Hi,
I am trying to train dreambooth sdxl but keep running out of memory when trying it for 1024px resolution. I am using the following command with the latest repo on github. Any way to run it in less memory.
accelerate launch train_dreambooth_lora_sdxl.py
–pretrained_model_name_or_path=$MODEL_NAME
–instance_data_dir=$INSTANCE_DIR
–output_dir=$OUTPUT_DIR
–mixed_precision=“fp16”
–instance_prompt=“a photo of sks dog”
–resolution=1024
–train_batch_size=1
–gradient_accumulation_steps=8
–learning_rate=1e-4
–gradient_checkpointing
–lr_scheduler=“constant”
–lr_warmup_steps=0
–max_train_steps=500
–validation_prompt=“A photo of sks dog in a bucket”
–validation_epochs=25
–seed=“0”
–enable_xformers_memory_efficient_attention