ComfyUI Node: Train LoRA

Authored by ali-vilab

Created

Updated

1316 stars

Category

training

Inputs

model MODEL
latents LATENT
positive CONDITIONING
batch_size INT
grad_accumulation_steps INT
steps INT
learning_rate FLOAT
rank INT
optimizer
  • AdamW
  • Adam
  • SGD
  • RMSprop
loss_function
  • MSE
  • L1
  • Huber
  • SmoothL1
seed INT
training_dtype
  • bf16
  • fp32
lora_dtype
  • bf16
  • fp32
algorithm
  • LoRA
  • LoHa
  • LoKr
  • OFT
gradient_checkpointing BOOLEAN
existing_lora
  • [None]

Outputs

MODEL

LORA_MODEL

LOSS_MAP

INT

Extension: ComfyUI-ACE_Plus

Custom nodes for various visual generation and editing tasks using ACE_Plus FFT Model.

Authored by ali-vilab

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