• 版本 [version]
• 下载 90
• 文件大小 12204
• 文件计数 1
• 创建日期 2026年6月18日
• 最后更新 2026年9月21日

文生图高清放大

文生图高清放大 是一套面向高清放大场景的 ComfyUI 工作流，全图共 12 个节点、16 条连线。链路以 SaveImage ×2、CLIPTextEncode ×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 SD1.5majicmixRealistic_v7.safetensors、SD1.5vaeFtMse840000Ema_v10.safetensors、4x-UltraSharp.pth。下载后直接导入即可使用，建议显存 4GB 起。

• 主模型：SD1.5majicmixRealistic_v7.safetensors、SD1.5vaeFtMse840000Ema_v10.safetensors、4x-UltraSharp.pth
• 核心节点：SaveImage ×2、CLIPTextEncode ×2、CheckpointLoaderSimple ×1
• 输出形式：输出图像 · 512×768
• 规模：12 节点 / 16 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": "f672a8b5-0f10-47b0-abc0-9e23d266b3de",
    "revision": 0,
    "last_node_id": 38,
    "last_link_id": 74,
    "nodes": [
        {
            "id": 2,
            "type": "CheckpointLoaderSimple",
            "pos": [
                -682.311279296875,
                519.2742919921875
            ],
            "size": [
                315,
                98
            ],
            "flags": [],
            "order": 0,
            "mode": 0,
            "inputs": [
                {
                    "localized_name": "ckpt_name",
                    "name": "ckpt_name",
                    "type": "COMBO",
                    "widget": {
                        "name": "ckpt_name"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "MODEL",
                    "localized_name": "MODEL",
                    "name": "MODEL",
                    "type": "MODEL",
                    "links": [
                        1,
                        42
                    ]
                },
                {
                    "label": "CLIP",
                    "localized_name": "CLIP",
                    "name": "CLIP",
                    "type": "CLIP",
                    "links": [
                        8,
                        9
                    ]
                },
                {
                    "label": "VAE",
                    "localized_name": "VAE",
                    "name": "VAE",
                    "type": "VAE",
                    "links": []
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.29",
                "Node name for S&R": "CheckpointLoaderSimple"
            },
            "widgets_values": [
                "SD1.5majicmixRealistic_v7.safetensors"
            ]
        },
        {
            "id": 31,
            "type": "VAELoader",
            "pos": [
                -682.311279296875,
                679.274169921875
            ],
            "size": [
                315,
                58
            ],
            "flags": [],
            "order": 1,
            "mode": 0,
            "inputs": [
                {
                    "localized_name": "vae_name",
                    "name": "vae_name",
                    "type": "COMBO",
                    "widget": {
                        "name": "vae_name"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "VAE",
                    "localized_name": "VAE",
                    "name": "VAE",
                    "type": "VAE",
                    "slot_index": 0,
                    "links": [
                        58,
                        60
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.29",
                "Node name for S&R": "VAELoader"
            },
            "widgets_values": [
                "SD1.5vaeFtMse840000Ema_v10.safetensors"
            ]
        },
        {
            "id": 5,
            "type": "EmptyLatentImage",
            "pos": [
                -661.795592169941,
                900.4967389036256
            ],
            "size": [
                370,
                110
            ],
            "flags": [],
            "order": 2,
            "mode": 0,
            "inputs": [
                {
                    "localized_name": "width",
                    "name": "width",
                    "type": "INT",
                    "widget": {
                       
… (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。