NNT Define RNN Layer is a ComfyUI node in the NNT Neural Network Toolkit/Layers category from ComfyUI Neural Network Toolkit NNT . Inputs: input_size…

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 

input_size

hidden_size

num_layers

nonlinearity

bias

batch_first

dropout

bidirectional

LAYER_STACK

NntDefineRNNLayer

NNT Define RNN Layer

Name	Type	Default	Description
input_size	INT	101–2048	—
hidden_size	INT	201–2048	—
num_layers	INT	11–10	—
nonlinearity	COMBO	tanh	2 options: tanh, relu
bias	COMBO	True	2 options: True, False
batch_first	COMBO	True	2 options: True, False
dropout	FLOAT	0.00–1	—
bidirectional	COMBO	False	2 options: True, False
LAYER_STACKopt	LIST		—

NNT Define RNN Layer

Inputs (9)

Outputs (1)