### Install Transformers Library

Source: https://learn.thinkdiffusion.com/automatic1111-in-the-cloud-guide

Command to install the Hugging Face transformers library.

```bash
pip install transformers
```

--------------------------------

### Launch Automatic1111

Source: https://learn.thinkdiffusion.com/automatic1111-in-the-cloud-guide

Command to start the web interface.

```bash
python launch.py
```

--------------------------------

### Load Image Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/04/Video2Video-Wan-Style-Transfer.json

Sets up the image loading node for the starting frame of the video-to-video process.

```json
{
      "id": 63,
      "type": "LoadImage",
      "pos": [
        -1498.0606689453125,
        -1153.4552001953125
      ],
      "size": [
        350,
        350
      ],
      "flags": {
        "collapsed": false
      },
      "order": 42,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            94
          ]
        },
        {
          "name": "MASK",
          "type": "MASK",
          "links": null
        }
      ],
      "title": "Load Image: Start image",
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.27",
        "Node name for S&R": "LoadImage"
      },
      "widgets_values": [
        "t2i_00018_.png",
        "image",
        ""
      ],
      "color": "#2a363b",
      "bgcolor": "#3f5159"
    }
```

--------------------------------

### Install InsightFace dependency

Source: https://learn.thinkdiffusion.com/face-swapping-with-roop

Run this command in a command window to install the required InsightFace package for face swapping functionality.

```bash
pip install insightface==0.7.3
```

--------------------------------

### Configure Automatic1111 Paths

Source: https://learn.thinkdiffusion.com/automatic1111-in-the-cloud-guide

Example of setting command line arguments for custom model and output directories.

```bash
set COMMANDLINE_ARGS=--ckpt-dir /path/to/models --outdir /path/to/outputs
```

--------------------------------

### ComfyUI Node Configuration Examples

Source: https://learn.thinkdiffusion.com/content/files/2025/09/ThinkDiffusion-StableDiffusion-ComfyUI-Reference2Video-VACE-Control-with-Reference-FIXED-2.json

JSON definitions for WanVideoSampler, GetNode, and AddLabel nodes used in ComfyUI workflows.

```json
{
          "name": "fantasytalking_embeds",
          "shape": 7,
          "type": "FANTASYTALKING_EMBEDS",
          "link": null
        },
        {
          "name": "uni3c_embeds",
          "shape": 7,
          "type": "UNI3C_EMBEDS",
          "link": null
        },
        {
          "name": "multitalk_embeds",
          "shape": 7,
          "type": "MULTITALK_EMBEDS",
          "link": null
        },
        {
          "name": "freeinit_args",
          "shape": 7,
          "type": "FREEINITARGS",
          "link": null
        },
        {
          "name": "teacache_args",
          "shape": 7,
          "type": "TEACACHEARGS",
          "link": 334
        }
      ],
      "outputs": [
        {
          "name": "samples",
          "type": "LATENT",
          "links": [
            298
          ]
        },
        {
          "name": "denoised_samples",
          "type": "LATENT",
          "links": null
        }
      ],
      "properties": {
        "cnr_id": "ComfyUI-WanVideoWrapper",
        "ver": "2d2a184723dae88388e130659f51c36fcadeaba8",
        "Node name for S&R": "WanVideoSampler",
        "ue_properties": {
          "widget_ue_connectable": {},
          "version": "7.1",
          "input_ue_unconnectable": {}
        }
      },
      "widgets_values": [
        20,
        4.000000000000001,
        8.000000000000002,
        267786354346554,
        "randomize",
        true,
        "unipc",
        0,
        1,
        false,
        "comfy",
        0,
        -1,
        false
      ]
    },
    {
      "id": 166,
      "type": "GetNode",
      "pos": [
        2469.59619140625,
        -1097.7593994140625
      ],
      "size": [
        210,
        58
      ],
      "flags": {
        "collapsed": true
      },
      "order": 17,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "WANVAE",
          "type": "WANVAE",
          "links": [
            297
          ]
        }
      ],
      "title": "Get_WanVAE",
      "properties": {
        "ue_properties": {
          "widget_ue_connectable": {},
          "version": "7.1",
          "input_ue_unconnectable": {}
        }
      },
      "widgets_values": [
        "WanVAE"
      ],
      "color": "#322",
      "bgcolor": "#533"
    },
    {
      "id": 153,
      "type": "GetNode",
      "pos": [
        2529.59619140625,
        -867.7593994140625
      ],
      "size": [
        233.0802459716797,
        60.23356246948242
      ],
      "flags": {
        "collapsed": true
      },
      "order": 18,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            319
          ]
        }
      ],
      "title": "Get_reference_image",
      "properties": {
        "ue_properties": {
          "widget_ue_connectable": {},
          "version": "7.1",
          "input_ue_unconnectable": {}
        }
      },
      "widgets_values": [
        "reference_image"
      ],
      "color": "#2a363b",
      "bgcolor": "#3f5159"
    },
    {
      "id": 250,
      "type": "GetNode",
      "pos": [
        2539.59619140625,
        -807.7593994140625
      ],
      "size": [
        257.8947448730469,
        58
      ],
      "flags": {
        "collapsed": true
      },
      "order": 19,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            456
          ]
        }
      ],
      "title": "Get_original_video",
      "properties": {
        "ue_properties": {
          "widget_ue_connectable": {},
          "version": "7.1",
          "input_ue_unconnectable": {}
        }
      },
      "widgets_values": [
        "original_video"
      ],
      "color": "#2a363b",
      "bgcolor": "#3f5159"
    },
    {
      "id": 156,
      "type": "AddLabel",
      "pos": [
        2579.59619140625,
        -857.7593994140625
      ],
      "size": [
        315,
        274
      ],
      "flags": {
        "collapsed": true
      },
      "order": 33,
      "mode": 0,
      "inputs": [
        {
          "name": "image",
          "type": "IMAGE",
          "link": 319
        },
        {
          "name": "caption",
          "shape": 7,
          "type": "STRING",
          "link": null
        }
      ],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            290
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfyui-kjnodes",
        "ver": "52c2e31a903fec2dd654fb614ea82ba2757d5028",
        "Node name for S&R": "AddLabel",
        "ue_properties": {
          "widget_ue_connectable": {},
          "version": "7.1",
          "input_ue_unconnectable": {}
        }
      },
      "widgets_values": [
        10,
        2,
        48,
        32,
        "white",
        "black",
        "FreeMono.ttf"
```

--------------------------------

### Preview Image Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/04/Style-Transfer-Dance-Noodle-1.json

Sets up a node to preview images with custom background overrides.

```json
{
      "id": 210,
      "type": "PreviewImage",
      "pos": [
        -2470,
        1920
      ],
      "size": [
        223.60797119140625,
        246
      ],
      "flags": {},
      "order": 48,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 472,
          "slot_index": 0
        }
      ],
      "outputs": [],
      "title": "Preview Mask",
      "properties": {
        "Node name for S&R": "PreviewImage",
        "ttNbgOverride": {
          "color": "#222",
          "bgcolor": "#000",
          "groupcolor": "#444"
        }
      },
      "widgets_values": [],
      "color": "#222",
      "bgcolor": "#000"
    }
```

--------------------------------

### Get Width Node

Source: https://learn.thinkdiffusion.com/content/files/2025/08/ThinkDiffusion-StableDiffusion-ComfyUI-Image2Video-Wan-Uni3C-FIXED-2.json

A collapsed utility node used to retrieve the width parameter.

```json
{
  "id": 178,
  "type": "GetNode",
  "pos": [
    -772.6264038085938,
    -1570
  ],
  "size": [
    210,
    58
  ],
  "flags": {
    "collapsed": true
  },
  "order": 5,
  "mode": 0,
  "inputs": [],
  "outputs": [
    {
      "label": "WANVAE",
      "name": "INT",
      "type": "INT",
      "links": [
        219
      ]
    }
  ],
  "title": "Get_width",
  "properties": {},
  "widgets_values": [
    "width"
  ],
  "color": "#1b4669",
  "bgcolor": "#29699c"
}
```

--------------------------------

### Clone and Navigate Automatic1111 Repository

Source: https://learn.thinkdiffusion.com/automatic1111-in-the-cloud-guide

Commands to download the repository and enter the directory.

```bash
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
cd stable-diffusion-webui
```

--------------------------------

### Preview Image Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/01/ThinkDiffusion-StableDiffusion-ComfyUI-Style-Transfer-Dance-Noodle.json

Sets up a node to display image outputs within the ComfyUI workspace.

```json
    {
      "id": 210,
      "type": "PreviewImage",
      "pos": [
        -2470,
        1920
      ],
      "size": [
        223.60797119140625,
        246
      ],
      "flags": {},
      "order": 48,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 472,
          "slot_index": 0
        }
      ],
      "outputs": [],
      "title": "Preview Mask",
      "properties": {
        "Node name for S&R": "PreviewImage",
        "ttNbgOverride": {
          "color": "#222",
          "bgcolor": "#000",
          "groupcolor": "#444"
        }
      },
      "widgets_values": [],
      "color": "#222",
      "bgcolor": "#000"
    }
```

--------------------------------

### Get and Set Node Configurations

Source: https://learn.thinkdiffusion.com/content/files/2025/09/ThinkDiffusion-StableDiffusion-ComfyUI-Wan2.1-InfiniteTalk_V2V.json

JSON definitions for GetNode and SetNode utility nodes used for managing workflow variables.

```json
{
      "id": 272,
      "type": "GetNode",
      "pos": [
        2054.598876953125,
        -2717.357666015625
      ],
      "size": [
        210,
        60
      ],
      "flags": {
        "collapsed": true
      },
      "order": 12,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "INT",
          "type": "INT",
          "links": [
            544
          ]
        }
      ],
      "title": "Get_max_frames",
      "properties": {},
      "widgets_values": [
        "max_frames"
      ],
      "color": "#1b4669",
      "bgcolor": "#29699c"
    },
    {
      "id": 253,
      "type": "SetNode",
      "pos": [
        2048.661865234375,
        -2716.11669921875
      ],
      "size": [
        210,
        60
      ],
      "flags": {
        "collapsed": true
      },
      "order": 37,
      "mode": 0,
      "inputs": [
        {
          "name": "AUDIO",
          "type": "AUDIO",
```

--------------------------------

### Get Image Size and Count Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/03/ThinkDiffusion-StableDiffusion-ComfyUI-Hunyuan-Video2Video.json

Configuration for the GetImageSizeAndCount node used to extract metadata from input images.

```json
{
      "id": 39,
      "type": "GetImageSizeAndCount",
      "pos": [
        -309.3996887207031,
        -284.49066162109375
      ],
      "size": [
        277.20001220703125,
        86
      ],
      "flags": {
        "collapsed": true
      },
      "order": 13,
      "mode": 0,
      "inputs": [
        {
          "name": "image",
          "type": "IMAGE",
          "link": 81
        }
      ],
      "outputs": [
        {
          "name": "image",
          "type": "IMAGE",
          "links": [
            49,
            58
          ],
          "slot_index": 0
        },
        {
          "name": "width",
          "label": "768 width",
          "type": "INT",
          "links": [
            55
          ],
          "slot_index": 1
        },
        {
          "name": "height",
          "label": "448 height",
          "type": "INT",
          "links": [
            56
          ],
          "slot_index": 2
        },
        {
          "name": "count",
          "label": "21 count",
          "type": "INT",
          "links": [
            57
          ],
          "slot_index": 3
        }
      ],
      "properties": {
        "Node name for S&R": "GetImageSizeAndCount"
      },
      "widgets_values": []
    }
```

--------------------------------

### Define ComfyUI Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2024/06/TD_Odyssey.json

Example of a node definition within a ComfyUI workflow, showing properties, widget values, and input/output connections.

```json
],
      "properties": {
        "Node name for S&R": "CLIPTextEncode"
      },
      "widgets_values": [
        "ugly, deformed, bad lighting, blurry, text, watermark, extra hands, bad quality, deformed hands, deformed fingers, nostalgic, drawing, painting, bad anatomy, worst quality, blurry, blurred, normal quality, bad focus, tripod, three legs, weird legs, short legs"
      ],
      "color": "#322",
      "bgcolor": "#533"
    },
    {
      "id": 111,
      "type": "VHS_LoadVideo",
      "pos": [
        -991,
        -998
      ],
      "size": [
        235.1999969482422,
        658.5777723524305
      ],
      "flags": {},
      "order": 8,
      "mode": 0,
      "inputs": [
        {
          "name": "meta_batch",
          "type": "VHS_BatchManager",
          "link": null
        }
      ],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            230
          ],
          "shape": 3,
          "slot_index": 0
        },
        {
          "name": "frame_count",
          "type": "INT",
          "links": null,
          "shape": 3
        },
        {
          "name": "audio",
          "type": "VHS_AUDIO",
          "links": null,
          "shape": 3
        },
        {
          "name": "video_info",
          "type": "VHS_VIDEOINFO",
          "links": null,
          "shape": 3
        }
      ],
      "properties": {
        "Node name for S&R": "VHS_LoadVideo"
      },
      "widgets_values": {
        "video": "main.mp4",
        "force_rate": 0,
        "force_size": "Disabled",
        "custom_width": 520,
        "custom_height": 512,
        "frame_load_cap": 12,
        "skip_first_frames": 0,
        "select_every_nth": 1,
        "choose video to upload": "image",
        "videopreview": {
          "hidden": false,
          "paused": false,
          "params": {
            "frame_load_cap": 12,
            "skip_first_frames": 0,
            "force_rate": 0,
            "filename": "main.mp4",
            "type": "input",
            "format": "video/mp4",
            "select_every_nth": 1,
            "force_size": "Disabled"
          }
        }
      }
    }
```

--------------------------------

### GetNode Configurations

Source: https://learn.thinkdiffusion.com/content/files/2025/04/ThinkDiffusion-StableDiffusion-ComfyUI-Vid2Vid-Wan-ReCamMaster-v3.json

Configurations for retrieving WanVideo model and text embedding nodes.

```json
{
      "id": 141,
      "type": "GetNode",
      "pos": [
        692.23876953125,
        -729.8995971679688
      ],
      "size": [
        210,
        60
      ],
      "flags": {
        "collapsed": true
      },
      "order": 26,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "label": "WANVIDEOMODEL",
          "name": "MODEL",
          "type": "MODEL",
          "links": [
            407
          ]
        }
      ],
      "title": "Get_wan_model",
      "properties": {},
      "widgets_values": [
        "wan_model"
      ],
      "color": "#223",
      "bgcolor": "#335"
    }
```

```json
{
      "id": 143,
      "type": "GetNode",
      "pos": [
        669.94970703125,
        -589.6582641601562
      ],
      "size": [
        250.43063354492188,
        58
      ],
      "flags": {
        "collapsed": true
      },
      "order": 27,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "label": "WANVIDEOTEXTEMBEDS",
          "name": "WANVIDEOTEXTEMBEDS",
          "type": "WANVIDEOTEXTEMBEDS",
          "links": [
            267
          ]
        }
      ],
      "title": "Get_wan_txt_embeds",
      "properties": {},
      "widgets_values": [
        "wan_txt_embeds"
      ],
      "color": "#432",
      "bgcolor": "#653"
    }
```

--------------------------------

### Wan Video Model Loader Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/04/ThinkDiffusion-StableDiffusion-ComfyUI-Video2Video-Wan-Style-Transfer.json

Configuration for loading the Wan Video model with specific device and precision settings.

```json
{
      "id": 22,
      "type": "WanVideoModelLoader",
      "pos": [
        -1127.0413818359375,
        -996.92724609375
      ],
      "size": [
        398.23052978515625,
        234
      ],
      "flags": {},
      "order": 22,
      "mode": 0,
      "inputs": [
        {
          "name": "compile_args",
          "shape": 7,
          "type": "WANCOMPILEARGS",
          "link": null
        },
        {
          "name": "block_swap_args",
          "shape": 7,
          "type": "BLOCKSWAPARGS",
          "link": null
        },
        {
          "name": "lora",
          "shape": 7,
          "type": "WANVIDLORA",
          "link": null
        },
        {
          "name": "vram_management_args",
          "shape": 7,
          "type": "VRAM_MANAGEMENTARGS",
          "link": null
        },
        {
          "name": "vace_model",
          "shape": 7,
          "type": "VACEPATH",
          "link": null
        }
      ],
      "outputs": [
        {
          "name": "model",
          "type": "WANVIDEOMODEL",
          "slot_index": 0,
          "links": [
            29,
            103
          ]
        }
      ],
      "properties": {
        "cnr_id": "ComfyUI-WanVideoWrapper",
        "ver": "d20baf00247fd06553fdc9253e18732244e54172",
        "Node name for S&R": "WanVideoModelLoader"
      },
      "widgets_values": [
        "Wan2.1-Fun-Control-14B_fp8_e4m3fn.safetensors",
        "fp16",
        "fp8_e4m3fn",
        "offload_device",
        "sdpa"
      ],
      "color": "#323",
      "bgcolor": "#535"
    }
```

--------------------------------

### WanVideoExperimentalArgs Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/09/ThinkDiffusion-StableDiffusion-ComfyUI-Reference2Video-VACE-Control-with-Reference-FIXED-2.json

Configuration for the WanVideoExperimentalArgs node, defining various experimental parameters.

```json
{
      "id": 150,
      "type": "WanVideoExperimentalArgs",
      "pos": [
        1679.595947265625,
        -337.7593994140625
      ],
      "size": [
        327.5999755859375,
        298
      ],
      "flags": {},
      "order": 16,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "exp_args",
          "type": "EXPERIMENTALARGS",
          "links": [
            306
          ]
        }
      ],
      "properties": {
        "cnr_id": "ComfyUI-WanVideoWrapper",
        "ver": "2d2a184723dae88388e130659f51c36fcadeaba8",
        "Node name for S&R": "WanVideoExperimentalArgs",
        "ue_properties": {
          "widget_ue_connectable": {},
          "version": "7.1",
          "input_ue_unconnectable": {}
        }
      },
      "widgets_values": [
        "",
        true,
        false,
        0,
        false,
        1,
        1.25,
        20,
        false,
        0,
        false
      ]
    }
```

--------------------------------

### Configure DownloadAndLoadCogVideoModel Node

Source: https://learn.thinkdiffusion.com/content/files/2024/12/ThinkDiffusion-StableDiffusion-ComfyUI-CogVideoX.json

Sets up the model loader for CogVideoX, specifying the model repository and device settings.

```json
{
      "id": 59,
      "type": "DownloadAndLoadCogVideoModel",
      "pos": [
        471,
        66
      ],
      "size": [
        315,
        218
      ],
      "flags": {},
      "order": 6,
      "mode": 0,
      "inputs": [
        {
          "name": "block_edit",
          "type": "TRANSFORMERBLOCKS",
          "link": null,
          "shape": 7
        },
        {
          "name": "lora",
          "type": "COGLORA",
          "link": null,
          "shape": 7
        },
        {
          "name": "compile_args",
          "type": "COMPILEARGS",
          "link": null,
          "shape": 7
        }
      ],
      "outputs": [
        {
          "name": "model",
          "type": "COGVIDEOMODEL",
          "links": [
            144
          ]
        },
        {
          "name": "vae",
          "type": "VAE",
          "links": [
            132,
            141
          ],
          "slot_index": 1
        }
      ],
      "properties": {
        "Node name for S&R": "DownloadAndLoadCogVideoModel"
      },
      "widgets_values": [
        "kijai/CogVideoX-5b-1.5-I2V",
        "bf16",
        "disabled",
        false,
        "sdpa",
        "main_device"
      ],
      "color": "#323",
      "bgcolor": "#535"
    }
```

--------------------------------

### Video Preview Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/04/ThinkDiffusion-StableDiffusion-ComfyUI-Vid2Vid_Depth_Control_LoRA_Comfy_v0329.json

Configuration object for a video preview node, defining output paths and format settings.

```json
        "save_metadata": true,
        "trim_to_audio": false,
        "pingpong": false,
        "save_output": true,
        "videopreview": {
          "hidden": false,
          "paused": false,
          "params": {
            "filename": "WanVideo_00064.mp4",
            "subfolder": "",
            "type": "output",
            "format": "video/h264-mp4",
            "frame_rate": 16,
            "workflow": "WanVideo_00064.png",
            "fullpath": "/home/ubuntu/user_data/comfyui/outputs/WanVideo_00064.mp4"
          }
        }
      }
    }
```

--------------------------------

### PreviewImage Node Configurations

Source: https://learn.thinkdiffusion.com/content/files/2025/01/ThinkDiffusion_Character_Consistency_Flux.json

Configurations for PreviewImage nodes used to display output images.

```json
{
      "id": 356,
      "type": "PreviewImage",
      "pos": [
        -1405.7767333984375,
        937.5159912109375
      ],
      "size": [
        429.7591247558594,
        487.59930419921875
      ],
      "flags": {},
      "order": 42,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 703
        }
      ],
      "outputs": [],
      "properties": {
        "Node name for S&R": "PreviewImage"
      },
      "widgets_values": []
    }
```

```json
{
      "id": 140,
      "type": "PreviewImage",
      "pos": [
        -471.7761535644531,
        907.5160522460938
      ],
      "size": [
        466.0791320800781,
        510.5869445800781
      ],
      "flags": {},
      "order": 47,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 285
        }
      ],
      "outputs": [],
      "properties": {
        "Node name for S&R": "PreviewImage"
      },
      "widgets_values": []
    }
```

--------------------------------

### WanVideoVAELoader Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/04/Video2Video-Wan-Style-Transfer.json

Configuration for the WanVideoVAELoader node, specifying the VAE model file and precision settings.

```json
"type": "WanVideoVAELoader",
      "pos": [
        -1058.8778076171875,
        -715.0900268554688
      ],
      "size": [
        290,
        82
      ],
      "flags": {},
      "order": 23,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "vae",
          "type": "WANVAE",
          "slot_index": 0,
          "links": [
            239
          ]
        }
      ],
      "properties": {
        "cnr_id": "ComfyUI-WanVideoWrapper",
        "ver": "d20baf00247fd06553fdc9253e18732244e54172",
        "Node name for S&R": "WanVideoVAELoader"
      },
      "widgets_values": [
        "Wan2_1_VAE_bf16.safetensors",
        "bf16"
      ],
      "color": "#323",
      "bgcolor": "#535"
    }
```

--------------------------------

### Load Reference Video Node Configuration

Source: https://learn.thinkdiffusion.com/content/files/2025/04/Video2Video-Wan-Style-Transfer.json

Configuration for a UI node used to load reference video files.

```json
{
  "allow_interaction": true
},
"order": 19,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Load Reference Video",
"properties": {
  "fontSize": 30,
  "fontFamily": "Arial",
  "fontColor": "#ffffff",
  "textAlign": "left",
  "backgroundColor": "transparent",
  "padding": 0,
  "borderRadius": 0
},
"color": "#fff0",
"bgcolor": "#fff0"
```