• 版本 [version]
• 下载 133
• 文件大小 10090
• 文件计数 1
• 创建日期 2026年1月11日
• 最后更新 2026年9月21日

图生图高清放大

图生图高清放大 是一套面向高清放大场景的 ComfyUI 工作流，全图共 10 个节点、11 条连线。链路以 CLIPTextEncode ×2、UpscaleModelLoader ×1、UltimateSDUpscale ×1 为主干，输出图像，适合需要稳定批量出图的同学。主模型 4x-UltraSharp.pth、SD1.5majicmixRealistic_v7.safetensors、SD1.5vaeFtMse840000Ema_v10.safetensors。下载后直接导入即可使用，建议显存 4GB 起。

• 主模型：4x-UltraSharp.pth、SD1.5majicmixRealistic_v7.safetensors、SD1.5vaeFtMse840000Ema_v10.safetensors
• 核心节点：CLIPTextEncode ×2、UpscaleModelLoader ×1、UltimateSDUpscale ×1
• 输出形式：输出图像
• 规模：10 节点 / 11 连线
• 建议显存：4GB 起
• 适用场景：2K/4K/8K 无损放大、细节重绘与纹理修复，救回模糊与 AI 感素材。

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": "f986b659-5bac-41b7-bb8b-799fbc2e63f5",
    "revision": 0,
    "last_node_id": 38,
    "last_link_id": 77,
    "nodes": [
        {
            "id": 26,
            "type": "UpscaleModelLoader",
            "pos": [
                1160,
                750
            ],
            "size": [
                315,
                58
            ],
            "flags": [],
            "order": 0,
            "mode": 0,
            "inputs": [
                {
                    "localized_name": "模型名称",
                    "name": "model_name",
                    "type": "COMBO",
                    "widget": {
                        "name": "model_name"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "UPSCALE_MODEL",
                    "localized_name": "放大模型",
                    "name": "UPSCALE_MODEL",
                    "type": "UPSCALE_MODEL",
                    "links": [
                        46
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.29",
                "Node name for S&R": "UpscaleModelLoader"
            },
            "widgets_values": [
                "4x-UltraSharp.pth"
            ]
        },
        {
            "id": 25,
            "type": "UltimateSDUpscale",
            "pos": [
                1590,
                510
            ],
            "size": [
                315,
                614
            ],
            "flags": [],
            "order": 8,
            "mode": 0,
            "inputs": [
                {
                    "label": "image",
                    "localized_name": "image",
                    "name": "image",
                    "type": "IMAGE",
                    "link": 74
                },
                {
                    "label": "model",
                    "localized_name": "model",
                    "name": "model",
                    "type": "MODEL",
                    "link": 42
                },
                {
                    "label": "positive",
                    "localized_name": "positive",
                    "name": "positive",
                    "type": "CONDITIONING",
                    "link": 43
                },
                {
                    "label": "negative",
                    "localized_name": "negative",
                    "name": "negative",
                    "type": "CONDITIONING",
                    "link": 44
                },
                {
                    "label": "vae",
                    "localized_name": "vae",
                    "name": "vae",
                    "type": "VAE",
                    "link": 60
                },
                {
                    "label": "upscale_model",
                    "localized_name": "upscale_model",
                    "name": "upscale_model",
                    "type": "UPSCALE_MODEL",
                    "link": 46
                },
                {
                    "localized_name": "upscale_by",
                    "name": "upscale_by",
                    "type": "FLOAT",
                    "widget": {
                        "name": "upscale_by"
                    },
                    "link": null
                },
                {
                    "localized_name": "seed",
                    "name": "seed",
                    "type": "INT",
                    "widget": {
                        "name": "seed"
                    },
                    "link": null
                },
                {
                    "localized_name": "steps",
                    "name": "steps",

… (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。