Naphat John

feel only support one point now

Thanks for you reply, The bash command I used: `accelerate launch diff_train.py \ --pretrained_model_name_or_path stabilityai/stable-diffusion-2-1 \ --instance_data_dir train \ --resolution=256 --gradient_accumulation_steps=1 --center_crop --random_flip \ --learning_rate=5e-6 --lr_scheduler constant_with_warmup \ --lr_warmup_steps=5000 --max_train_steps=100000...

Thanks for your suggestion, while I set im_batch=1, num_inference_steps=5, nbatches set 4, still have this error