Open dizhenx opened 1 year ago
When I put in 10 face pictures and trained them for 1200 steps with dreambooth, most of the faces generated by reasoning are deformed. Why? Why can't I generate a face picture that is the same as the original picture?
conda activate diffusers cd /mnt/data/creative/diffusers/examples/dreambooth export MODEL_NAME="/mnt/data/creative/diffusers/examples/dreambooth/hub/models--runwayml--stable-diffusion-v1-5/snapshots/c9ab35ff5f2c362e9e22fbafe278077e196057f0" export INSTANCE_DIR="/mnt/data/creative/diffusers/instance-images/liudehua" export CLASS_DIR="/mnt/data/creative/diffusers/class-images/liudehua" export OUTPUT_DIR="/mnt/data/creative/diffusers/class-images/model/liudehua"
accelerate launch --config_file /mnt/data/huggingface/accelerate/default_config1.yaml --mixed_precision="fp16" train_dreambooth.py \ --pretrained_model_name_or_path=$MODEL_NAME \ --instance_data_dir=$INSTANCE_DIR \ --class_data_dir=$CLASS_DIR \ --output_dir=$OUTPUT_DIR \ --with_prior_preservation --prior_loss_weight=1.0 \ --instance_prompt="a photo of ldh man" \ --class_prompt="a photo of man" \ --resolution=512 \ --train_batch_size=1 \ --sample_batch_size=1 \ --gradient_accumulation_steps=1 --gradient_checkpointing \ --learning_rate=1e-6 \ --lr_scheduler="constant" \ --lr_warmup_steps=0 \ --num_class_images=200 \ --max_train_steps=1200
No response
diffusers
Describe the bug
When I put in 10 face pictures and trained them for 1200 steps with dreambooth, most of the faces generated by reasoning are deformed. Why? Why can't I generate a face picture that is the same as the original picture?![微信截图_20230713161823](https://github.com/ShivamShrirao/diffusers/assets/104120998/27cfb9c3-3034-4ad3-8c8c-99aaa2101688)
Reproduction
conda activate diffusers cd /mnt/data/creative/diffusers/examples/dreambooth export MODEL_NAME="/mnt/data/creative/diffusers/examples/dreambooth/hub/models--runwayml--stable-diffusion-v1-5/snapshots/c9ab35ff5f2c362e9e22fbafe278077e196057f0" export INSTANCE_DIR="/mnt/data/creative/diffusers/instance-images/liudehua" export CLASS_DIR="/mnt/data/creative/diffusers/class-images/liudehua" export OUTPUT_DIR="/mnt/data/creative/diffusers/class-images/model/liudehua"
accelerate launch --config_file /mnt/data/huggingface/accelerate/default_config1.yaml --mixed_precision="fp16" train_dreambooth.py \ --pretrained_model_name_or_path=$MODEL_NAME \ --instance_data_dir=$INSTANCE_DIR \ --class_data_dir=$CLASS_DIR \ --output_dir=$OUTPUT_DIR \ --with_prior_preservation --prior_loss_weight=1.0 \ --instance_prompt="a photo of ldh man" \ --class_prompt="a photo of man" \ --resolution=512 \ --train_batch_size=1 \ --sample_batch_size=1 \ --gradient_accumulation_steps=1 --gradient_checkpointing \ --learning_rate=1e-6 \ --lr_scheduler="constant" \ --lr_warmup_steps=0 \ --num_class_images=200 \ --max_train_steps=1200
Logs
No response
System Info
diffusers
version: 0.15.0.dev0