• 版本 [version]
• 下载 102
• 文件大小 14199
• 文件计数 1
• 创建日期 2026年3月27日
• 最后更新 2026年9月21日

05.ControlNet的简单应用(Simple Application of ControlNet)

05.ControlNet的简单应用(Simple Application of ControlNet) 是一套面向人像调节场景的 ComfyUI 工作流，全图共 14 个节点、16 条连线。链路以 CLIPTextEncode ×2、SaveImage ×2、CheckpointLoaderSimple ×1 为主干，输出图像，默认输出 512×768，适合需要稳定批量出图的同学。主模型 SD15majicmixRealistic_v7.safetensors、SD15vaeFtMse840000Ema_v10.safetensors、SD15control_v11p_sd15_openpose.pth。下载后直接导入即可使用，建议显存 4GB 起。

• 主模型：SD15majicmixRealistic_v7.safetensors、SD15vaeFtMse840000Ema_v10.safetensors、SD15control_v11p_sd15_openpose.pth
• 核心节点：CLIPTextEncode ×2、SaveImage ×2、CheckpointLoaderSimple ×1
• 输出形式：输出图像 · 512×768
• 规模：14 节点 / 16 连线
• 建议显存：4GB 起
• 适用场景：人像精修、磨皮、修手修脸、去 AI 味与表情姿态微调。

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": 21,
    "last_link_id": 33,
    "nodes": [
        {
            "id": 4,
            "type": "CheckpointLoaderSimple",
            "pos": [
                66,
                200
            ],
            "size": [
                315,
                98
            ],
            "flags": [],
            "order": 0,
            "mode": 0,
            "inputs": [],
            "outputs": [
                {
                    "name": "MODEL",
                    "type": "MODEL",
                    "links": [
                        1
                    ],
                    "slot_index": 0,
                    "label": "MODEL"
                },
                {
                    "name": "CLIP",
                    "type": "CLIP",
                    "links": [
                        3,
                        5
                    ],
                    "slot_index": 1,
                    "label": "CLIP"
                },
                {
                    "name": "VAE",
                    "type": "VAE",
                    "links": [],
                    "slot_index": 2,
                    "label": "VAE"
                }
            ],
            "properties": {
                "Node name for S&R": "CheckpointLoaderSimple"
            },
            "widgets_values": [
                "SD15majicmixRealistic_v7.safetensors"
            ]
        },
        {
            "id": 16,
            "type": "VAELoader",
            "pos": [
                66,
                382
            ],
            "size": [
                315,
                58
            ],
            "flags": [],
            "order": 1,
            "mode": 0,
            "inputs": [],
            "outputs": [
                {
                    "name": "VAE",
                    "type": "VAE",
                    "links": [
                        18,
                        30
                    ],
                    "slot_index": 0,
                    "shape": 3,
                    "label": "VAE"
                }
            ],
            "properties": {
                "Node name for S&R": "VAELoader"
            },
            "widgets_values": [
                "SD15vaeFtMse840000Ema_v10.safetensors"
            ]
        },
        {
            "id": 7,
            "type": "CLIPTextEncode",
            "pos": [
                493,
                348
            ],
            "size": [
                425.27801513671875,
                180.6060791015625
            ],
            "flags": [],
            "order": 7,
            "mode": 0,
            "inputs": [
                {
                    "name": "clip",
                    "type": "CLIP",
                    "link": 5,
                    "label": "clip"
                }
            ],
            "outputs": [
                {
                    "name": "CONDITIONING",
                    "type": "CONDITIONING",
                    "links": [
                        27
                    ],
                    "slot_index": 0,
                    "label": "CONDITIONING"
                }
            ],
            "properties": {
                "Node name for S&R": "CLIPTextEncode"
            },
            "widgets_values": [
                "(worst quality, low quality, bad_pictures, bad_pictures,  negative_hand-neg), nsfw, txt, watermark, "
            ]
        },
        {
            "id": 6,
            "type": "CLIPTextEncode",
            "pos": [
                492,
                132
            ],
            "size": [
                422.84503173828125,
                164.31304931640625
            ],
            "flags": [],
            "order": 6,
            "mode": 0,
            "inputs": [
             
… (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。