train_text_to_image.py
script from huggingface diffusers
Before running the scripts, make sure to install the library's training dependencies:
Important
To make sure you can successfully run the latest versions of the example scripts, we highly recommend installing from source and keeping the install up to date as we update the example scripts frequently and install some example-specific requirements. To do this, execute the following steps in a new virtual environment:
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
Then cd in the example folder and run
pip install -r requirements.txt
And initialize an 🤗Accelerate environment with:
accelerate config
Low-Rank Adaption of Large Language Models was first introduced by Microsoft in LoRA: Low-Rank Adaptation of Large Language Models by Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen.
In a nutshell, LoRA allows adapting pretrained models by adding pairs of rank-decomposition matrices to existing weights and only training those newly added weights. This has a couple of advantages:
- Previous pretrained weights are kept frozen so that model is not prone to catastrophic forgetting.
- Rank-decomposition matrices have significantly fewer parameters than original model, which means that trained LoRA weights are easily portable.
- LoRA attention layers allow to control to which extent the model is adapted toward new training images via a
scale
parameter.
cloneofsimo was the first to try out LoRA training for Stable Diffusion in the popular lora GitHub repository.
With LoRA, it's possible to fine-tune Stable Diffusion on a custom image-caption pair dataset on consumer GPUs like Tesla T4, Tesla V100.
First, you need to set up your development environment as is explained in the installation section. Make sure to set the MODEL_NAME
and DATASET_NAME
environment variables. Here, we will use Stable Diffusion v1-5 and the Pokemons dataset.
Note: Change the resolution
to 768 if you are using the stable-diffusion-2 768x768 model.
Note: It is quite useful to monitor the training progress by regularly generating sample images during training. Weights and Biases is a nice solution to easily see generating images during training. All you need to do is to run pip install wandb
before training to automatically log images.
export MODEL_NAME="CompVis/stable-diffusion-v1-5"
export DATASET_NAME="lambdalabs/pokemon-blip-captions"
For this example we want to directly store the trained LoRA embeddings on the Hub, so
we need to be logged in and add the --push_to_hub
flag.
huggingface-cli login
Now we can start training!
accelerate launch --mixed_precision="bf16" --num_processes=1 --num_machines=1 --dynamo_backend=no train_text_to_image_lora.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--dataset_name=$DATASET_NAME \
--dataloader_num_workers=4 \
--resolution=512 \
--rank=4 \
--center_crop \
--random_flip \
--train_batch_size=8 \
--gradient_accumulation_steps=4 \
--max_train_steps=5000 \
--learning_rate=1e-04 \
--max_grad_norm=1 \
--lr_scheduler="cosine" \
--lr_warmup_steps=0 \
--output_dir=${OUTPUT_DIR} \
--checkpoints_total_limit=5 \
--validation_prompt="A pokemon with blue eyes." \
--num_validation_images=4 \
--validation_epochs=30 \
--seed=1337 \
--enable_xformers_memory_efficient_attention \
--report_to="wandb" \
The above command will also run inference as fine-tuning progresses and log the results to Weights and Biases.
Note: When using LoRA we can use a much higher learning rate compared to non-LoRA fine-tuning. Here we use 1e-4 instead of the usual 1e-5. Also, by using LoRA, it's possible to run train_text_to_image_lora.py
in consumer GPUs like T4 or V100.
Please refer to inference.py
You can enable memory efficient attention by installing xFormers and passing the --enable_xformers_memory_efficient_attention
argument to the script.
xFormers training is not available for Flax/JAX.
Note:
According to this issue, xFormers v0.0.16
cannot be used for training in some GPUs. If you observe that problem, please install a development version as indicated in that comment.