学习链接：Datawhale
什么是LoRA？
Stable diffusion 提供了中的Lora(LoRA)模型是一种轻量级的微调方法，即“Low-Rank Adaptation”（低秩适应）。LoRA也不是指单一的具体模型，而是指一类通过特定微调技术应用于基础模型的扩展应用。
在Stable Diffusion模型的应用中，LoRA被用作一种插件，允许用户在不修改SD模型的情况下，利用少量数据训练出具有特定画风、IP或人物特征的模型。这种技术在社区使用和个人开发者中非常受欢迎。例如，可以通过LoRA模型改变SD模型的生成风格，或者为SD模型添加新的人物。
Baseline跑通流程
1. 安装 Data-Juicer 和 DiffSynth-Studio
!pip install simple-aesthetics-predictor
!pip install -v -e data-juicer
!pip uninstall pytorch-lightning -y
!pip install peft lightning pandas torchvision
!pip install -e DiffSynth-StudioData-Juicer的核心是其包含超过80个高度系统化且可复用的算子（operators），这些算子构成了强大的数据处理工具箱，允许用户灵活地对数据进行清洗、生成、分析与转换。值得注意的是，它支持通过配置文件实现流程自动化，减少了手动编码的需求，大大提升了效率。此外，采用高效的并行处理框架，如Aliyun-PAI、Ray、Slurm和CUDA，Data-Juicer优化了资源利用，加快了数据处理速度，降低了计算成本。
DiffSynth-Studio 是一个创新的扩散引擎，专门设计用于实现图片和视频的风格转换。它通过先进的机器学习技术，为用户提供了一种全新的创作方式，使得风格转换变得更加高效和直观。该工具的目标用户群体广泛，包括但不限于艺术家、设计师、视频编辑者和AI爱好者。无论是专业人士还是业余爱好者，都能在DiffSynth-Studio中找到实现创意的工具和方法。
2.下载数据集
from modelscope.msdatasets import MsDataset
ds = MsDataset.load(
'AI-ModelScope/lowres_anime',
subset_name='default',
split='train',
cache_dir="/mnt/workspace/kolors/data"
)import json, os
from data_juicer.utils.mm_utils import SpecialTokens
from tqdm import tqdm
os.makedirs("./data/lora_dataset/train", exist_ok=True)
os.makedirs("./data/data-juicer/input", exist_ok=True)
with open("./data/data-juicer/input/metadata.jsonl", "w") as f:
for data_id, data in enumerate(tqdm(ds)):
image = data["image"].convert("RGB")
image.save(f"/mnt/workspace/kolors/data/lora_dataset/train/{data_id}.jpg")
metadata = {"text": "二次元", "image": [f"/mnt/workspace/kolors/data/lora_dataset/train/{data_id}.jpg"]}
f.write(json.dumps(metadata))
f.write("\n")3.数据处理（这一步简单概括）
data_juicer_config = """
# global parameters
project_name: 'data-process'
dataset_path: './data/data-juicer/input/metadata.jsonl' # path to your dataset directory or file
np: 4 # number of subprocess to process your dataset
text_keys: 'text'
image_key: 'image'
image_special_token: '<__dj__image>'
export_path: './data/data-juicer/output/result.jsonl'
# process schedule
# a list of several process operators with their arguments
process:
- image_shape_filter:
min_width: 1024
min_height: 1024
any_or_all: any
- image_aspect_ratio_filter:
min_ratio: 0.5
max_ratio: 2.0
any_or_all: any
"""
with open("data/data-juicer/data_juicer_config.yaml", "w") as file:
file.write(data_juicer_config.strip())
!dj-process --config data/data-juicer/data_juicer_config.yaml保存处理好的数据
import pandas as pd
import os, json
from PIL import Image
from tqdm import tqdm
texts, file_names = [], []
os.makedirs("./data/lora_dataset_processed/train", exist_ok=True)
with open("./data/data-juicer/output/result.jsonl", "r") as file:
for data_id, data in enumerate(tqdm(file.readlines())):
data = json.loads(data)
text = data["text"]
texts.append(text)
image = Image.open(data["image"][0])
image_path = f"./data/lora_dataset_processed/train/{data_id}.jpg"
image.save(image_path)
file_names.append(f"{data_id}.jpg")
data_frame = pd.DataFrame()
data_frame["file_name"] = file_names
data_frame["text"] = texts
data_frame.to_csv("./data/lora_dataset_processed/train/metadata.csv", index=False, encoding="utf-8-sig")
data_frame第四步：训练模型
下载模型
import os
cmd = """
python DiffSynth-Studio/examples/train/kolors/train_kolors_lora.py \
--pretrained_unet_path models/kolors/Kolors/unet/diffusion_pytorch_model.safetensors \
--pretrained_text_encoder_path models/kolors/Kolors/text_encoder \
--pretrained_fp16_vae_path models/sdxl-vae-fp16-fix/diffusion_pytorch_model.safetensors \
--lora_rank 16 \
--lora_alpha 4.0 \
--dataset_path data/lora_dataset_processed \
--output_path ./models \
--max_epochs 1 \
--center_crop \
--use_gradient_checkpointing \
--precision "16-mixed"
""".strip()
os.system(cmd)from diffsynth import ModelManager, SDXLImagePipeline
from peft import LoraConfig, inject_adapter_in_model
import torch
def load_lora(model, lora_rank, lora_alpha, lora_path):
lora_config = LoraConfig(
r=lora_rank,
lora_alpha=lora_alpha,
init_lora_weights="gaussian",
target_modules=["to_q", "to_k", "to_v", "to_out"],
)
model = inject_adapter_in_model(lora_config, model)
state_dict = torch.load(lora_path, map_location="cpu")
model.load_state_dict(state_dict, strict=False)
return model
# Load models
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda",
file_path_list=[
"models/kolors/Kolors/text_encoder",
"models/kolors/Kolors/unet/diffusion_pytorch_model.safetensors",
"models/kolors/Kolors/vae/diffusion_pytorch_model.safetensors"
])
pipe = SDXLImagePipeline.from_model_manager(model_manager)
# Load LoRA
pipe.unet = load_lora(
pipe.unet,
lora_rank=16, # This parameter should be consistent with that in your training script.
lora_alpha=2.0, # lora_alpha can control the weight of LoRA.
lora_path="models/lightning_logs/version_0/checkpoints/epoch=0-step=500.ckpt"
)