• 版本 [version]
• 下载 143
• 文件大小 17453
• 文件计数 1
• 创建日期 2026年6月9日
• 最后更新 2026年9月21日

FusionX_LoRa_I2V

FusionX_LoRa_I2V：基于 Wan 2.1、SDXL 搭建的视频生成方案，节点规模 16 个、连线 20 条。工作流主路径为 CLIPTextEncode ×2、ModelSamplingSD3 ×1、CLIPVisionLoader ×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 clip_vision_h.safetensors、Wan_2.1wan_2.1_vae.safetensors、wan2.1umt5_xxl_fp8_e4m3fn_scaled.safetensors。已挂载 LoRA：Wan2.1Wan2.1_I2V_14B_FusionX_LoRA.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：clip_vision_h.safetensors、Wan_2.1wan_2.1_vae.safetensors、wan2.1umt5_xxl_fp8_e4m3fn_scaled.safetensors
• LoRA / 适配器：Wan2.1Wan2.1_I2V_14B_FusionX_LoRA.safetensors
• 核心节点：CLIPTextEncode ×2、ModelSamplingSD3 ×1、CLIPVisionLoader ×1
• 输出形式：输出视频
• 规模：16 节点 / 20 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

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": "d17897db-05ed-462e-bfce-93c5456e87bc",
    "revision": 0,
    "last_node_id": 305,
    "last_link_id": 117,
    "nodes": [
        {
            "id": 54,
            "type": "ModelSamplingSD3",
            "pos": [
                335.56304931640625,
                -355.10980224609375
            ],
            "size": [
                219.82144165039062,
                59.586307525634766
            ],
            "flags": [],
            "order": 12,
            "mode": 0,
            "inputs": [
                {
                    "label": "model",
                    "localized_name": "model",
                    "name": "model",
                    "type": "MODEL",
                    "link": 115
                },
                {
                    "label": "shift",
                    "localized_name": "shift",
                    "name": "shift",
                    "type": "FLOAT",
                    "widget": {
                        "name": "shift"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "MODEL",
                    "localized_name": "MODEL",
                    "name": "MODEL",
                    "type": "MODEL",
                    "slot_index": 0,
                    "links": [
                        111
                    ]
                }
            ],
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.36",
                "Node name for S&R": "ModelSamplingSD3",
                "widget_ue_connectable": []
            },
            "widgets_values": [
                1.0000000000000002
            ]
        },
        {
            "id": 6,
            "type": "CLIPTextEncode",
            "pos": [
                -189.72805786132812,
                -335.90411376953125
            ],
            "size": [
                415.14501953125,
                207.21304321289062
            ],
            "flags": [],
            "order": 5,
            "mode": 0,
            "inputs": [
                {
                    "label": "clip",
                    "localized_name": "clip",
                    "name": "clip",
                    "type": "CLIP",
                    "link": 74
                },
                {
                    "label": "text",
                    "localized_name": "text",
                    "name": "text",
                    "type": "STRING",
                    "widget": {
                        "name": "text"
                    },
                    "link": null
                }
            ],
            "outputs": [
                {
                    "label": "CONDITIONING",
                    "localized_name": "CONDITIONING",
                    "name": "CONDITIONING",
                    "type": "CONDITIONING",
                    "slot_index": 0,
                    "links": [
                        97
                    ]
                }
            ],
            "title": "CLIP Text Encode (Positive Prompt)",
            "properties": {
                "cnr_id": "comfy-core",
                "ver": "0.3.36",
                "Node name for S&R": "CLIPTextEncode",
                "widget_ue_connectable": []
            },
            "widgets_values": [
                "A girl is dancing gracefully in an endless sea of flowers, slowly moving her hands in elegant arcs. The camera starts with a close-up of her upper body, highlighting her flowing hair and the soft movement of her delicate dress, then gradually pulls back, revealing the vast expanse of blossoms surrounding her. "
            ],
            "color": "#232",
            "bgcolor": "#353"
        },
        {
   
… (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。