ComfyUI Node: Init SDXL LoRA Training

Authored by kijai

Created

Updated

1157 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

FluxTrainer/SDXL

Inputs

SDXL_models TRAIN_SDXL_MODELS
dataset JSON
optimizer_settings ARGS
output_name STRING
output_dir STRING
network_dim INT
network_alpha FLOAT
learning_rate FLOAT
max_train_steps INT
cache_latents
  • disk
  • memory
  • disabled
cache_text_encoder_outputs
  • disk
  • memory
  • disabled
highvram BOOLEAN
blocks_to_swap INT
fp8_base BOOLEAN
gradient_dtype
  • fp32
  • fp16
  • bf16
save_dtype
  • fp32
  • fp16
  • bf16
  • fp8_e4m3fn
  • fp8_e5m2
attention_mode
  • sdpa
  • xformers
  • disabled
train_text_encoder
  • disabled
  • clip_l
clip_l_lr FLOAT
clip_g_lr FLOAT
sample_prompts_pos STRING
sample_prompts_neg STRING
gradient_checkpointing
  • enabled
  • disabled
additional_args STRING
resume_args ARGS
block_args ARGS
loss_args ARGS
network_config NETWORK_CONFIG

Outputs

NETWORKTRAINER

INT

KOHYA_ARGS

Extension: ComfyUI Flux Trainer

Currently supports LoRA training, and untested full finetune with code from kohya's scripts: a/https://github.com/kohya-ss/sd-scripts

Authored by kijai

View Nodes

Looking for a different node?

More nodes in ComfyUI Flux Trainer

Other FluxTrainer/SDXL nodes

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more