Train a Stable Diffusion LoRA on Cloud GPU

runcrate instances create --name lora-train --gpu RTX4090 --template ubuntu-train
runcrate instances status lora-train

runcrate cp ./training_images/ lora-train:/workspace/training_images/

runcrate ssh lora-train -- "pip install diffusers transformers accelerate peft safetensors pillow"

runcrate ssh lora-train -- "accelerate launch diffusers/examples/dreambooth/train_dreambooth_lora_sdxl.py \
  --pretrained_model_name_or_path='stabilityai/stable-diffusion-xl-base-1.0' \
  --instance_data_dir='/workspace/training_images' \
  --instance_prompt='a photo of sks person' \
  --output_dir='/workspace/lora-output' \
  --resolution=1024 \
  --train_batch_size=1 \
  --gradient_accumulation_steps=4 \
  --learning_rate=1e-4 \
  --max_train_steps=1500 \
  --mixed_precision='fp16' \
  --seed=42"

runcrate ssh lora-train -- nvidia-smi
runcrate ssh lora-train -- "ls -la /workspace/lora-output/"

runcrate ssh lora-train -- "python -c \"
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
    'stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipe.load_lora_weights('/workspace/lora-output')
image = pipe('a photo of sks person in a garden', num_inference_steps=30).images[0]
image.save('/workspace/test_output.png')
print('Generated test image.')
\""

runcrate cp lora-train:/workspace/lora-output/ ./my-sdxl-lora/
runcrate cp lora-train:/workspace/test_output.png ./test_output.png

runcrate instances delete lora-train