• 版本 [version]
  • 下载 63
  • 文件大小 9775
  • 文件计数 1
  • 创建日期 2025年12月9日
  • 最后更新 2026年9月21日

局部重绘

这是一份开箱即用的局部重绘工作流(SD 1.5),拖入 ComfyUI 即可运行,全图 11 节点 / 15 连线。核心流程 CLIPTextEncode ×2、InpaintModelConditioning ×1、SaveImage ×1,输出图像,参数已调好,替换输入图即可复现效果。主模型 SD1.5vaeFtMse840000Ema_v10.safetensors、SD1.5majicmixRealistic_v7.safetensors。下载后直接导入即可使用,建议显存 4GB 起。

  • 主模型:SD1.5vaeFtMse840000Ema_v10.safetensors、SD1.5majicmixRealistic_v7.safetensors
  • 核心节点:CLIPTextEncode ×2、InpaintModelConditioning ×1、SaveImage ×1
  • 输出形式:输出图像
  • 规模:11 节点 / 15 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

局部重绘 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

局部重绘

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": "a70fdf90-e052-42c4-b42e-4f655898c64f",
    "revision": 0,
    "last_node_id": 45,
    "last_link_id": 76,
    "nodes": [
        {
            "id": 25,
            "type": "InpaintModelConditioning",
            "pos": [
                -333.39663671901275,
                2166.559045782817
            ],
            "size": [
                216.59999084472656,
                138
            ],
            "flags": [],
            "order": 6,
            "mode": 0,
            "inputs": [
                {
                    "label": "positive",
                    "localized_name": "positive",
                    "name": "positive",
                    "type": "CONDITIONING",
                    "link": 46
                },
                {
                    "label": "negative",
                    "localized_name": "negative",
                    "name": "negative",
                    "type": "CONDITIONING",
                    "link": 47
                },
                {
                    "label": "vae",
                    "localized_name": "vae",
                    "name": "vae",
                    "type": "VAE",
                    "link": 69
                },
                {
                    "label": "pixels",
                    "localized_name": "pixels",
                    "name": "pixels",
                    "type": "IMAGE",
                    "link": 50
                },
                {
                    "label": "mask",
                    "localized_name": "mask",
                    "name": "mask",
                    "type": "MASK",
                    "link": 72
                },
                {
                    "localized_name": "noise_mask",
                    "name": "noise_mask",
                    "type": "BOOLEAN",
                    "widget": {
                        "name": "noise_mask"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "positive",
                    "localized_name": "positive",
                    "name": "positive",
                    "type": "CONDITIONING",
                    "slot_index": 0,
                    "links": [
                        51
                    ]
                },
                {
                    "label": "negative",
                    "localized_name": "negative",
                    "name": "negative",
                    "type": "CONDITIONING",
                    "slot_index": 1,
                    "links": [
                        52
                    ]
                },
                {
                    "label": "latent",
                    "localized_name": "latent",
                    "name": "latent",
                    "type": "LATENT",
                    "slot_index": 2,
                    "links": [
                        74
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.29",
                "Node name for S&R": "InpaintModelConditioning"
            },
            "widgets_values": [
                true
            ]
        },
        {
            "id": 30,
            "type": "CLIPTextEncode",
            "pos": [
                -494.0562596920851,
                1825.1778267274653
            ],
            "size": [
                425.27801513671875,
                180.6060791015625
            ],
            "flags": {
                "collapsed": false
            },
            "order": 5,
            "mode": 0,
            "inputs": [
                {
                    "label": "clip",
                    "localized_name": "clip",
              
… (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