git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .

cd examples/instruct_pix2pix

pip install -r requirements.txt

accelerate config

accelerate config default

from accelerate.utils import write_basic_config

write_basic_config()

export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
export DATASET_ID="fusing/instructpix2pix-1000-samples"

accelerate launch --mixed_precision="fp16" train_instruct_pix2pix.py \
    --pretrained_model_name_or_path=$MODEL_NAME \
    --dataset_name=$DATASET_ID \
    --enable_xformers_memory_efficient_attention \
    --resolution=256 --random_flip \
    --train_batch_size=4 --gradient_accumulation_steps=4 --gradient_checkpointing \
    --max_train_steps=15000 \
    --checkpointing_steps=5000 --checkpoints_total_limit=1 \
    --learning_rate=5e-05 --max_grad_norm=1 --lr_warmup_steps=0 \
    --conditioning_dropout_prob=0.05 \
    --mixed_precision=fp16 \
    --seed=42 \
    --push_to_hub

accelerate launch --mixed_precision="fp16" train_instruct_pix2pix.py \
    --pretrained_model_name_or_path=$MODEL_NAME \
    --dataset_name=$DATASET_ID \
    --enable_xformers_memory_efficient_attention \
    --resolution=256 --random_flip \
    --train_batch_size=4 --gradient_accumulation_steps=4 --gradient_checkpointing \
    --max_train_steps=15000 \
    --checkpointing_steps=5000 --checkpoints_total_limit=1 \
    --learning_rate=5e-05 --max_grad_norm=1 --lr_warmup_steps=0 \
    --conditioning_dropout_prob=0.05 \
    --mixed_precision=fp16 \
    --val_image_url="https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png" \
    --validation_prompt="make the mountains snowy" \
    --seed=42 \
    --report_to=wandb \
    --push_to_hub

accelerate launch --mixed_precision="fp16" --multi_gpu train_instruct_pix2pix.py \
 --pretrained_model_name_or_path=stable-diffusion-v1-5/stable-diffusion-v1-5 \
 --dataset_name=sayakpaul/instructpix2pix-1000-samples \
 --use_ema \
 --enable_xformers_memory_efficient_attention \
 --resolution=512 --random_flip \
 --train_batch_size=4 --gradient_accumulation_steps=4 --gradient_checkpointing \
 --max_train_steps=15000 \
 --checkpointing_steps=5000 --checkpoints_total_limit=1 \
 --learning_rate=5e-05 --lr_warmup_steps=0 \
 --conditioning_dropout_prob=0.05 \
 --mixed_precision=fp16 \
 --seed=42 \
 --push_to_hub

import PIL
import requests
import torch
from diffusers import StableDiffusionInstructPix2PixPipeline

model_id = "your_model_id"  # <- 이를 수정하세요.
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
generator = torch.Generator("cuda").manual_seed(0)

url = "https://huggingface.co/datasets/sayakpaul/sample-datasets/resolve/main/test_pix2pix_4.png"


def download_image(url):
   image = PIL.Image.open(requests.get(url, stream=True).raw)
   image = PIL.ImageOps.exif_transpose(image)
   image = image.convert("RGB")
   return image


image = download_image(url)
prompt = "wipe out the lake"
num_inference_steps = 20
image_guidance_scale = 1.5
guidance_scale = 10

edited_image = pipe(
   prompt,
   image=image,
   num_inference_steps=num_inference_steps,
   image_guidance_scale=image_guidance_scale,
   guidance_scale=guidance_scale,
   generator=generator,
).images[0]
edited_image.save("edited_image.png")