Update README.md

README.md

@@ -211,4 +211,39 @@ accelerate launch train_dreambooth_lora_sd3_miniature.py \
   --max_train_steps=500 \
   --checkpointing_steps=500 \
   --seed="3234290"
-```
+
+### With prior preservation and more flexible training script
+
+Training notebook with prior preservation, using more flexible framework: [SD3_DreamBooth-LoRA_Fine-Tune-with-prior-preservation.ipynb](https://huggingface.co/lamm-mit/stable-diffusion-3-medium-leaf-inspired/resolve/main/SD3_DreamBooth-LoRA_Fine-Tune-with-prior-preservation.ipynb)
+
+The notebook automatically downloads the training code. 
+
+```raw
+accelerate launch train_dreambooth_lora_sd3.py \
+      --pretrained_model_name_or_path="{pretrained_model_name_or_path}" \
+      --dataset_name="lamm-mit/{instance_output_dir}_data" \
+      --caption_column='caption' \
+      --image_column='image' \
+      --instance_prompt="{instance_prompt}" \
+      --with_prior_preservation \
+      --prior_loss_weight=1.0 \
+      --output_dir="{instance_output_dir}" \
+      --class_data_dir="{class_data_dir}" \
+      --class_prompt="{class_prompt}" \
+      --num_class_images={num_class_images} \
+      --mixed_precision="fp16" \
+      --resolution=1024 \
+      --train_batch_size=1 \
+      --gradient_accumulation_steps=4 \
+      --gradient_checkpointing \
+      --learning_rate=1e-4 \
+      --lr_scheduler="constant" \
+      --weighting_scheme="logit_normal" \
+      --lr_warmup_steps=0 \
+      --use_8bit_adam \
+      --max_train_steps=500 \
+      --checkpointing_steps=500 \
+      --seed="3234290"
+```
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/PQrUWTt7S0l5S62zgjeNo.png)