1. 安装配置MMagic
1.1 安装Pytorch
# 安装Pytorch
!pip3 install install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio==0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
1.2 安装MMCV、MMEngine环境
!pip3 install openmim
!mim install 'mmcv>=2.0.0'
!mim install 'mmengine'
1.3 安装MMagic
方式一：
!mim install 'mmagic'
方式二：源码安装
!rm -rf mmagic # 删除原有的 mmagic 文件夹（如有）
!git clone https://github.com/open-mmlab/mmagic.git # 下载 mmagic 源代码
import os
os.chdir('mmagic')
!pip3 install -e .
1.4检查安装成功
# 检查 Pytorch
import torch, torchvision
print('Pytorch 版本', torch.__version__)
print('CUDA 是否可用',torch.cuda.is_available())
# 检查 mmcv
import mmcv
from mmcv.ops import get_compiling_cuda_version, get_compiler_version
print('MMCV版本', mmcv.__version__)
print('CUDA版本', get_compiling_cuda_version())
print('编译器版本', get_compiler_version())
# 检查 mmagic
import mmagic
print('MMagic版本', mmagic.__version__)
1.5 安装其他工具包
!pip install opencv-python pillow matplotlib seaborn tqdm -i https://pypi.tuna.tsinghua.edu.cn/simple
!pip install clip transformers gradio 'httpx[socks]' diffusers==0.14.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
!mim install 'mmdet>=3.0.0'
2.应用：黑白照片上色
2.1 进入 MMagic 主目录
import os
os.chdir('mmagic')
2.2下载样例图片
!wget https://zihao-openmmlab.obs.cn-east-3.myhuaweicloud.com/20230613-MMagic/data/test_colorization.jpg -O test_colorization.jpg
2.3 运行预测
!python demo/mmagic_inference_demo.py \--model-name inst_colorization \--img test_colorization.jpg \--result-out-dir out_colorization.png
3.应用：文生图 Stable Diffusion
3.1 导入工具包
from mmagic.apis import MMagicInferencer
3.2 载入模型
sd_inferencer = MMagicInferencer(model_name='stable_diffusion')
3.3 指定Prompt文本
text_prompts = 'A panda is having dinner at KFC'
text_prompts = 'A Persian cat walking in the streets of New York'
3.4 预测
sd_inferencer.infer(text=text_prompts, result_out_dir='output/sd_res.png')
4.应用：文生图 Dreambooth
4.1 进入 MMagic 主目录
import os
os.chdir('mmagic')
4.2 在数据集上训练Dreambooth
!bash tools/dist_train.sh configs/dreambooth/dreambooth-lora.py 1
4.3 用训练好的模型做预测
from mmengine import Configfrom mmagic.registry import MODELS
from mmagic.utils import register_all_modulesregister_all_modules()
cfg = Config.fromfile('./mmagic/configs/dreambooth/dreambooth-lora.py')
dreambooth_lora = MODELS.build(cfg.model)
state = torch.load('mmagic/work_dirs/dreambooth-lora/iter_1000.pth')['state_dict']
def convert_state_dict(state):state_dict_new = {}for k, v in state.items():if '.module' in k:k_new = k.replace('.module', '')else:k_new = kif 'vae' in k:if 'to_q' in k:k_new = k.replace('to_q', 'query')elif 'to_k' in k:k_new = k.replace('to_k', 'key')elif 'to_v' in k:k_new = k.replace('to_v', 'value')elif 'to_out' in k:k_new = k.replace('to_out.0', 'proj_attn')state_dict_new[k_new] = vreturn state_dict_new
dreambooth_lora.load_state_dict(convert_state_dict(state))
dreambooth_lora = dreambooth_lora.cuda()
samples = dreambooth_lora.infer('side view of sks dog', guidance_scale=5)
samples['samples'][0]
samples = dreambooth_lora.infer('ear close-up of sks dog', guidance_scale=5)
samples['samples'][0]
5.应用：图生图-ControlNet-Canny
5.1 进入 MMagic 主目录
import os
os.chdir('mmagic')
5.2 导入工具包
import cv2
import numpy as np
import mmcv
from mmengine import Config
from PIL import Imagefrom mmagic.registry import MODELS
from mmagic.utils import register_all_modulesregister_all_modules()
5.3 载入ControlNet模型
cfg = Config.fromfile('configs/controlnet/controlnet-canny.py')
controlnet = MODELS.build(cfg.model).cuda()
5.4 输入Canny边缘图
control_url = 'https://user-images.githubusercontent.com/28132635/230288866-99603172-04cb-47b3-8adb-d1aa532d1d2c.jpg'
control_img = mmcv.imread(control_url)
control = cv2.Canny(control_img, 100, 200)
control = control[:, :, None]
control = np.concatenate([control] * 3, axis=2)
control = Image.fromarray(control)
5.5 Prompt
prompt = 'Room with blue walls and a yellow ceiling.'
5.6 执行预测
output_dict = controlnet.infer(prompt, control=control)
samples = output_dict['samples']
for idx, sample in enumerate(samples):sample.save(f'sample_{idx}.png')
controls = output_dict['controls']
for idx, control in enumerate(controls):control.save(f'control_{idx}.png')
6.应用：图生图-ControlNet-Pose
6.1 进入 MMagic 主目录
import os
os.chdir('mmagic')
6.2 导入工具包
import mmcv
from mmengine import Config
from PIL import Imagefrom mmagic.registry import MODELS
from mmagic.utils import register_all_modulesregister_all_modules()
6.3 载入ControlNet模型
cfg = Config.fromfile('configs/controlnet/controlnet-pose.py')
# convert ControlNet's weight from SD-v1.5 to Counterfeit-v2.5
cfg.model.unet.from_pretrained = 'gsdf/Counterfeit-V2.5'
cfg.model.vae.from_pretrained = 'gsdf/Counterfeit-V2.5'
cfg.model.init_cfg['type'] = 'convert_from_unet'
controlnet = MODELS.build(cfg.model).cuda()
# call init_weights manually to convert weight
controlnet.init_weights()
6.4 Prompt
prompt = 'masterpiece, best quality, sky, black hair, skirt, sailor collar, looking at viewer, short hair, building, bangs, neckerchief, long sleeves, cloudy sky, power lines, shirt, cityscape, pleated skirt, scenery, blunt bangs, city, night, black sailor collar, closed mouth'6.5 输入Pose图
control_url = 'https://user-images.githubusercontent.com/28132635/230380893-2eae68af-d610-4f7f-aa68-c2f22c2abf7e.png'
control_img = mmcv.imread(control_url)
control = Image.fromarray(control_img)
control.save('control.png')
6.6 执行预测
output_dict = controlnet.infer(prompt, control=control, width=512, height=512, guidance_scale=7.5)
samples = output_dict['samples']
for idx, sample in enumerate(samples):sample.save(f'sample_{idx}.png')
controls = output_dict['controls']
for idx, control in enumerate(controls):control.save(f'control_{idx}.png')
7. 图生图-ControlNet Animation
7.1方式一：Gradio命令行
!python demo/gradio_controlnet_animation.py
7.2 方式二：MMagic API
# 导入工具包
from mmagic.apis import MMagicInferencer# Create a MMEdit instance and infer
editor = MMagicInferencer(model_name='controlnet_animation')
# 指定 prompt 咒语
prompt = 'a girl, black hair, T-shirt, smoking, best quality, extremely detailed'
negative_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
# 待测视频
# https://user-images.githubusercontent.com/12782558/227418400-80ad9123-7f8e-4c1a-8e19-0892ebad2a4f.mp4
video = '../run_forrest_frames_rename_resized.mp4'
save_path = '../output_video.mp4'
# 执行预测
editor.infer(video=video, prompt=prompt, image_width=512, image_height=512, negative_prompt=negative_prompt, save_path=save_path)
