AI夏令营 AIGC方向 魔塔

AIGC方向 第四期 task01 笔记

作为一个ai小白，这次的夏令营活动让我见识到了ai的强大，我也想通过这次活动为后续项目奠定一定的经验和技术基础。当然，对于一些模型和框架我也是比较陌生的，下面是我的笔记。

baseline：一个基础模型或标准，用于比较和评估算法的性能，在机器学习和深度学习中尤为重要，可以帮助评估算法的性能是否有所提升。通常在项目或竞赛中会使用。

LoRa模型：低秩适应模型，引入低秩矩阵减少参数，降低微调成本，最初适用于NLP领域，模型的微调能力较强。

1. 首先是申请阿里云PAI-DSW试用（云端机器学习开发IDE），不必申请GPU机器以及下载各种驱动，可以直接创建PAI实例
2. 新建终端，打开baseline文件

3. git lfs install
   git clone https://www.modelscope.cn/datasets/maochase/kolors.git

复制这行代码到baseline ，目的是为了拉取远端文件进行下载

4. 训练模型，输入prompts，获取想要的图片
5. 等待20min，获取图片
   6.新建终端并输入

mkdir /mnt/workspace/kolors/output & cd
cp /mnt/workspace/kolors/models/lightning_logs/version_0/checkpoints/epoch=0-step=500.ckpt /mnt/workspace/kolors/output/
cp /mnt/workspace/kolors/1.jpg /mnt/workspace/kolors/output/

以获取图片并下载至本地

下图为我在魔塔创建的模型（已发布）

后续还会进行进一步的学习，包括微调模型以获得质量更高的图片，精读baseline等

baseline代码

baseline作为一个基础模型，其是通过python代码进行实现的，下面为夏令营提供的代码

1. 安装环境

!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-Studio

2. 下载数据集

#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. 处理数据集，保留数据处理结果

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
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

4. 微调

下载模型

from diffsynth import download_models
download_models([“Kolors”, “SDXL-vae-fp16-fix”])

#模型训练
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)

5.加载微调好的模型

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”
)

6.输出图片

torch.manual_seed(0)
image = pipe(
prompt=“二次元，一个紫色短发小女孩，在家中沙发上坐着，双手托着腮，很无聊，全身，粉色连衣裙”,
negative_prompt=“丑陋、变形、嘈杂、模糊、低对比度”,
cfg_scale=4,
num_inference_steps=50, height=1024, width=1024,
)
image.save(“1.jpg”)

个人收获

python强大的库功能给予了微调的工具，使得模型训练出来更为契合我们的使用，是开发AI的一门不错语言。
kolors作为一款开源的文生图大模型，也让我们自己的模型有各自与众不同的特点。
后续的AI生图的学习与python和kolors大模型是密不可分的。