{
  "id": "nvidia_background",
  "name": "Nvidia Background",
  "displayName": "Nvidia Background",
  "category": "TOP",
  "subcategory": "NVIDIA",
  "version": "",
  "lastUpdated": "2025-08-08T00:37:48.386Z",
  "sourceFile": "C:\\Program Files\\Derivative\\TouchDesigner\\Samples\\Learn\\OfflineHelp\\https.docs.derivative.ca\\Nvidia_Background_TOP.htm",
  "url": "",
  "description": "OS: This operator is only supported under the Microsoft Windows operating system.Hardware: This TOP uses the AI Green Screening module from the Nvidia Maxine Video Effects engine and requires a 20, 30 or 40 series Nvidia RTX card to operate.",
  "summary": "OS: This operator is only supported under the Microsoft Windows operating system.Hardware: This TOP uses the AI Green Screening module from the Nvidia Maxine Video Effects engine and requires a 20, 30",
  "details": "",
  "usage": "",
  "tips": [],
  "warnings": [],
  "parameters": [
    {
      "id": null,
      "name": "Model Folder",
      "label": "Model Folder",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "From Derivative\n\t\t\n\t\t\n\t\t\n\t\t\n\t\tJump to navigation\n\t\tJump to search\n\t\t\nNOTE\n\nOS: This operator is only supported under the Microsoft Windows operating system.Hardware: This  uses the AI Green Screening module from the Nvidia Maxine Video Effects engine and requires a 20, 30 or 40 series Nvidia RTX card to operate.\n\n\n\nThe Nvidia Background  performs AI image segmentation to separate a person from the background of a given image. Unlike the RGB Key TOP or the Chroma Key TOP, the background top uses AI to identify the foreground and background portions of the image and does not require a solid background color. However, the AI model is trained to look for specific image patterns (a person in front of a webcam) and may not perform as well on generic input as the key TOPS. The output of the node is a monochrome key image where white pixels indicate the foreground person and black pixels represent the background. Commonly, this key image is used to replace the background of the source image using the Matte TOP or other compositing nodes. \nDue to the time it takes to run the AI model, the output of the Background  will be multiple frames behind the original image when processing a video input. For accurate compositing you will want to match the output key image with the original frame that was used to produce it. An easy way to do this is to use a Cache TOP with the Output Index set to a negative number of frames. When placed between the source video and the compositor input, this will delay the source image so that it synchronizes with the key image.\nTip: The AI model is tuned for a single person sitting in front of a webcam. Videos including full body images, multiple people or indirect camera angles may not perform well.\nTip: In addition to selecting Performance using the mode parameter, you can also reduce  load by reducing the resolution of the input image. The Blur TOP and Level TOP may also be useful to refine the output key image before compositing.\nnvidiabackgroundTOP_Class\n\nContents\n \n \n \n \n \n \n \n\n\n\n\n\n  modelfolder - The location of the AI model files used to perform the image segmentation. By default, these files are included inside the Config/Models folder inside your TouchDesigner installation folder. You can use this parameter to point to an alternative folder with compatible model files.\n\n\n\n  mode -  - Choose which mode to run the AI model in.\n\n quality - Run the high quality image segmentation model. This model will run slower, but may produce a better quality key image. performance - Run the high performance AI model. This model will run faster, but may produce a lower quality key image.\n\n\n\n  outputresolution -  - quickly change the resolution of the 's data.\n\n useinput - Uses the input's resolution. eighth - Multiply the input's resolution by that amount. quarter - Multiply the input's resolution by that amount. half - Multiply the input's resolution by that amount. 2x - Multiply the input's resolution by that amount. 4x - Multiply the input's resolution by that amount. 8x - Multiply the input's resolution by that amount. fit - Fits the width and height to the resolution given below, while maintaining the aspect ratio. limit - The width and height are limited to the resolution given below. If one of the dimensions exceeds the given resolution, the width and height will be reduced to fit inside the given limits while maintaining the aspect ratio. custom - Enables the  parameter below, giving direct control over width and height.\n\n  resolution -  - Enabled only when the  parameter is set to Custom . Some Generators like Constant and Ramp do not use inputs and only use this field to determine their size. The drop down menu on the right provides some commonly used resolutions.\n\n resolutionw - resolutionh -\n\n  resmenu - A drop-down menu with some commonly used resolutions.\n\n\n\n  resmult - Uses the Global  Multiplier found in Edit>Preferences>TOPs. This multiplies all the TOPs resolutions by the set amount. This is handy when working on computers with different hardware specifications. If a project is designed on a desktop workstation with lots of graphics memory, a user on a laptop with only 64MB VRAM can set the Global  Multiplier to a value of half or quarter so it runs at an acceptable speed. By checking this checkbox on, this  is affected by the global multiplier.\n\n\n\n  outputaspect -  - Sets the image aspect ratio allowing any textures to be viewed in any size. Watch for unexpected results when compositing TOPs with different aspect ratios. (You can define images with non-square pixels using xres, yres, aspectx, aspecty where xres/yres != aspectx/aspecty.)\n\n useinput - Uses the input's aspect ratio. resolution - Uses the aspect of the image's defined resolution (ie 512x256 would be 2:1), whereby each pixel is square. custom - Lets you explicitly define a custom aspect ratio in the Aspect parameter below.\n\n  aspect -  - Use when Output Aspect parameter is set to Custom Aspect.\n\n aspect1 - aspect2 -\n\n  armenu - A drop-down menu with some commonly used aspect ratios.\n\n\n\n  inputfiltertype -  - This controls pixel filtering on the input image of the .\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. This is how you get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.\n\n  fillmode -  - Determine how the  image is displayed in the viewer.\nNOTE:To get an understanding of how TOPs work with images, you will want to set this to Native  as you lay down TOPs when starting out. This will let you see what is actually happening without any automatic viewer resizing.\n\n\n useinput - Uses the same Fill Viewer settings as it's input. fill - Stretches the image to fit the edges of the viewer. width - Stretches image to fit viewer horizontally. height - Stretches image to fit viewer vertically. best - Stretches or squashes image so no part of image is cropped. outside - Stretches or squashes image so image fills viewer while constraining it's proportions. This often leads to part of image getting cropped by viewer. nativeres - Displays the native resolution of the image in the viewer.\n\n  filtertype -  - This controls pixel filtering in the viewers.\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. Use this to get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.\n\n  npasses - Duplicates the operation of the  the specified number of times. Making this larger than 1 is essentially the same as taking the output from each pass, and passing it into the first input of the node and repeating the process. Other inputs and parameters remain the same for each pass.\n\n\n\n  chanmask - Allows you to choose which channels (R, G, B, or A) the  will operate on. All channels are selected by default.\n\n\n\n  format -  - Format used to store data for each channel in the image (ie. R, G, B, and A). Refer to Pixel Formats for more information.\n\n useinput - Uses the input's pixel format. rgba8fixed - Uses 8-bit integer values for each channel. srgba8fixed - Uses 8-bit integer values for each channel and stores color in sRGB colorspace. rgba16float - Uses 16-bits per color channel, 64-bits per pixel. rgba32float - Uses 32-bits per color channel, 128-bits per pixels. rgb10a2fixed - Uses 10-bits per color channel and 2-bits for alpha, 32-bits total per pixel. rgba16fixed - Uses 16-bits per color channel, 64-bits total per pixel. rgba11float - A RGB floating point format that has 11 bits for the Red and Green channels, and 10-bits for the Blue , 32-bits total per pixel (therefore the same memory usage as 8-bit RGBA). The Alpha channel in this format will always be 1. Values can go above one, but can't be negative. ie. the range is [0, infinite). rgb16float - rgb32float - mono8fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 8-bits per pixel. mono16fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono16float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono32float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 32-bits per pixel. rg8fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 8-bits per channel, 16-bits total per pixel. rg16fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg16float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg32float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 32-bits per channel, 64-bits total per pixel. a8fixed - An Alpha only format that has 8-bits per channel, 8-bits per pixel. a16fixed - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a16float - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a32float - An Alpha only format that has 32-bits per channel, 32-bits per pixel. monoalpha8fixed - A 2 channel format, one value for RGB and one value for Alpha. 8-bits per channel, 16-bits per pixel. monoalpha16fixed - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha16float - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha32float - A 2 channel format, one value for RGB and one value for Alpha. 32-bits per channel, 64-bits per pixel.\n\n\n\n -\n\n\nExtra Information for the Nvidia Background  can be accessed via an Info CHOP.\n\n\n\n - Horizontal resolution of the  in pixels. - Vertical resolution of the  in pixels. - Horizontal aspect of the . - Vertical aspect of the . - Depth of 2D or 3D array if this  contains a 2D or 3D texture array. - Total amount of texture memory used by this .\n - Number of times the operator has cooked since the process started. - Duration of the last cook in milliseconds. - Frame number when this operator was last cooked relative to the component timeline. - Frame number when this operator was last cooked relative to the absolute time. - Time in milliseconds at which the operator started cooking in the frame it was cooked. - Time in milliseconds at which the operator finished cooking in the frame it was cooked. - 1 if operator was cooked this frame. - Number of warnings in this operator if any. - Number of errors in this operator if any.\nTouchDesigner Build: Latest\\nwikieditorwikieditorwikieditorbefore wikieditor\nTOPs\n• • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • \n\nAn Operator Family that creates, composites and modifies images, and reads/writes images and movies to/from files and the network. TOPs run on the graphics card's GPU.\n\n\n\nThe Graphics Processing Unit. This is the high-speed, many-core processor of the graphics card/chip that takes geometry, images and data from the CPU and creates images and processed data.\n\n\n\nA Folder in TouchDesigner always refers to a Windows or macOS operating system directory/folder system that contain files and other folders. It does not refer to operators within TouchDesigner. See Network Path.\n\n\n\nThe width and height of an image in pixels. Most TOPs, like the Movie File In TOP can set the image resolution. See Aspect Ratio for the width/height ratio of an image, taking into account non-square pixels.\n\n\n\nThe viewer of a node can be (1) the interior of a node (the Node Viewer), (2) a floating window (RMB->View... on node), or (3) a Pane that graphically shows the results of an operator.\n\n\n\nA CHOP outputs one or more channels, where a channel is simply a sequence of numbers (Samples), representing motion, audio, etc. Channels are passed between CHOPs in TouchDesigner networks. Channels can be Exported to Parameters.\n\n\n\nAn Operator Family which operate on Channels (a sequence of numbers (Samples)) which are used for animation, audio, mathematics, simulation, logic, UI construction, and data streamed from/to devices and protocols.\n\n\n\n\n\n\n\n\nRetrieved from \"https://docs.derivative.ca/index.php?title=Nvidia_Background_TOP&oldid=30816\"\n\t\tCategory: TOPs",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.379Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Model Folder",
      "label": "Model Folder",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "From Derivative\n\t\t\n\t\t\n\t\t\n\t\t\n\t\tJump to navigation\n\t\tJump to search\n\t\t\nNOTE\n\nOS: This operator is only supported under the Microsoft Windows operating system.Hardware: This  uses the AI Green Screening module from the Nvidia Maxine Video Effects engine and requires a 20, 30 or 40 series Nvidia RTX card to operate.\n\n\n\nThe Nvidia Background  performs AI image segmentation to separate a person from the background of a given image. Unlike the RGB Key TOP or the Chroma Key TOP, the background top uses AI to identify the foreground and background portions of the image and does not require a solid background color. However, the AI model is trained to look for specific image patterns (a person in front of a webcam) and may not perform as well on generic input as the key TOPS. The output of the node is a monochrome key image where white pixels indicate the foreground person and black pixels represent the background. Commonly, this key image is used to replace the background of the source image using the Matte TOP or other compositing nodes. \nDue to the time it takes to run the AI model, the output of the Background  will be multiple frames behind the original image when processing a video input. For accurate compositing you will want to match the output key image with the original frame that was used to produce it. An easy way to do this is to use a Cache TOP with the Output Index set to a negative number of frames. When placed between the source video and the compositor input, this will delay the source image so that it synchronizes with the key image.\nTip: The AI model is tuned for a single person sitting in front of a webcam. Videos including full body images, multiple people or indirect camera angles may not perform well.\nTip: In addition to selecting Performance using the mode parameter, you can also reduce  load by reducing the resolution of the input image. The Blur TOP and Level TOP may also be useful to refine the output key image before compositing.\nnvidiabackgroundTOP_Class\n\nContents\n \n \n \n \n \n \n \n\n\n\n\n\n  modelfolder - The location of the AI model files used to perform the image segmentation. By default, these files are included inside the Config/Models folder inside your TouchDesigner installation folder. You can use this parameter to point to an alternative folder with compatible model files.\n\n\n\n  mode -  - Choose which mode to run the AI model in.\n\n quality - Run the high quality image segmentation model. This model will run slower, but may produce a better quality key image. performance - Run the high performance AI model. This model will run faster, but may produce a lower quality key image.\n\n\n\n  outputresolution -  - quickly change the resolution of the 's data.\n\n useinput - Uses the input's resolution. eighth - Multiply the input's resolution by that amount. quarter - Multiply the input's resolution by that amount. half - Multiply the input's resolution by that amount. 2x - Multiply the input's resolution by that amount. 4x - Multiply the input's resolution by that amount. 8x - Multiply the input's resolution by that amount. fit - Fits the width and height to the resolution given below, while maintaining the aspect ratio. limit - The width and height are limited to the resolution given below. If one of the dimensions exceeds the given resolution, the width and height will be reduced to fit inside the given limits while maintaining the aspect ratio. custom - Enables the  parameter below, giving direct control over width and height.\n\n  resolution -  - Enabled only when the  parameter is set to Custom . Some Generators like Constant and Ramp do not use inputs and only use this field to determine their size. The drop down menu on the right provides some commonly used resolutions.\n\n resolutionw - resolutionh -\n\n  resmenu - A drop-down menu with some commonly used resolutions.\n\n\n\n  resmult - Uses the Global  Multiplier found in Edit>Preferences>TOPs. This multiplies all the TOPs resolutions by the set amount. This is handy when working on computers with different hardware specifications. If a project is designed on a desktop workstation with lots of graphics memory, a user on a laptop with only 64MB VRAM can set the Global  Multiplier to a value of half or quarter so it runs at an acceptable speed. By checking this checkbox on, this  is affected by the global multiplier.\n\n\n\n  outputaspect -  - Sets the image aspect ratio allowing any textures to be viewed in any size. Watch for unexpected results when compositing TOPs with different aspect ratios. (You can define images with non-square pixels using xres, yres, aspectx, aspecty where xres/yres != aspectx/aspecty.)\n\n useinput - Uses the input's aspect ratio. resolution - Uses the aspect of the image's defined resolution (ie 512x256 would be 2:1), whereby each pixel is square. custom - Lets you explicitly define a custom aspect ratio in the Aspect parameter below.\n\n  aspect -  - Use when Output Aspect parameter is set to Custom Aspect.\n\n aspect1 - aspect2 -\n\n  armenu - A drop-down menu with some commonly used aspect ratios.\n\n\n\n  inputfiltertype -  - This controls pixel filtering on the input image of the .\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. This is how you get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.\n\n  fillmode -  - Determine how the  image is displayed in the viewer.\nNOTE:To get an understanding of how TOPs work with images, you will want to set this to Native  as you lay down TOPs when starting out. This will let you see what is actually happening without any automatic viewer resizing.\n\n\n useinput - Uses the same Fill Viewer settings as it's input. fill - Stretches the image to fit the edges of the viewer. width - Stretches image to fit viewer horizontally. height - Stretches image to fit viewer vertically. best - Stretches or squashes image so no part of image is cropped. outside - Stretches or squashes image so image fills viewer while constraining it's proportions. This often leads to part of image getting cropped by viewer. nativeres - Displays the native resolution of the image in the viewer.\n\n  filtertype -  - This controls pixel filtering in the viewers.\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. Use this to get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.\n\n  npasses - Duplicates the operation of the  the specified number of times. Making this larger than 1 is essentially the same as taking the output from each pass, and passing it into the first input of the node and repeating the process. Other inputs and parameters remain the same for each pass.\n\n\n\n  chanmask - Allows you to choose which channels (R, G, B, or A) the  will operate on. All channels are selected by default.\n\n\n\n  format -  - Format used to store data for each channel in the image (ie. R, G, B, and A). Refer to Pixel Formats for more information.\n\n useinput - Uses the input's pixel format. rgba8fixed - Uses 8-bit integer values for each channel. srgba8fixed - Uses 8-bit integer values for each channel and stores color in sRGB colorspace. rgba16float - Uses 16-bits per color channel, 64-bits per pixel. rgba32float - Uses 32-bits per color channel, 128-bits per pixels. rgb10a2fixed - Uses 10-bits per color channel and 2-bits for alpha, 32-bits total per pixel. rgba16fixed - Uses 16-bits per color channel, 64-bits total per pixel. rgba11float - A RGB floating point format that has 11 bits for the Red and Green channels, and 10-bits for the Blue , 32-bits total per pixel (therefore the same memory usage as 8-bit RGBA). The Alpha channel in this format will always be 1. Values can go above one, but can't be negative. ie. the range is [0, infinite). rgb16float - rgb32float - mono8fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 8-bits per pixel. mono16fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono16float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono32float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 32-bits per pixel. rg8fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 8-bits per channel, 16-bits total per pixel. rg16fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg16float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg32float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 32-bits per channel, 64-bits total per pixel. a8fixed - An Alpha only format that has 8-bits per channel, 8-bits per pixel. a16fixed - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a16float - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a32float - An Alpha only format that has 32-bits per channel, 32-bits per pixel. monoalpha8fixed - A 2 channel format, one value for RGB and one value for Alpha. 8-bits per channel, 16-bits per pixel. monoalpha16fixed - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha16float - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha32float - A 2 channel format, one value for RGB and one value for Alpha. 32-bits per channel, 64-bits per pixel.\n\n\n\n -\n\n\nExtra Information for the Nvidia Background  can be accessed via an Info CHOP.\n\n\n\n - Horizontal resolution of the  in pixels. - Vertical resolution of the  in pixels. - Horizontal aspect of the . - Vertical aspect of the . - Depth of 2D or 3D array if this  contains a 2D or 3D texture array. - Total amount of texture memory used by this .\n - Number of times the operator has cooked since the process started. - Duration of the last cook in milliseconds. - Frame number when this operator was last cooked relative to the component timeline. - Frame number when this operator was last cooked relative to the absolute time. - Time in milliseconds at which the operator started cooking in the frame it was cooked. - Time in milliseconds at which the operator finished cooking in the frame it was cooked. - 1 if operator was cooked this frame. - Number of warnings in this operator if any. - Number of errors in this operator if any.\nTouchDesigner Build: Latest\\nwikieditorwikieditorwikieditorbefore wikieditor\nTOPs\n• • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • \n\nAn Operator Family that creates, composites and modifies images, and reads/writes images and movies to/from files and the network. TOPs run on the graphics card's GPU.\n\n\n\nThe Graphics Processing Unit. This is the high-speed, many-core processor of the graphics card/chip that takes geometry, images and data from the CPU and creates images and processed data.\n\n\n\nA Folder in TouchDesigner always refers to a Windows or macOS operating system directory/folder system that contain files and other folders. It does not refer to operators within TouchDesigner. See Network Path.\n\n\n\nThe width and height of an image in pixels. Most TOPs, like the Movie File In TOP can set the image resolution. See Aspect Ratio for the width/height ratio of an image, taking into account non-square pixels.\n\n\n\nThe viewer of a node can be (1) the interior of a node (the Node Viewer), (2) a floating window (RMB->View... on node), or (3) a Pane that graphically shows the results of an operator.\n\n\n\nA CHOP outputs one or more channels, where a channel is simply a sequence of numbers (Samples), representing motion, audio, etc. Channels are passed between CHOPs in TouchDesigner networks. Channels can be Exported to Parameters.\n\n\n\nAn Operator Family which operate on Channels (a sequence of numbers (Samples)) which are used for animation, audio, mathematics, simulation, logic, UI construction, and data streamed from/to devices and protocols.\n\n\n\n\n\n\n\n\nRetrieved from \"https://docs.derivative.ca/index.php?title=Nvidia_Background_TOP&oldid=30816\"\n\t\tCategory: TOPs",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.381Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Model Folder",
      "label": "Model Folder",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "NOTE\n\nOS: This operator is only supported under the Microsoft Windows operating system.Hardware: This  uses the AI Green Screening module from the Nvidia Maxine Video Effects engine and requires a 20, 30 or 40 series Nvidia RTX card to operate.\n\n\n\nThe Nvidia Background  performs AI image segmentation to separate a person from the background of a given image. Unlike the RGB Key TOP or the Chroma Key TOP, the background top uses AI to identify the foreground and background portions of the image and does not require a solid background color. However, the AI model is trained to look for specific image patterns (a person in front of a webcam) and may not perform as well on generic input as the key TOPS. The output of the node is a monochrome key image where white pixels indicate the foreground person and black pixels represent the background. Commonly, this key image is used to replace the background of the source image using the Matte TOP or other compositing nodes. \nDue to the time it takes to run the AI model, the output of the Background  will be multiple frames behind the original image when processing a video input. For accurate compositing you will want to match the output key image with the original frame that was used to produce it. An easy way to do this is to use a Cache TOP with the Output Index set to a negative number of frames. When placed between the source video and the compositor input, this will delay the source image so that it synchronizes with the key image.\nTip: The AI model is tuned for a single person sitting in front of a webcam. Videos including full body images, multiple people or indirect camera angles may not perform well.\nTip: In addition to selecting Performance using the mode parameter, you can also reduce  load by reducing the resolution of the input image. The Blur TOP and Level TOP may also be useful to refine the output key image before compositing.\nnvidiabackgroundTOP_Class\n\nContents\n \n \n \n \n \n \n \n\n\n\n\n\n  modelfolder - The location of the AI model files used to perform the image segmentation. By default, these files are included inside the Config/Models folder inside your TouchDesigner installation folder. You can use this parameter to point to an alternative folder with compatible model files.\n\n\n\n  mode -  - Choose which mode to run the AI model in.\n\n quality - Run the high quality image segmentation model. This model will run slower, but may produce a better quality key image. performance - Run the high performance AI model. This model will run faster, but may produce a lower quality key image.\n\n\n\n  outputresolution -  - quickly change the resolution of the 's data.\n\n useinput - Uses the input's resolution. eighth - Multiply the input's resolution by that amount. quarter - Multiply the input's resolution by that amount. half - Multiply the input's resolution by that amount. 2x - Multiply the input's resolution by that amount. 4x - Multiply the input's resolution by that amount. 8x - Multiply the input's resolution by that amount. fit - Fits the width and height to the resolution given below, while maintaining the aspect ratio. limit - The width and height are limited to the resolution given below. If one of the dimensions exceeds the given resolution, the width and height will be reduced to fit inside the given limits while maintaining the aspect ratio. custom - Enables the  parameter below, giving direct control over width and height.\n\n  resolution -  - Enabled only when the  parameter is set to Custom . Some Generators like Constant and Ramp do not use inputs and only use this field to determine their size. The drop down menu on the right provides some commonly used resolutions.\n\n resolutionw - resolutionh -\n\n  resmenu - A drop-down menu with some commonly used resolutions.\n\n\n\n  resmult - Uses the Global  Multiplier found in Edit>Preferences>TOPs. This multiplies all the TOPs resolutions by the set amount. This is handy when working on computers with different hardware specifications. If a project is designed on a desktop workstation with lots of graphics memory, a user on a laptop with only 64MB VRAM can set the Global  Multiplier to a value of half or quarter so it runs at an acceptable speed. By checking this checkbox on, this  is affected by the global multiplier.\n\n\n\n  outputaspect -  - Sets the image aspect ratio allowing any textures to be viewed in any size. Watch for unexpected results when compositing TOPs with different aspect ratios. (You can define images with non-square pixels using xres, yres, aspectx, aspecty where xres/yres != aspectx/aspecty.)\n\n useinput - Uses the input's aspect ratio. resolution - Uses the aspect of the image's defined resolution (ie 512x256 would be 2:1), whereby each pixel is square. custom - Lets you explicitly define a custom aspect ratio in the Aspect parameter below.\n\n  aspect -  - Use when Output Aspect parameter is set to Custom Aspect.\n\n aspect1 - aspect2 -\n\n  armenu - A drop-down menu with some commonly used aspect ratios.\n\n\n\n  inputfiltertype -  - This controls pixel filtering on the input image of the .\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. This is how you get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.\n\n  fillmode -  - Determine how the  image is displayed in the viewer.\nNOTE:To get an understanding of how TOPs work with images, you will want to set this to Native  as you lay down TOPs when starting out. This will let you see what is actually happening without any automatic viewer resizing.\n\n\n useinput - Uses the same Fill Viewer settings as it's input. fill - Stretches the image to fit the edges of the viewer. width - Stretches image to fit viewer horizontally. height - Stretches image to fit viewer vertically. best - Stretches or squashes image so no part of image is cropped. outside - Stretches or squashes image so image fills viewer while constraining it's proportions. This often leads to part of image getting cropped by viewer. nativeres - Displays the native resolution of the image in the viewer.\n\n  filtertype -  - This controls pixel filtering in the viewers.\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. Use this to get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.\n\n  npasses - Duplicates the operation of the  the specified number of times. Making this larger than 1 is essentially the same as taking the output from each pass, and passing it into the first input of the node and repeating the process. Other inputs and parameters remain the same for each pass.\n\n\n\n  chanmask - Allows you to choose which channels (R, G, B, or A) the  will operate on. All channels are selected by default.\n\n\n\n  format -  - Format used to store data for each channel in the image (ie. R, G, B, and A). Refer to Pixel Formats for more information.\n\n useinput - Uses the input's pixel format. rgba8fixed - Uses 8-bit integer values for each channel. srgba8fixed - Uses 8-bit integer values for each channel and stores color in sRGB colorspace. rgba16float - Uses 16-bits per color channel, 64-bits per pixel. rgba32float - Uses 32-bits per color channel, 128-bits per pixels. rgb10a2fixed - Uses 10-bits per color channel and 2-bits for alpha, 32-bits total per pixel. rgba16fixed - Uses 16-bits per color channel, 64-bits total per pixel. rgba11float - A RGB floating point format that has 11 bits for the Red and Green channels, and 10-bits for the Blue , 32-bits total per pixel (therefore the same memory usage as 8-bit RGBA). The Alpha channel in this format will always be 1. Values can go above one, but can't be negative. ie. the range is [0, infinite). rgb16float - rgb32float - mono8fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 8-bits per pixel. mono16fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono16float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono32float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 32-bits per pixel. rg8fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 8-bits per channel, 16-bits total per pixel. rg16fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg16float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg32float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 32-bits per channel, 64-bits total per pixel. a8fixed - An Alpha only format that has 8-bits per channel, 8-bits per pixel. a16fixed - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a16float - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a32float - An Alpha only format that has 32-bits per channel, 32-bits per pixel. monoalpha8fixed - A 2 channel format, one value for RGB and one value for Alpha. 8-bits per channel, 16-bits per pixel. monoalpha16fixed - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha16float - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha32float - A 2 channel format, one value for RGB and one value for Alpha. 32-bits per channel, 64-bits per pixel.\n\n\n\n -\n\n\nExtra Information for the Nvidia Background  can be accessed via an Info CHOP.\n\n\n\n - Horizontal resolution of the  in pixels. - Vertical resolution of the  in pixels. - Horizontal aspect of the . - Vertical aspect of the . - Depth of 2D or 3D array if this  contains a 2D or 3D texture array. - Total amount of texture memory used by this .\n - Number of times the operator has cooked since the process started. - Duration of the last cook in milliseconds. - Frame number when this operator was last cooked relative to the component timeline. - Frame number when this operator was last cooked relative to the absolute time. - Time in milliseconds at which the operator started cooking in the frame it was cooked. - Time in milliseconds at which the operator finished cooking in the frame it was cooked. - 1 if operator was cooked this frame. - Number of warnings in this operator if any. - Number of errors in this operator if any.\nTouchDesigner Build: Latest\\nwikieditorwikieditorwikieditorbefore wikieditor\nTOPs\n• • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • \n\nAn Operator Family that creates, composites and modifies images, and reads/writes images and movies to/from files and the network. TOPs run on the graphics card's GPU.\n\n\n\nThe Graphics Processing Unit. This is the high-speed, many-core processor of the graphics card/chip that takes geometry, images and data from the CPU and creates images and processed data.\n\n\n\nA Folder in TouchDesigner always refers to a Windows or macOS operating system directory/folder system that contain files and other folders. It does not refer to operators within TouchDesigner. See Network Path.\n\n\n\nThe width and height of an image in pixels. Most TOPs, like the Movie File In TOP can set the image resolution. See Aspect Ratio for the width/height ratio of an image, taking into account non-square pixels.\n\n\n\nThe viewer of a node can be (1) the interior of a node (the Node Viewer), (2) a floating window (RMB->View... on node), or (3) a Pane that graphically shows the results of an operator.\n\n\n\nA CHOP outputs one or more channels, where a channel is simply a sequence of numbers (Samples), representing motion, audio, etc. Channels are passed between CHOPs in TouchDesigner networks. Channels can be Exported to Parameters.\n\n\n\nAn Operator Family which operate on Channels (a sequence of numbers (Samples)) which are used for animation, audio, mathematics, simulation, logic, UI construction, and data streamed from/to devices and protocols.\n\n\n\n\n\n\n\n\nRetrieved from \"https://docs.derivative.ca/index.php?title=Nvidia_Background_TOP&oldid=30816\"",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Model Folder",
      "label": "Model Folder",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "modelfolder - The location of the AI model files used to perform the image segmentation. By default, these files are included inside the Config/Models folder inside your TouchDesigner installation folder. You can use this parameter to point to an alternative folder with compatible model files.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Mode",
      "label": "Mode",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "mode -  - Choose which mode to run the AI model in.\n\n quality - Run the high quality image segmentation model. This model will run slower, but may produce a better quality key image. performance - Run the high performance AI model. This model will run faster, but may produce a lower quality key image.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Quality",
      "label": "Quality",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "quality - Run the high quality image segmentation model. This model will run slower, but may produce a better quality key image. performance - Run the high performance AI model. This model will run faster, but may produce a lower quality key image.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Output Resolution",
      "label": "Output Resolution",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "outputresolution -  - quickly change the resolution of the 's data.\n\n useinput - Uses the input's resolution. eighth - Multiply the input's resolution by that amount. quarter - Multiply the input's resolution by that amount. half - Multiply the input's resolution by that amount. 2x - Multiply the input's resolution by that amount. 4x - Multiply the input's resolution by that amount. 8x - Multiply the input's resolution by that amount. fit - Fits the width and height to the resolution given below, while maintaining the aspect ratio. limit - The width and height are limited to the resolution given below. If one of the dimensions exceeds the given resolution, the width and height will be reduced to fit inside the given limits while maintaining the aspect ratio. custom - Enables the  parameter below, giving direct control over width and height.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Use Input",
      "label": "Use Input",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "useinput - Uses the input's resolution. eighth - Multiply the input's resolution by that amount. quarter - Multiply the input's resolution by that amount. half - Multiply the input's resolution by that amount. 2x - Multiply the input's resolution by that amount. 4x - Multiply the input's resolution by that amount. 8x - Multiply the input's resolution by that amount. fit - Fits the width and height to the resolution given below, while maintaining the aspect ratio. limit - The width and height are limited to the resolution given below. If one of the dimensions exceeds the given resolution, the width and height will be reduced to fit inside the given limits while maintaining the aspect ratio. custom - Enables the  parameter below, giving direct control over width and height.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Resolution",
      "label": "Resolution",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "resolution -  - Enabled only when the  parameter is set to Custom . Some Generators like Constant and Ramp do not use inputs and only use this field to determine their size. The drop down menu on the right provides some commonly used resolutions.\n\n resolutionw - resolutionh -",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "W",
      "label": "W",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "resolutionw - resolutionh -",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.383Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Resolution Menu",
      "label": "Resolution Menu",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "resmenu - A drop-down menu with some commonly used resolutions.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Use Global Res Multiplier",
      "label": "Use Global Res Multiplier",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "resmult - Uses the Global  Multiplier found in Edit>Preferences>TOPs. This multiplies all the TOPs resolutions by the set amount. This is handy when working on computers with different hardware specifications. If a project is designed on a desktop workstation with lots of graphics memory, a user on a laptop with only 64MB VRAM can set the Global  Multiplier to a value of half or quarter so it runs at an acceptable speed. By checking this checkbox on, this  is affected by the global multiplier.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Output Aspect",
      "label": "Output Aspect",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "outputaspect -  - Sets the image aspect ratio allowing any textures to be viewed in any size. Watch for unexpected results when compositing TOPs with different aspect ratios. (You can define images with non-square pixels using xres, yres, aspectx, aspecty where xres/yres != aspectx/aspecty.)\n\n useinput - Uses the input's aspect ratio. resolution - Uses the aspect of the image's defined resolution (ie 512x256 would be 2:1), whereby each pixel is square. custom - Lets you explicitly define a custom aspect ratio in the Aspect parameter below.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Use Input",
      "label": "Use Input",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "useinput - Uses the input's aspect ratio. resolution - Uses the aspect of the image's defined resolution (ie 512x256 would be 2:1), whereby each pixel is square. custom - Lets you explicitly define a custom aspect ratio in the Aspect parameter below.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Aspect",
      "label": "Aspect",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "aspect -  - Use when Output Aspect parameter is set to Custom Aspect.\n\n aspect1 - aspect2 -",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Aspect1",
      "label": "Aspect1",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "aspect1 - aspect2 -",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Aspect Menu",
      "label": "Aspect Menu",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "armenu - A drop-down menu with some commonly used aspect ratios.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Input Smoothness",
      "label": "Input Smoothness",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "inputfiltertype -  - This controls pixel filtering on the input image of the .\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. This is how you get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Nearest Pixel",
      "label": "Nearest Pixel",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. This is how you get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Fill Viewer",
      "label": "Fill Viewer",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "fillmode -  - Determine how the  image is displayed in the viewer.\nNOTE:To get an understanding of how TOPs work with images, you will want to set this to Native  as you lay down TOPs when starting out. This will let you see what is actually happening without any automatic viewer resizing.\n\n\n useinput - Uses the same Fill Viewer settings as it's input. fill - Stretches the image to fit the edges of the viewer. width - Stretches image to fit viewer horizontally. height - Stretches image to fit viewer vertically. best - Stretches or squashes image so no part of image is cropped. outside - Stretches or squashes image so image fills viewer while constraining it's proportions. This often leads to part of image getting cropped by viewer. nativeres - Displays the native resolution of the image in the viewer.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Use Input",
      "label": "Use Input",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "useinput - Uses the same Fill Viewer settings as it's input. fill - Stretches the image to fit the edges of the viewer. width - Stretches image to fit viewer horizontally. height - Stretches image to fit viewer vertically. best - Stretches or squashes image so no part of image is cropped. outside - Stretches or squashes image so image fills viewer while constraining it's proportions. This often leads to part of image getting cropped by viewer. nativeres - Displays the native resolution of the image in the viewer.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Viewer Smoothness",
      "label": "Viewer Smoothness",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "filtertype -  - This controls pixel filtering in the viewers.\n\n nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. Use this to get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Nearest Pixel",
      "label": "Nearest Pixel",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "nearest - Uses nearest pixel or accurate image representation. Images will look jaggy when viewing at any zoom level other than Native . linear - Uses linear filtering between pixels. Use this to get  images in viewers to look good at various zoom levels, especially useful when using any Fill Viewer setting other than Native . mipmap - Uses  mipmap filtering when scaling images. This can be used to reduce artifacts and sparkling in moving/scaling images that have lots of detail.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.384Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Passes",
      "label": "Passes",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "npasses - Duplicates the operation of the  the specified number of times. Making this larger than 1 is essentially the same as taking the output from each pass, and passing it into the first input of the node and repeating the process. Other inputs and parameters remain the same for each pass.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.385Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Channel Mask",
      "label": "Channel Mask",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "chanmask - Allows you to choose which channels (R, G, B, or A) the  will operate on. All channels are selected by default.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.385Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Pixel Format",
      "label": "Pixel Format",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "format -  - Format used to store data for each channel in the image (ie. R, G, B, and A). Refer to Pixel Formats for more information.\n\n useinput - Uses the input's pixel format. rgba8fixed - Uses 8-bit integer values for each channel. srgba8fixed - Uses 8-bit integer values for each channel and stores color in sRGB colorspace. rgba16float - Uses 16-bits per color channel, 64-bits per pixel. rgba32float - Uses 32-bits per color channel, 128-bits per pixels. rgb10a2fixed - Uses 10-bits per color channel and 2-bits for alpha, 32-bits total per pixel. rgba16fixed - Uses 16-bits per color channel, 64-bits total per pixel. rgba11float - A RGB floating point format that has 11 bits for the Red and Green channels, and 10-bits for the Blue , 32-bits total per pixel (therefore the same memory usage as 8-bit RGBA). The Alpha channel in this format will always be 1. Values can go above one, but can't be negative. ie. the range is [0, infinite). rgb16float - rgb32float - mono8fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 8-bits per pixel. mono16fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono16float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono32float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 32-bits per pixel. rg8fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 8-bits per channel, 16-bits total per pixel. rg16fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg16float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg32float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 32-bits per channel, 64-bits total per pixel. a8fixed - An Alpha only format that has 8-bits per channel, 8-bits per pixel. a16fixed - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a16float - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a32float - An Alpha only format that has 32-bits per channel, 32-bits per pixel. monoalpha8fixed - A 2 channel format, one value for RGB and one value for Alpha. 8-bits per channel, 16-bits per pixel. monoalpha16fixed - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha16float - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha32float - A 2 channel format, one value for RGB and one value for Alpha. 32-bits per channel, 64-bits per pixel.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.385Z",
      "rawData": {},
      "sourceElement": null
    },
    {
      "id": null,
      "name": "Use Input",
      "label": "Use Input",
      "group": "General",
      "page": "",
      "type": "float",
      "dataType": "number",
      "style": "",
      "defaultValue": null,
      "minValue": null,
      "maxValue": null,
      "step": null,
      "menuItems": [],
      "menuLabels": [],
      "allowCustom": false,
      "maxLength": null,
      "pattern": null,
      "isArray": false,
      "arraySize": 1,
      "dimensions": 1,
      "description": "useinput - Uses the input's pixel format. rgba8fixed - Uses 8-bit integer values for each channel. srgba8fixed - Uses 8-bit integer values for each channel and stores color in sRGB colorspace. rgba16float - Uses 16-bits per color channel, 64-bits per pixel. rgba32float - Uses 32-bits per color channel, 128-bits per pixels. rgb10a2fixed - Uses 10-bits per color channel and 2-bits for alpha, 32-bits total per pixel. rgba16fixed - Uses 16-bits per color channel, 64-bits total per pixel. rgba11float - A RGB floating point format that has 11 bits for the Red and Green channels, and 10-bits for the Blue , 32-bits total per pixel (therefore the same memory usage as 8-bit RGBA). The Alpha channel in this format will always be 1. Values can go above one, but can't be negative. ie. the range is [0, infinite). rgb16float - rgb32float - mono8fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 8-bits per pixel. mono16fixed - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono16float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 16-bits per pixel. mono32float - Single channel, where RGB will all have the same value, and Alpha will be 1.0. 32-bits per pixel. rg8fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 8-bits per channel, 16-bits total per pixel. rg16fixed - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg16float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 16-bits per channel, 32-bits total per pixel. rg32float - A 2 channel format, R and G have values, while B is 0 always and Alpha is 1.0. 32-bits per channel, 64-bits total per pixel. a8fixed - An Alpha only format that has 8-bits per channel, 8-bits per pixel. a16fixed - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a16float - An Alpha only format that has 16-bits per channel, 16-bits per pixel. a32float - An Alpha only format that has 32-bits per channel, 32-bits per pixel. monoalpha8fixed - A 2 channel format, one value for RGB and one value for Alpha. 8-bits per channel, 16-bits per pixel. monoalpha16fixed - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha16float - A 2 channel format, one value for RGB and one value for Alpha. 16-bits per channel, 32-bits per pixel. monoalpha32float - A 2 channel format, one value for RGB and one value for Alpha. 32-bits per channel, 64-bits per pixel.",
      "tooltip": "",
      "help": "",
      "units": "",
      "examples": [],
      "isReadOnly": false,
      "isAdvanced": false,
      "isHidden": false,
      "isAnimatable": true,
      "isExpression": false,
      "isPython": false,
      "dependsOn": [],
      "affects": [],
      "linkedTo": [],
      "expressionLanguage": "",
      "defaultExpression": "",
      "commonExpressions": [],
      "order": 0,
      "isVisible": true,
      "conditionalDisplay": null,
      "isValid": true,
      "validationErrors": [],
      "lastUpdated": "2025-08-08T00:37:48.385Z",
      "rawData": {},
      "sourceElement": null
    }
  ],
  "parameterGroups": {},
  "codeExamples": [],
  "pythonExamples": [],
  "expressions": [],
  "commonInputs": [],
  "commonOutputs": [],
  "relatedOperators": [],
  "workflowPatterns": [],
  "images": [],
  "videos": [],
  "assets": [],
  "keywords": [
    "nvidia",
    "background",
    "only",
    "supported",
    "under",
    "microsoft",
    "windows",
    "operating",
    "system.hardware:",
    "uses",
    "green",
    "screening"
  ],
  "tags": [
    "TOP",
    "TouchDesigner",
    "Nvidia Background"
  ],
  "searchWeight": 1,
  "contentHash": "",
  "processingDate": "2025-08-08T00:37:48.386Z",
  "processingVersion": "1.0.0",
  "isValid": true,
  "validationErrors": []
}