Datawhale AI夏令营第四期魔搭-AIGC方向 task01笔记

yesno233233 / 2024-08-09 / 原文

Datawhale AI夏令营第四期魔搭-AIGC方向 task01笔记

提示词

提示词很重要，一般写法：主体描述，细节描述，修饰词，艺术风格，艺术家
举个例子
【promts】
Beautiful and cute girl, smiling, 16 years old, denim jacket, gradient background, soft colors, soft lighting, cinematic edge lighting, light and dark contrast, anime, super detail, 8k
【负向prompts】
(lowres, low quality, worst quality:1.2), (text:1.2), deformed, black and white,disfigured, low contrast, cropped, missing fingers

参考图控制

可以给出或粗略或详细的线稿，在此基础上给ai创作

代码

TASK 1
https://linklearner.com/activity/14/10/24

1. 环境安装

!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

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，保存数据处理结果

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. lora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. 图片生成


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")