ComfyUI Node: NNT Edit Model Layers
Category
NNT Neural Network Toolkit/Models
Inputs
MODEL MODEL
operation
- Freeze
- Unfreeze
- Set weights and biases
- Prune
- Quantize
parameter_type
- weights
- biases
- both
layer_selection
- All layers
- First N layers
- Last N layers
- Selected types
layer_types
- Linear
- Conv2d
- BatchNorm2d
- All
num_layers INT
initialization
- random
- zeros
- ones
- xavier_uniform
- xavier_normal
- kaiming_uniform
- kaiming_normal
- orthogonal
- custom_value
custom_value FLOAT
pruning_amount FLOAT
quantization_bits INT
Outputs
MODEL
STRING
DICT
Extension: ComfyUI Neural Network Toolkit NNT
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.
Authored by inventorado
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more