import os
import moxing as mox
parent = os.path.join(os.getcwd(),'ControlNet')
if not os.path.exists(parent):
mox.file.copy_parallel('obs://modelarts-labs-bj4-v2/case_zoo/ControlNet/ControlNet',parent)
if os.path.exists(parent):
print('Code Copy Completed.')
else:
raise Exception('Failed to Copy the Code.')
else:
print("Code already exists!")
pose_model_path = os.path.join(os.getcwd(),"ControlNet/models/control_sd15_openpose.pth")
body_model_path = os.path.join(os.getcwd(),"ControlNet/annotator/ckpts/body_pose_model.pth")
hand_model_path = os.path.join(os.getcwd(),"ControlNet/annotator/ckpts/hand_pose_model.pth")
if not os.path.exists(pose_model_path):
mox.file.copy_parallel('obs://modelarts-labs-bj4-v2/case_zoo/ControlNet/ControlNet_models/control_sd15_openpose.pth',pose_model_path)
mox.file.copy_parallel('obs://modelarts-labs-bj4-v2/case_zoo/ControlNet/ControlNet_models/body_pose_model.pth',body_model_path)
mox.file.copy_parallel('obs://modelarts-labs-bj4-v2/case_zoo/ControlNet/ControlNet_models/hand_pose_model.pth',hand_model_path)
if os.path.exists(pose_model_path):
print('Models Download Completed')
else:
raise Exception('Failed to Copy the Models.')
else:
print("Model Packages already exists!")

!nvidia-smi
%cd ControlNet
!pip uninstall torch torchtext -y
!pip install torch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1
!pip install omegaconf==2.1.1 einops==0.3.0
!pip install pytorch-lightning==1.5.0
!pip install transformers==4.19.2 open_clip_torch==2.0.2
!pip install gradio==3.24.1
!pip install translate==3.6.1
!pip install scikit-image==0.19.3
!pip install basicsr==1.4.2

import config
import cv2
import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
from annotator.openpose import OpenposeDetector
from cldm.model import create_model, load_state_dict
from cldm.ddim_hacked import DDIMSampler
from translate import Translator
from PIL import Image
import matplotlib.pyplot as plt

apply_openpose = OpenposeDetector()
model = create_model('./models/cldm_v15.yaml').cpu()
model.load_state_dict(load_state_dict('./models/control_sd15_openpose.pth', location='cuda'))
model = model.cuda()
ddim_sampler = DDIMSampler(model)

def infer(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, guess_mode, strength, scale, seed, eta):
trans = Translator(from_lang="ZH",to_lang="EN-US")
prompt = trans.translate(prompt)
a_prompt = trans.translate(a_prompt)
n_prompt = trans.translate(n_prompt)


# 图像预处理
with torch.no_grad():
if type(input_image) is str:
input_image = np.array(Image.open(input_image))
input_image = HWC3(input_image)
detected_map, _ = apply_openpose(resize_image(input_image, detect_resolution))
detected_map = HWC3(detected_map)
img = resize_image(input_image, image_resolution)
H, W, C = img.shape


# 初始化检测映射
detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_NEAREST)
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
# 设置随机种子
if seed == -1:
seed = random.randint(0, 65535)
seed_everything(seed)
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
un_cond = {"c_concat": None if guess_mode else [control], "c_crossattn": [model.get_learned_conditioning([n_prompt] * num_samples)]}
shape = (4, H // 8, W // 8)
if config.save_memory:
model.low_vram_shift(is_diffusing=True)
# 采样
model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13) # Magic number. IDK why. Perhaps because 0.825**12<0.01 but 0.826**12>0.01
samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,
shape, cond, verbose=False, eta=eta,
unconditional_guidance_scale=scale,
unconditional_conditioning=un_cond)
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
# 后处理
x_samples = model.decode_first_stage(samples)
x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
results = [x_samples[i] for i in range(num_samples)]
return [detected_map] + results

#@title ControlNet-OpenPose
img_path = "test_imgs/pose1.png" #@param {type:"string"}
prompt = "优雅的女士" #@param {type:"string"}
seed = 1685862398 #@param {type:"slider", min:-1, max:2147483647, step:1}
guess_mode = False #@param {type:"raw", dropdown}
a_prompt = '质量最好，非常详细'
n_prompt = '长体，下肢，解剖不好，手不好，手指缺失，手指多，手指少，裁剪，质量最差，质量低'
num_samples = 1
image_resolution = 512
detect_resolution = 512
ddim_steps = 20
strength = 1.0
scale = 9.0
eta = 0.0
np_imgs = infer(img_path, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, guess_mode, strength, scale, seed, eta)
ori = Image.open(img_path)
src = Image.fromarray(np_imgs[0])
dst = Image.fromarray(np_imgs[1])
fig = plt.figure(figsize=(25, 10))
ax1 = fig.add_subplot(1, 3, 1)
plt.title('Orginal image', fontsize=16)
ax1.axis('off')
ax1.imshow(ori)
ax2 = fig.add_subplot(1, 3, 2)
plt.title('Pose image', fontsize=16)
ax2.axis('off')
ax2.imshow(src)
ax3 = fig.add_subplot(1, 3, 3)
plt.title('Generate image', fontsize=16)
ax3.axis('off')
ax3.imshow(dst)
plt.show()

block = gr.Blocks().queue()
with block:
with gr.Row():
gr.Markdown("## 💃人体姿态生成图像")
with gr.Row():
with gr.Column():
gr.Markdown("请上传一张人像图，设置好参数后，点击Run")
input_image = gr.Image(source='upload', type="numpy")
prompt = gr.Textbox(label="描述")
run_button = gr.Button(label="Run")
with gr.Accordion("高级选项", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=3, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="OpenPose Resolution", minimum=128, maximum=1024, value=512, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=30, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",
value='longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality')
with gr.Column():
result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid=2, height='auto')
ips = [input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, guess_mode, strength, scale, seed, eta]
run_button.click(fn=infer, inputs=ips, outputs=[result_gallery])
block.launch(share=True)