AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity

Update readme and default hyperparameters.

Browse Source
This commit is contained in:
Zhenhuan Liu
2022-09-22 10:19:45 -07:00
parent 51340f9921
commit 88ab347d3c
1 changed files with 29 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
examples/dreambooth/README.md
View File

@@ -38,26 +38,48 @@ Now let's get our dataset. Download images from [here](https://drive.google.com/
And launch the training using
```bash
export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export INSTANCE_DIR="path-to-instance-images"
export OUTPUT_DIR="path-to-save-model"
python train_dreambooth.py \
--pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
--instance_data_dir=$INSTANCE_DIR \
--output_dir=$OUTPUT_DIR \
--instance_prompt="a photo of sks dog" \
--resolution=512 \
--train_batch_size=1 \
--gradient_accumulation_steps=1 \
--learning_rate=5e-6 \
--lr_scheduler="constant" \
--lr_warmup_steps=0 \
--max_train_steps=400
```
Training with prior-preservation loss using
```bash
export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export INSTANCE_DIR="path-to-instance-images"
export CLASS_DIR="path-to-class-images"
export OUTPUT_DIR="path-to-save-model"
python train_dreambooth.py \
--pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
--instance_data_dir=$INSTANCE_DIR \
--class_data_dir=$CLASS_DIR \
--output_dir=$OUTPUT_DIR \
--with_prior_preservation \
--instance_prompt="a photo of sks dog" \
--class_prompt="a photo of dog" \
--resolution=512 \
--train_batch_size=4 \
--train_batch_size=1 \
--gradient_accumulation_steps=1 \
--learning_rate=1e-5 \
--learning_rate=5e-6 \
--lr_scheduler="constant" \
--lr_warmup_steps=0 \
--output_dir="dreambooth_dog" \
--instance_prompt="a photo of sks dog" \
--class_prompt="a photo of dog"
--num_class_images=1000 \
--max_train_steps=3000
--num_class_images=200 \
--max_train_steps=1000
```