于局部重绘的有效原图 URL。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7294/media-files/input-1-1.png"
    },
    "mask_image_url": {
      "title": "蒙版图片",
      "description": "用于指定编辑区域的有效蒙版图片 URL。",
      "type": "string",
      "default": "https://playgrounds-storage-public.runcomfy.net/tools/7294/media-files/mask.png"
    },
    "control_start": {
      "title": "控制起点",
      "description": "ControlNet 条件开始生效的位置,取值范围为 0 到 1。",
      "type": "float",
      "minimum": 0,
      "maximum": 1,
      "default": 0
    },
    "strength": {
      "title": "重绘强度",
      "description": "控制局部重绘条件的作用强度。",
      "type": "float",
      "minimum": 0,
      "maximum": 1,
      "default": 1
    },
    "loras": {
      "title": "LoRA",
      "description": "要应用的 LoRA 列表,最多可添加 3 个。",
      "type": "array",
      "items": {
        "path": {
          "title": "LoRA 路径",
          "description": "LoRA 权重的 URL 或 HuggingFace 仓库 ID(owner/repo)。",
          "type": "string",
          "format": "str",
          "default": ""
        },
        "scale": {
          "title": "LoRA 强度",
          "description": "控制 LoRA 模型的应用强度。",
          "type": "float",
          "format": "float_slider_with_range",
          "minimum": 0,
          "maximum": 4,
          "default": 1
        }
      },
      "maxItems": 3,
      "minItems": 0
    },
    "image_size": {
      "title": "宽高比(宽:高)",
      "description": "",
      "type": "string",
      "enum": [
        "square_hd",
        "square",
        "portrait_4_3",
        "portrait_16_9",
        "landscape_4_3",
        "landscape_16_9",
        "auto"
      ],
      "default": "auto"
    },
    "num_inference_steps": {
      "title": "推理步数",
      "description": "控制扩散推理的步数。",
      "type": "integer",
      "minimum": 1,
      "maximum": 30,
      "default": 20
    },
    "seed": {
      "title": "随机种子",
      "description": "",
      "type": "integer",
      "default": 0
    },
    "output_format": {
      "title": "输出格式",
      "description": "指定生成图片的文件格式。",
      "type": "string",
      "enum": [
        "jpeg",
        "png",
        "webp"
      ],
      "default": "png"
    },
    "control_scale": {
      "title": "控制强度",
      "description": "设置局部重绘 ControlNet 条件的作用强度。",
      "type": "float",
      "minimum": 0,
      "maximum": 1,
      "default": 0.75
    },
    "control_end": {
      "title": "控制终点",
      "description": "ControlNet 条件停止生效的位置,取值范围为 0 到 1。",
      "type": "float",
      "minimum": 0,
      "maximum": 1,
      "default": 0.6
    }
  }
}

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
  • Wan 2.6 Text to Video
  • Hailuo 2.3 Fast Standard
  • Happy Horse 1.1 reference to video
  • Seedance 2.5 Reference to Video
  • Seedance 2.0 Pro
  • 查看所有模型 →
图像模型
  • Seedream 5.0 Pro Image Edit
  • seedream 4.0
  • Flux 2 Flash Edit
  • Nano Banana Pro
  • Nano Banana 2 Edit
  • GPT Image 2 Image Edit
  • 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。