Back to Invokeai

List of Default Nodes

docs/nodes/defaultNodes.md

6.12.022.0 KB
Original Source

List of Default Nodes

The table below contains a list of the default nodes shipped with InvokeAI and their descriptions.

NodeFunction
Add IntegersAdds two numbers
Boolean Primitive CollectionA collection of boolean primitive values
Boolean PrimitiveA boolean primitive value
Canny ProcessorCanny edge detection for ControlNet
CenterPadCropPad or crop an image's sides from the center by specified pixels. Positive values are outside of the image.
CLIP SkipSkip layers in clip text_encoder model.
CollectCollects values into a collection
Color CorrectShifts the colors of a target image to match the reference image, optionally using a mask to only color-correct certain regions of the target image.
Color PrimitiveA color primitive value
Compel PromptParse prompt using compel package to conditioning.
Conditioning Primitive CollectionA collection of conditioning tensor primitive values
Conditioning PrimitiveA conditioning tensor primitive value
Content Shuffle ProcessorApplies content shuffle processing to image
ControlNetCollects ControlNet info to pass to other nodes
Create Denoise MaskConverts a greyscale or transparency image into a mask for denoising.
Create Gradient MaskCreates a mask for Gradient ("soft", "differential") inpainting that gradually expands during denoising. Improves edge coherence.
Denoise LatentsDenoises noisy latents to decodable images
Divide IntegersDivides two numbers
Dynamic PromptParses a prompt using adieyal/dynamicprompts' random or combinatorial generator
FaceMaskGenerates masks for faces in an image to use with Inpainting
FaceIdentifierIdentifies and labels faces in an image
FaceOffCreates a new image that is a scaled bounding box with a mask on the face for Inpainting
Float MathPerform basic math operations on two floats
Float Primitive CollectionA collection of float primitive values
Float PrimitiveA float primitive value
Float RangeCreates a range
HED (softedge) ProcessorApplies HED edge detection to image
Blur ImageBlurs an image
Extract Image ChannelGets a channel from an image.
Image Primitive CollectionA collection of image primitive values
Integer MathPerform basic math operations on two integers
Convert Image ModeConverts an image to a different mode.
Crop ImageCrops an image to a specified box. The box can be outside of the image.
Ideal SizeCalculates an ideal image size for latents for a first pass of a multi-pass upscaling to avoid duplication and other artifacts
Image Hue AdjustmentAdjusts the Hue of an image.
Inverse Lerp ImageInverse linear interpolation of all pixels of an image
Image PrimitiveAn image primitive value
Lerp ImageLinear interpolation of all pixels of an image
Offset Image ChannelAdd to or subtract from an image color channel by a uniform value.
Multiply Image ChannelMultiply or Invert an image color channel by a scalar value.
Multiply ImagesMultiplies two images together using PIL.ImageChops.multiply().
Blur NSFW ImageAdd blur to NSFW-flagged images
Paste ImagePastes an image into another image.
ImageProcessorBase class for invocations that preprocess images for ControlNet
Resize ImageResizes an image to specific dimensions
Round FloatRounds a float to a specified number of decimal places
Float to IntegerConverts a float to an integer. Optionally rounds to an even multiple of a input number.
Scale ImageScales an image by a factor
Image to LatentsEncodes an image into latents.
Add Invisible WatermarkAdd an invisible watermark to an image
Solid Color InfillInfills transparent areas of an image with a solid color
PatchMatch InfillInfills transparent areas of an image using the PatchMatch algorithm
Tile InfillInfills transparent areas of an image with tiles of the image
Integer Primitive CollectionA collection of integer primitive values
Integer PrimitiveAn integer primitive value
IterateIterates over a list of items
Latents Primitive CollectionA collection of latents tensor primitive values
Latents PrimitiveA latents tensor primitive value
Latents to ImageGenerates an image from latents.
Leres (Depth) ProcessorApplies leres processing to image
Lineart Anime ProcessorApplies line art anime processing to image
Lineart ProcessorApplies line art processing to image
LoRA LoaderApply selected lora to unet and text_encoder.
Main Model LoaderLoads a main model, outputting its submodels.
Combine MaskCombine two masks together by multiplying them using PIL.ImageChops.multiply().
Mask EdgeApplies an edge mask to an image
Mask from AlphaExtracts the alpha channel of an image as a mask.
Mediapipe Face ProcessorApplies mediapipe face processing to image
Midas (Depth) ProcessorApplies Midas depth processing to image
MLSD ProcessorApplies MLSD processing to image
Multiply IntegersMultiplies two numbers
NoiseGenerates latent noise.
Normal BAE ProcessorApplies NormalBae processing to image
ONNX Latents to ImageGenerates an image from latents.
ONNX Prompt (Raw)A node to process inputs and produce outputs. May use dependency injection in init to receive providers.
ONNX Text to LatentsGenerates latents from conditionings.
ONNX Model LoaderLoads a main model, outputting its submodels.
OpenCV InpaintSimple inpaint using opencv.
DW Openpose ProcessorApplies Openpose processing to image
PIDI ProcessorApplies PIDI processing to image
Prompts from FileLoads prompts from a text file
Random IntegerOutputs a single random integer.
Random RangeCreates a collection of random numbers
Integer RangeCreates a range of numbers from start to stop with step
Integer Range of SizeCreates a range from start to start + size with step
Resize LatentsResizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8.
SDXL Compel PromptParse prompt using compel package to conditioning.
SDXL LoRA LoaderApply selected lora to unet and text_encoder.
SDXL Main Model LoaderLoads an sdxl base model, outputting its submodels.
SDXL Refiner Compel PromptParse prompt using compel package to conditioning.
SDXL Refiner Model LoaderLoads an sdxl refiner model, outputting its submodels.
Scale LatentsScales latents by a given factor.
Segment Anything ProcessorApplies segment anything processing to image
Show ImageDisplays a provided image, and passes it forward in the pipeline.
String Primitive CollectionA collection of string primitive values
String PrimitiveA string primitive value
Subtract IntegersSubtracts two numbers
Tile Resample ProcessorTile resampler processor
Upscale (RealESRGAN)Upscales an image using RealESRGAN.
VAE LoaderLoads a VAE model, outputting a VaeLoaderOutput
Zoe (Depth) ProcessorApplies Zoe depth processing to image