M1dataset/sacristy

---
pretty_name: sacristy
---
INSTALL REQUIREMENTS

!wget -q https://github.com/ShivamShrirao/diffusers/raw/main/examples/dreambooth/train_dreambooth.py
!wget -q https://github.com/ShivamShrirao/diffusers/raw/main/scripts/convert_diffusers_to_original_stable_diffusion.py
%pip install -qq git+https://github.com/ShivamShrirao/diffusers
%pip install -q -U --pre triton
%pip install -q accelerate transformers ftfy bitsandbytes==0.35.0 gradio natsort safetensors

WEIGHTS

save_to_gdrive = False
if save_to_gdrive:
from google.colab import drive
drive.mount('/content/drive')

MODEL_NAME = "runwayml/stable-diffusion-v1-5"

OUTPUT_DIR = "stable_diffusion_weights/zwx"
if save_to_gdrive:
OUTPUT_DIR = "/content/drive/MyDrive/" + OUTPUT_DIR
else:
OUTPUT_DIR = "/content/" + OUTPUT_DIR

print(f"[*] Weights will be saved at {OUTPUT_DIR}")

!mkdir -p $OUTPUT_DIR

CONCEPT LIST
concepts_list = [
{
"instance_prompt": "photo of sacristy",
"class_prompt": "photo of a room",
"instance_data_dir": "/content/data/sacristy",
"class_data_dir": "/content/data/room"
},
{
"instance_prompt": "photo of screens furniture",
"class_prompt": "photo of a furniture",
"instance_data_dir": "/content/data/screens",
"class_data_dir": "/content/data/furniture"
}
]

import json
import os
for c in concepts_list:
os.makedirs(c["instance_data_dir"], exist_ok=True)

with open("concepts_list.json", "w") as f:
json.dump(concepts_list, f, indent=4)
UPLOADS

import os
from google.colab import files
import shutil

for c in concepts_list:
print(f"Uploading instance images for `{c['instance_prompt']}`")
uploaded = files.upload()
for filename in uploaded.keys():
dst_path = os.path.join(c['instance_data_dir'], filename)
shutil.move(filename, dst_path)

TRAINING

!accelerate launch train_dreambooth.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--pretrained_vae_name_or_path="stabilityai/sd-vae-ft-mse" \
--output_dir=$OUTPUT_DIR \
--revision="fp16" \
--with_prior_preservation --prior_loss_weight=1.0 \
--seed=1337 \
--resolution=512 \
--train_batch_size=1 \
--train_text_encoder \
--mixed_precision="fp16" \
--use_8bit_adam \
--gradient_accumulation_steps=1 \
--learning_rate=1e-6 \
--lr_scheduler="constant" \
--lr_warmup_steps=0 \
--num_class_images=50 \
--sample_batch_size=4 \
--max_train_steps=800 \
--save_interval=10000 \
--concepts_list="concepts_list.json"

原始信息汇总

数据集概述

数据集名称

• pretty_name: sacristy

数据集结构

• 概念列表: 包含两个概念，每个概念包含以下字段：
  • instance_prompt: 实例提示，如"photo of sacristy"和"photo of screens furniture"
  • class_prompt: 类别提示，如"photo of a room"和"photo of a furniture"
  • instance_data_dir: 实例数据目录，如"/content/data/sacristy"和"/content/data/screens"
  • class_data_dir: 类别数据目录，如"/content/data/room"和"/content/data/furniture"

数据集操作

• 数据目录创建: 使用os.makedirs确保每个实例数据目录存在。
• 数据上传: 通过Google Colab的files.upload功能上传实例图像，并移动到相应的实例数据目录。

训练配置

• 模型和VAE路径: 使用"runwayml/stable-diffusion-v1-5"作为模型，"stabilityai/sd-vae-ft-mse"作为VAE。
• 输出目录: 根据是否保存到Google Drive设置不同的输出目录。
• 训练参数: 包括但不限于：
  • 分辨率: 512
  • 训练批次大小: 1
  • 学习率: 1e-6
  • 最大训练步骤: 800
  • 保存间隔: 10000
  • 概念列表文件: "concepts_list.json"