• 版本 [version]
  • 下载 80
  • 文件大小 16119
  • 文件计数 1
  • 创建日期 2026年8月22日
  • 最后更新 2026年9月21日

Wan2.2_Video_Upscale

Wan2.2_Video_Upscale:基于 Wan 2.2、SDXL 搭建的视频生成方案,节点规模 17 个、连线 17 条。工作流主路径为 CLIPTextEncode ×2、UpscaleModelLoader ×1、ImageUpscaleWithModel ×1,配合 输出视频;节点已按执行顺序排布,便于二次修改。主模型 4x-UltraSharp.pth、Wan_2.1wan_2.1_vae.safetensors、Wanumt5_xxl_fp8_e4m3fn_scaled.safetensors。下载后直接导入即可使用,建议显存 16GB 起(视频生成建议 24GB)。

  • 主模型:4x-UltraSharp.pth、Wan_2.1wan_2.1_vae.safetensors、Wanumt5_xxl_fp8_e4m3fn_scaled.safetensors
  • 核心节点:CLIPTextEncode ×2、UpscaleModelLoader ×1、ImageUpscaleWithModel ×1
  • 输出形式:输出视频
  • 规模:17 节点 / 17 连线
  • 建议显存:16GB 起(视频生成建议 24GB)
  • 适用场景:图生视频、首尾帧、数字人与长视频一致性控制工作流。

工作流节点图

Wan2.2_Video_Upscale 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

Wan2.2_Video_Upscale

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": "115b5f64-0734-4438-afcf-e7122530c4ec",
    "revision": 0,
    "last_node_id": 25,
    "last_link_id": 28,
    "nodes": [
        {
            "id": 16,
            "type": "UpscaleModelLoader",
            "pos": [
                -1527.7799072265625,
                577.1587524414062
            ],
            "size": [
                270,
                58
            ],
            "flags": [],
            "order": 1,
            "mode": 0,
            "inputs": [
                {
                    "label": "model_name",
                    "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": [
                        17
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.49",
                "Node name for S&R": "UpscaleModelLoader"
            },
            "widgets_values": [
                "4x-UltraSharp.pth"
            ]
        },
        {
            "id": 15,
            "type": "ImageUpscaleWithModel",
            "pos": [
                -1231.6405029296875,
                615.332763671875
            ],
            "size": [
                221.98202514648438,
                46
            ],
            "flags": [],
            "order": 9,
            "mode": 0,
            "inputs": [
                {
                    "label": "upscale_model",
                    "localized_name": "放大模型",
                    "name": "upscale_model",
                    "type": "UPSCALE_MODEL",
                    "link": 17
                },
                {
                    "label": "image",
                    "localized_name": "图像",
                    "name": "image",
                    "type": "IMAGE",
                    "link": 18
                }
            ],
            "outputs": [
                {
                    "label": "IMAGE",
                    "localized_name": "图像",
                    "name": "IMAGE",
                    "type": "IMAGE",
                    "links": [
                        19
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.49",
                "Node name for S&R": "ImageUpscaleWithModel"
            },
            "widgets_values": []
        },
        {
            "id": 3,
            "type": "VAEEncode",
            "pos": [
                -659.7444458007812,
                637.6016235351562
            ],
            "size": [
                140,
                46
            ],
            "flags": [],
            "order": 13,
            "mode": 0,
            "inputs": [
                {
                    "label": "pixels",
                    "localized_name": "像素",
                    "name": "pixels",
                    "type": "IMAGE",
                    "link": 2
                },
                {
                    "label": "vae",
                    "localized_name": "vae",
                    "name": "vae",
                    "type": "VAE",
                    "link": 6
                }
            ],
            "outputs": [
                {
                    "label": "LATENT",
                    "localized_name": "Latent",
                    "name": "LAT
… (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