Trained for 8025 steps at batch size 16 on the phrase ' headshot of person ' where person is a wildcard. The phrase was run through the SDXL to SD1.5 pipeline outlined here https://civitai.com/articles/1430/applying-sd-15-models-and-loras-to-sdxl-1024x1024-comfyui
# Full command CUDA_VISIBLE_DEVICES=0 accelerate launch --num_cpu_threads_per_process=2 "sdxl_train_network.py" --enable_bucket --pretrained_model_name_or_path="/ml2/trained/ComfyUI/models/checkpoints/stable-diffusion-xl-base-1.0/sd_xl_base_1.0.safetensors" --train_data_dir="/ml2/trained/sd-scripts/data/headshot" --resolution="1024,1024" --output_dir="/ml2/trained/ComfyUI/models/loras/Lora/sdxl" --logging_dir="./logs" --save_model_as=safetensors --output_name="headshot2" --network_alpha="1" --network_dim=32 --network_module=networks.lora --text_encoder_lr=0.0004 --unet_lr=0.0004 --lr_scheduler="constant" --train_batch_size="16" --max_train_steps="10000" --mixed_precision="bf16" --save_every_n_epochs="1" --save_precision="bf16" --caption_extension=".txt" --optimizer_type="Adafactor" --optimizer_args scale_parameter=False relative_step=False warmup_init=False --max_data_loader_n_workers="0" --bucket_reso_steps=64 --gradient_checkpointing --xformers --bucket_no_upscale
Reducing the network_dim reduced the filesize
Trained for 8025 steps at batch size 16 on the phrase ' headshot of person ' where person is a wildcard. The phrase was run through the SDXL to SD1.5 pipeline outlined here https://civitai.com/articles/1430/applying-sd-15-models-and-loras-to-sdxl-1024x1024-comfyui
Reducing the network_dim reduced the filesize