NNT Define Positional Encoding is a ComfyUI node in the NNT Neural Network Toolkit/Transformers category from ComfyUI Neural Network Toolkit NNT . Inputs…

Neural Network Toolkit (NNT) for ComfyUI is an extensive set of custom ComfyUI nodes for designing, training, and fine-tuning neural networks. This toolkit allows defining models, layers, training workflows, transformers, and tensor operations in a visual manner using nodes.

ComfyUI Neural Network Toolkit NNT 

d_model

max_seq_length

dropout

encoding_type

learnable

normalize

LAYER_STACK

NntDefinePositionalEncoding

LIST

NNT Define Positional Encoding

Name	Type	Default	Description
d_model	INT	51264–2048	—
max_seq_length	INT	51216–2048	—
dropout	FLOAT	0.10–0.9	—
encoding_type	COMBO	sinusoidal	4 options: sinusoidal, learned, rotary, alibi
learnable	COMBO	False	2 options: True, False
normalize	COMBO	True	2 options: True, False
LAYER_STACKopt	LIST		—

NNT Define Positional Encoding

Inputs (7)

Outputs (1)