• 版本 [version]
  • 下载 64
  • 文件大小 53569
  • 文件计数 1
  • 创建日期 2026年9月14日
  • 最后更新 2026年9月20日

FLUX原结构局部重绘 换头 换脸 换装

这是一份开箱即用的局部重绘工作流(FLUX、ControlNet),拖入 ComfyUI 即可运行,全图 40 节点 / 53 连线。核心流程 PreviewImage ×3、SetUnionControlNetType ×3、AIO_Preprocessor ×3,输出图像,参数已调好,替换输入图即可复现效果。主模型 FLUX.1-dev-Controlnet-Canny-InstantX.safetensors、FLUX.1-dev-Controlnet-Depth-InstantX.safetensors、FLUX.1-ControlNet-Pose-V1.safetensors。下载后直接导入即可使用,建议显存 12GB 起(建议 16GB 以上)。

  • 主模型:FLUX.1-dev-Controlnet-Canny-InstantX.safetensors、FLUX.1-dev-Controlnet-Depth-InstantX.safetensors、FLUX.1-ControlNet-Pose-V1.safetensors
  • 核心节点:PreviewImage ×3、SetUnionControlNetType ×3、AIO_Preprocessor ×3
  • 输出形式:输出图像
  • 规模:40 节点 / 53 连线
  • 建议显存:12GB 起(建议 16GB 以上)
  • 适用场景:蒙版局部重绘、主体替换、材质替换与瑕疵修复。

工作流节点图

FLUX原结构局部重绘 换头 换脸 换装 工作流节点图

图较大可横向滚动;点击图片查看高清矢量原图(浏览器中可自由缩放)。

资源头图

FLUX原结构局部重绘 换头 换脸 换装

使用说明

下载工作流文件后在 ComfyUI 中直接拖入画布(或菜单 Load 导入)即可运行;缺失的自定义节点用 ComfyUI Manager 一键安装,模型按文件名放入对应的 models 目录。

源码预览

{
    "id": "5021388e-9d5b-46fd-b4a1-9bda3e42e4c9",
    "revision": 0,
    "last_node_id": 49,
    "last_link_id": 62,
    "nodes": [
        {
            "id": 10,
            "type": "PreviewImage",
            "pos": [
                -630,
                750
            ],
            "size": [
                440,
                390
            ],
            "flags": [],
            "order": 25,
            "mode": 0,
            "inputs": [
                {
                    "label": "图像",
                    "name": "images",
                    "type": "IMAGE",
                    "link": 10
                }
            ],
            "outputs": [],
            "properties": {
                "Node name for S&R": "PreviewImage",
                "cnr_id": "comfy-core",
                "ver": "0.3.31",
                "widget_ue_connectable": []
            },
            "widgets_values": []
        },
        {
            "id": 11,
            "type": "PreviewImage",
            "pos": [
                -120,
                750
            ],
            "size": [
                440,
                390
            ],
            "flags": [],
            "order": 24,
            "mode": 4,
            "inputs": [
                {
                    "label": "图像",
                    "name": "images",
                    "type": "IMAGE",
                    "link": 11
                }
            ],
            "outputs": [],
            "properties": {
                "Node name for S&R": "PreviewImage",
                "cnr_id": "comfy-core",
                "ver": "0.3.31",
                "widget_ue_connectable": []
            },
            "widgets_values": []
        },
        {
            "id": 12,
            "type": "SetUnionControlNetType",
            "pos": [
                -120,
                250
            ],
            "size": [
                440,
                58
            ],
            "flags": [],
            "order": 20,
            "mode": 4,
            "inputs": [
                {
                    "label": "ControlNet",
                    "name": "control_net",
                    "type": "CONTROL_NET",
                    "link": 12
                }
            ],
            "outputs": [
                {
                    "label": "ControlNet",
                    "name": "CONTROL_NET",
                    "type": "CONTROL_NET",
                    "links": [
                        29
                    ]
                }
            ],
            "properties": {
                "Node name for S&R": "SetUnionControlNetType",
                "cnr_id": "comfy-core",
                "ver": "0.3.31",
                "widget_ue_connectable": {
                    "type": true
                }
            },
            "widgets_values": [
                "depth"
            ]
        },
        {
            "id": 13,
            "type": "AIO_Preprocessor",
            "pos": [
                -120,
                370
            ],
            "size": [
                440,
                82
            ],
            "flags": [],
            "order": 15,
            "mode": 4,
            "inputs": [
                {
                    "label": "图像",
                    "name": "image",
                    "type": "IMAGE",
                    "link": 13
                }
            ],
            "outputs": [
                {
                    "label": "图像",
                    "name": "IMAGE",
                    "type": "IMAGE",
                    "links": [
                        11,
                        30
                    ]
                }
            ],
            "properties": {
                "Node name for S&R": "AIO_Preprocessor",
… (完整内容请下载文件查看)

代码较长,以上仅前 3800 字符 —— 点击下方按钮下载完整 JSON。

发表回复

你的电子邮件地址不会被公开 * 为必填字段

提交评论