本文共享自华为云社区《Pose泰裤辣! 一键提取姿势生成新图画》,作者: Emma_Liu 。
人体姿势骨架生成图画 ControlNet-Human Pose in Stable Diffusion
相关链接:Notebook事例地址: 人体姿势生成图画 ControlNet-Human Pose in Stable Diffusion
AI gallery:developer.huaweicloud.com/develop/aig…
也可通过AI Gallery,查找【人体姿势生成图画】一键体会!
ControlNet
什么是ControlNet?ControlNet最早是在L.Zhang等人的论文《Adding Conditional Control to Text-to-Image Diffusion Model》中提出的,意图是提高预练习的分散模型的功能。它引入了一个结构,支持在分散模型 (如 Stable Diffusion) 上附加额定的多种空间语义条件来操控生成过程。
ControlNet能够仿制构图和人体姿势。它处理了生成想要的切当姿势困难的问题。
Human Pose运用OpenPose检测要害点,如头部、肩膀、手的位置等。它适用于仿制人类姿势,但不适用于其他细节,如服装、发型和布景。
ControlNet 的工作原理是将可练习的网络模块附加到稳定分散模型的U-Net (噪声预测器)的各个部分。Stable Diffusion 模型的权重是确定的,在练习过程中它们是不变的。在练习期间仅修改附加模块。
研讨论文中的模型图很好地总结了这一点。开始,附加网络模块的权重全部为零,使新模型能够利用经过练习和确定的模型。
练习 ControlNet 包含以下过程:
- 克隆分散模型的预练习参数,如Stable Diffusion的潜在UNet,(称为 “可练习副本”),同时也独自保留预练习的参数(“确定副本”)。这样做是为了使确定的参数副本能够保留从大型数据集中学习到的很多常识,而可练习的副本则用于学习特定的使命方面。
- 参数的可练习副本和确定副本通过 “零卷积 “层衔接,该层作为ControlNet结构的一部分被优化。这是一个练习技巧,在练习新的条件时,保留冻结模型现已学会的语义。
从图上看,练习ControlNet是这样的:
ControlNet供给了八个扩展,每个扩展都能够对分散模型进行不同的操控。这些扩展是Canny, Depth, HED, M-LSD, Normal, Openpose, Scribble, and Semantic Segmentation。
ControlNet-Pose2imge适配ModelArts
运用方法:
输入一个图画,并提示模型生成一个图画。Openpose将为你检测姿势,从图画提取人体姿势,用姿势信息操控生成具有相同姿势的新图画。
对两张图画分别为进行人体骨骼姿势提取,然后依据输入描绘词生成图画,如下图所示:
本事例需运用Pytorch-1.8 GPU-P100及以上规格运转
点击Run in ModelArts,将会进入到ModelArts CodeLab中,这时需求你登录华为云账号,假如没有账号,则需求注册一个,且要进行实名认证,参考《ModelArts准备工作_简易版》 即可完结账号注册和实名认证。 登录之后,等待顷刻,即可进入到CodeLab的运转环境
1. 环境准备
为了便利用户下载运用及快速体会,本事例已将代码及control_sd15_openpose预练习模型转存至华为云OBS中。留意:为了运用该模型与权重,你有必要接受该模型所要求的License,请拜访huggingface的lllyasviel/ControlNet, 仔细阅读里面的License。模型下载与加载需求几分钟时间。
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!")
check GPU & 装置依靠
大约耗时1min
!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
导包
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
2. 加载模型
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)
3. 人体姿势生成图画
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)
# 图画预处理
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
设置参数,生成图画
上传您的图画至./ControlNet/test_imgs/ 途径下,然后更改图画途径及其他参数后,点击运转。
参数阐明:
-
img_path:输入图画途径,黑白稿
-
prompt:提示词
-
a_prompt:次要的提示
-
n_prompt: 负面提示,不想要的内容
-
image_resolution: 对输入的图片进行最长边等比resize
-
detect_resolution: 中间生成条件图画的分辨率
-
scale:文本提示的操控强度,越大越强
-
guess_mode: 盲猜形式,默许封闭,开启后生成图画将不受prompt影响,运用更多样性的成果,生成后得到不那么恪守图画条件的成果
-
seed: 随机种子
-
ddim_steps: 采样步数,一般15-30,值越大越精细,耗时越长
-
DDIM eta: 生成过程中的随机噪声系数,一般选0或1,1表明有噪声更多样,0表明无噪声,更恪守描绘条件
-
strength: 这是使用 ControlNet 的过程数。它类似于图画到图画中的去噪强度。假如辅导强度为 1,则 ControlNet 使用于 100% 的采样过程。假如引导强度为 0.7 并且您正在履行 50 个过程,则 ControlNet 将使用于前 70% 的采样过程,即前 35 个过程。
#@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,解剖欠好,手欠好,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()
4. Gradio可视化部署
Gradio使用发动后可在下方页面上传图片依据提示生成图画,您也能够共享public url在手机端,PC端进行拜访生成图画。
请留意: 在图画生成需求耗费显存,您能够在左侧操作栏查看您的实时资源运用情况,点击GPU显存运用率即可查看,当显存缺乏时,您生成图画可能会报错,此时,您能够通过重启kernel的方式重置,然后重头运转即可规避。
block = gr.Blocks().queue()
with block:
with gr.Row():
gr.Markdown("## 人体姿势生成图画")
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="描绘")
run_button = gr.Button(label="Run")
with gr.Accordion("高档选项", 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)
点击重视,第一时间了解华为云新鲜技能~