• 版本 [version]
• 下载 63
• 文件大小 13199
• 文件计数 1
• 创建日期 2025年9月30日
• 最后更新 2026年9月21日

ControlNet的简单应用

ControlNet的简单应用 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 SaveImage ×2、CLIPTextEncode ×2、ControlNetApplyAdvanced ×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 SD1.5vaeFtMse840000Ema_v10.safetensors、SD1.5control_v11p_sd15_openpose.pth、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、SD1.5control_v11p_sd15_openpose.pth、SD1.5majicmixRealistic_v7.safetensors
• 核心节点：SaveImage ×2、CLIPTextEncode ×2、ControlNetApplyAdvanced ×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

{
    "id": "96dcedaf-e891-4e9a-a3c4-1779245bd232",
    "revision": 0,
    "last_node_id": 22,
    "last_link_id": 33,
    "nodes": [
        {
            "id": 20,
            "type": "ControlNetApplyAdvanced",
            "pos": [
                911.5072462375181,
                754.9306565800098
            ],
            "size": [
                315,
                186
            ],
            "flags": [],
            "order": 9,
            "mode": 0,
            "inputs": [
                {
                    "label": "positive",
                    "localized_name": "positive",
                    "name": "positive",
                    "type": "CONDITIONING",
                    "link": 26
                },
                {
                    "label": "negative",
                    "localized_name": "negative",
                    "name": "negative",
                    "type": "CONDITIONING",
                    "link": 27
                },
                {
                    "label": "control_net",
                    "localized_name": "control_net",
                    "name": "control_net",
                    "type": "CONTROL_NET",
                    "link": 28
                },
                {
                    "label": "image",
                    "localized_name": "image",
                    "name": "image",
                    "type": "IMAGE",
                    "link": 29
                },
                {
                    "label": "vae",
                    "localized_name": "vae",
                    "name": "vae",
                    "shape": 7,
                    "type": "VAE",
                    "link": 30
                },
                {
                    "localized_name": "strength",
                    "name": "strength",
                    "type": "FLOAT",
                    "widget": {
                        "name": "strength"
                    },
                    "link": null
                },
                {
                    "localized_name": "start_percent",
                    "name": "start_percent",
                    "type": "FLOAT",
                    "widget": {
                        "name": "start_percent"
                    },
                    "link": null
                },
                {
                    "localized_name": "end_percent",
                    "name": "end_percent",
                    "type": "FLOAT",
                    "widget": {
                        "name": "end_percent"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "positive",
                    "localized_name": "positive",
                    "name": "positive",
                    "type": "CONDITIONING",
                    "slot_index": 0,
                    "links": [
                        31
                    ]
                },
                {
                    "label": "negative",
                    "localized_name": "negative",
                    "name": "negative",
                    "type": "CONDITIONING",
                    "slot_index": 1,
                    "links": [
                        32
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.29",
                "Node name for S&R": "ControlNetApplyAdvanced"
            },
            "widgets_values": [
                1,
                0,
                1
            ]
        },
        {
            "id": 10,
            "type": "OpenposePreprocessor",
            "pos": [
                428.507246237517,
                933.9306565800102
            ],
 
… (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。