• 版本 [version]
• 下载 164
• 文件大小 16467
• 文件计数 1
• 创建日期 2026年3月2日
• 最后更新 2026年9月21日

comfyworkflows_f7579f23-b6fc-4464-94ec-d473526a1e64

comfyworkflows_f7579f23-b6fc-4464-94ec-d473526a1e64 是一套面向局部重绘场景的 ComfyUI 工作流，全图共 33 个节点、38 条连线。链路以 PreviewImage ×6、InpaintPreprocessor ×2、InvertMask ×2 为主干，输出图像，适合需要稳定批量出图的同学。主模型 segm/person_yolov8m-seg.pt、control_sd15_depth.pth、control_sd15_openpose.pth。下载后直接导入即可使用，建议显存 4GB 起。

• 主模型：segm/person_yolov8m-seg.pt、control_sd15_depth.pth、control_sd15_openpose.pth
• 核心节点：PreviewImage ×6、InpaintPreprocessor ×2、InvertMask ×2
• 输出形式：输出图像
• 规模：33 节点 / 38 连线
• 建议显存：4GB 起
• 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

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

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

{
    "last_node_id": 79,
    "last_link_id": 106,
    "nodes": [
        {
            "id": 6,
            "type": "PreviewImage",
            "pos": [
                610,
                610
            ],
            "size": [
                210,
                250
            ],
            "flags": [],
            "order": 13,
            "mode": 0,
            "inputs": [
                {
                    "name": "images",
                    "type": "IMAGE",
                    "link": 17
                }
            ],
            "properties": {
                "Node name for S&R": "PreviewImage"
            }
        },
        {
            "id": 4,
            "type": "CannyEdgePreprocessor",
            "pos": [
                550,
                190
            ],
            "size": [
                315,
                106
            ],
            "flags": [],
            "order": 8,
            "mode": 0,
            "inputs": [
                {
                    "name": "image",
                    "type": "IMAGE",
                    "link": 6
                }
            ],
            "outputs": [
                {
                    "name": "IMAGE",
                    "type": "IMAGE",
                    "links": [],
                    "shape": 3,
                    "slot_index": 0
                }
            ],
            "properties": {
                "Node name for S&R": "CannyEdgePreprocessor"
            },
            "widgets_values": [
                100,
                200,
                512
            ]
        },
        {
            "id": 10,
            "type": "PreviewImage",
            "pos": [
                1330,
                500
            ],
            "size": [
                210,
                250
            ],
            "flags": [],
            "order": 22,
            "mode": 0,
            "inputs": [
                {
                    "name": "images",
                    "type": "IMAGE",
                    "link": 9
                }
            ],
            "properties": {
                "Node name for S&R": "PreviewImage"
            }
        },
        {
            "id": 9,
            "type": "InpaintPreprocessor",
            "pos": [
                1320,
                330
            ],
            "size": [
                210,
                46
            ],
            "flags": [],
            "order": 19,
            "mode": 0,
            "inputs": [
                {
                    "name": "image",
                    "type": "IMAGE",
                    "link": 11
                },
                {
                    "name": "mask",
                    "type": "MASK",
                    "link": 20
                }
            ],
            "outputs": [
                {
                    "name": "IMAGE",
                    "type": "IMAGE",
                    "links": [
                        9,
                        32
                    ],
                    "shape": 3,
                    "slot_index": 0
                }
            ],
            "properties": {
                "Node name for S&R": "InpaintPreprocessor"
            }
        },
        {
            "id": 24,
            "type": "UltralyticsDetectorProvider",
            "pos": [
                1610,
                790
            ],
            "size": [
                315,
                78
            ],
            "flags": [],
            "order": 0,
            "mode": 0,
            "outputs": [
                {
                    "name": "BBOX_DETECTOR",
                    "type": "BBOX_DETECTOR",
                    "links": null,
                    "shape": 3
                },
                {
         
… (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。