pip install git+https://github.com/huggingface/diffusers
pip install -U -r diffusers/examples/dreambooth/requirements.txt

accelerate config

accelerate config default

from accelerate.utils import write_basic_config

write_basic_config()

  --checkpointing_steps=500

  --resume_from_checkpoint="checkpoint-1500"

from diffusers import DiffusionPipeline, UNet2DConditionModel
from transformers import CLIPTextModel
import torch

# 학습에 사용된 것과 동일한 인수(model, revision)로 파이프라인을 불러옵니다.
model_id = "CompVis/stable-diffusion-v1-4"

unet = UNet2DConditionModel.from_pretrained("/sddata/dreambooth/daruma-v2-1/checkpoint-100/unet")

# `args.train_text_encoder`로 학습한 경우면 텍스트 인코더를 꼭 불러오세요
text_encoder = CLIPTextModel.from_pretrained("/sddata/dreambooth/daruma-v2-1/checkpoint-100/text_encoder")

pipeline = DiffusionPipeline.from_pretrained(model_id, unet=unet, text_encoder=text_encoder, dtype=torch.float16)
pipeline.to("cuda")

# 추론을 수행하거나 저장하거나, 허브에 푸시합니다.
pipeline.save_pretrained("dreambooth-pipeline")

from accelerate import Accelerator
from diffusers import DiffusionPipeline

# 학습에 사용된 것과 동일한 인수(model, revision)로 파이프라인을 불러옵니다.
model_id = "CompVis/stable-diffusion-v1-4"
pipeline = DiffusionPipeline.from_pretrained(model_id)

accelerator = Accelerator()

# 초기 학습에 `--train_text_encoder`가 사용된 경우 text_encoder를 사용합니다.
unet, text_encoder = accelerator.prepare(pipeline.unet, pipeline.text_encoder)

# 체크포인트 경로로부터 상태를 복원합니다. 여기서는 절대 경로를 사용해야 합니다.
accelerator.load_state("/sddata/dreambooth/daruma-v2-1/checkpoint-100")

# unwrapped 모델로 파이프라인을 다시 빌드합니다.(.unet and .text_encoder로의 할당도 작동해야 합니다)
pipeline = DiffusionPipeline.from_pretrained(
    model_id,
    unet=accelerator.unwrap_model(unet),
    text_encoder=accelerator.unwrap_model(text_encoder),
)

# 추론을 수행하거나 저장하거나, 허브에 푸시합니다.
pipeline.save_pretrained("dreambooth-pipeline")

  --enable_xformers_memory_efficient_attention

  --set_grads_to_none

pip install bitsandbytes

export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export INSTANCE_DIR="path_to_training_images"
export CLASS_DIR="path_to_class_images"
export OUTPUT_DIR="path_to_saved_model"

accelerate launch 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 sks dog" \
  --class_prompt="a photo of dog" \
  --resolution=512 \
  --train_batch_size=1 \
  --gradient_accumulation_steps=2 --gradient_checkpointing \
  --use_8bit_adam \
  --learning_rate=5e-6 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --num_class_images=200 \
  --max_train_steps=800

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"

accelerate launch 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 sks dog" \
  --class_prompt="a photo of dog" \
  --resolution=512 \
  --train_batch_size=1 \
  --gradient_accumulation_steps=1 --gradient_checkpointing \
  --use_8bit_adam \
  --enable_xformers_memory_efficient_attention \
  --set_grads_to_none \
  --learning_rate=2e-6 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --num_class_images=200 \
  --max_train_steps=800

accelerate config

export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export INSTANCE_DIR="path_to_training_images"
export CLASS_DIR="path_to_class_images"
export OUTPUT_DIR="path_to_saved_model"

accelerate launch 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 sks dog" \
  --class_prompt="a photo of dog" \
  --resolution=512 \
  --train_batch_size=1 \
  --sample_batch_size=1 \
  --gradient_accumulation_steps=1 --gradient_checkpointing \
  --learning_rate=5e-6 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --num_class_images=200 \
  --max_train_steps=800 \
  --mixed_precision=fp16

from diffusers import StableDiffusionPipeline
import torch

model_id = "path_to_saved_model"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")

prompt = "A photo of sks dog in a bucket"
image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]

image.save("dog-bucket.png")