Koby Bibas

> @LaiaTarres thanks for your method, i changed this line to unet.conv_in.weight[:, 3:] = torch.zeros(unet.conv_in.weight[:, 3:].shape), > > but another error is happend, > >  > > how should...

When adding --gradient_checkpointing --use_8bit_adam the model training consumes 15GB although I'm not sure how it affects the results ``` accelerate launch finetune-unet.py --pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4" --instance_data_dir=demo/sample/train --output_dir=demo/custom-chkpts --resolution=512 --train_batch_size=1 --gradient_accumulation_steps=1 --learning_rate=1e-5 --num_train_epochs=500...