您的余额不足，模型已暂停发布查看详情

🧨定制你的粘土风照片🧨

AI绘画是AIGC（人工智能创作内容）的一个应用方向，也是2022年以来AI领域最热门的话题之一。目前采用的主流技术是Stable Diffusion，它包含基本的文生图任务text2img，以及图生图img2img、照片修复inpaint、高分辨率生成upscale等多种任务。本案例为粘土风格照片生成，即图生图任务。它提供了一个gradio交互界面，支持上传图片/摄像头拍照，来定制你的粘土风照片。下图为一个简单示例：

背景知识

一、Stable Diffusion技术简介

Stable Diffusion有V1、V2、XL等多个版本，不同版本之下又存在许多细分版本，例如sd-v1.4、sd-v1.5等。不同版本的差异在于，unet/encoder的网络结构不同、训练数据不同、采用多阶段生成等等。
从整体来看，SD会将prompt提示词等文本信息用tokenizer和text_encoder编码为潜向量，将输入图片用vae编码为潜向量，用潜向量作为unet的输入去预测噪声。反复迭代多次，最终得到去噪之后的潜向量，然后将其用vae再解码到像素空间。如此，即为SD pipeline生成图片的基本框架：

什么是负提示词negative_prompt：负提示词是引导Stable Diffusion获得你想要的结果的一种有效方式，而且有些图片只能通过使用负提示词来生成。正提示词的作用是引导扩散模型在prompt相关的潜空间进行采样，而负提示词则相反，会引导扩散模型不在负提示词相关的潜空间采样。举例说明，如果生成的人物照片有“胡子”，而你又不想让模型生成带“胡子”的照片，此时就可以将“胡子/mustache”加入负提示词。

什么是LoRA模型：全称Low-Rank Adaptation of Large Language Models，是一种用于微调大语言模型的技术。LoRA通过仅训练低秩矩阵，然后将这些参数注入到原始模型中，从而实现对模型的微调。LoRA 对Stable Diffusion模型中最关键的部分进行微小改动：交叉注意力层。并且将权重矩阵分解为两个较小（低秩）的矩阵，例如m*n的权重矩阵，分解为m*r和r*n两个低秩矩阵，r<<m,n。相比Dreambooth和文本反转等训练技术，LoRA 在文件大小和训练能力之间取得了良好的平衡。Dreambooth功能强大，但模型文件体积较大（2-7 GB）。文本反转模型很小（约100 KB），但微调能力有限。LoRA 位于二者之间：它们的文件大小适中（2-200 MB），而且训练能力还不错。LoRA模型不能单独使用，它通过修改基础模型的权重来改变生成图片的风格，例如本案例使用的粘土风格的LoRA模型。
什么是ControlNet模型：它允许输入调节图像，然后使用该调节图像来操控Stable Diffusion的图像生成。调节图像的类型众多，例如涂鸦、边缘图、姿势关键点、深度图、分割图、法线图等，这些输入都可以作为条件输入来指导生成图像的内容。详细内容可参考lllyasviel/ControlNet。ControlNet的可训练参数是从unet拷贝的副本，同时添加“zero convolution”，即权重和偏置全部初始化为零的“1x1”卷积。开始训练之前，ControlNet输出为零，不会损害生成的图像质量，随着训练的进行，调节图像的信息被加入，开始影响生成结果。

> ControlNet示意图和网络结构图均源自：https://github.com/lllyasviel/ControlNet

什么是noise schedule：噪声通过多次U-Net的处理，最终会输出我们想要的图片。在这多次迭代的过程中，每一次的降噪的幅度是不同的，所以我们就要通过schedulers来控制每次降噪的幅度（幅度一般是递减的）。其中，降噪幅度逐渐减小的原因是为了更精细地恢复图像的细节和结构。

> 图片源自：https://blog.csdn.net/lizhong2008/article/details/132257722

二、相关参考资料

C站：用户可以下载safetensor格式的模型权重、Lora模型、embedding等。
加载Lora模型推理：Lora作为最受欢迎的一种插件方式（adapter），用户可以在不修改基础模型的前提下，利用少量数据训练出具有特定画风、IP或人物特征的模型。
ControlNet使用方法：用户可以轻松地使用多种空间语义条件信息 (例如深度图、分割图、涂鸦图、关键点等) 来控制生成过程。
controlnet_aux：用于生成深度图、分割图、涂鸦图、关键点等条件输入图片的pip安装包，一般配合ControlNet使用。
降低显存占用：SD模型往往需要较大的显存来推理，huggingface官网提供了一些降低显存的方法。除此之外，释放GPU缓存torch.cuda.empty_cache()也是一种有效方式。

三、粘土风格生成案例介绍

基础模型：LEOSAM_HelloWorld_SDXL_v7.0，模型版权声明见文末
Lora模型：ReminiClay_LoRA_Dim128
controlnet模型：controlnet-canny-sdxl-1.0
粘土风格生成的Pipeline示意图如下：

注意事项

🔹 本案例运行条件：Python3.9、Pytorch-2.0.1，GPU规格选择P100（16G）及以上，CPU规格无限制

🔹 点击右上角Run in ModelArts，将会进入到ModelArts CodeLab中，这时需要你登录华为云账号，如果没有账号，则需要注册一个，且要进行实名认证，参考《如何创建华为云账号并且实名认证》即可完成账号注册和实名认证。登录之后，等待片刻，即可进入到CodeLab的运行环境

🔹 进入CodeLab之后，需要切换规格。可以选择如下图所示规格：nvidia-p100 (16G) * 1：

🔹 出现 Out Of Memory ，请检查是否为您的参数配置过高导致，❗❗❗可以尝试修改参数配置、重启kernel或更换更高规格资源进行规避。

步骤1 下载模型权重和代码

运行如下代码，将从OBS拷贝本案例所需的模型权重和代码文件
- 其中，LEOSAM_HelloWorld_SDXL_v7.0.safetensors是safetensor格式的模型权重，需要转换为diffusers库支持的格式。此外，sd_xl_base.yaml、laion和openai都是转换格式所必须的文件。
- ReminiClay_LoRA_Dim128为粘土风的Lora模型权重，controlnet-canny-sdxl-1.0为controlnet的模型权重。
- man.jpg和input_image_demos是用于测试的demo图片，frpc_linux_amd64是gradio用于生成公网链接的可执行文件。
- opus-mt-zh-en是翻译模型的权重，用于将中文提示词翻译为英文，以获得更好的生成效果。
  - 注意：下载失败无需手动删除，重新执行cell代码即可，下载成功后会出现.clay_file_download_finished文件。

import os
import moxing as mox

def remove_clay_files():
    work_dir = "/home/ma-user/work/ma_share/clay_style_demo"
    exclude_file = "clay_style_demo.ipynb"
    os.system(command=f"cd {work_dir} && rm -rf $(ls {work_dir} | grep -v {exclude_file})")
    os.system(command="rm -rf /home/ma-user/work/.Trash-1000/*")

if os.path.exists(".clay_file_download_finished"):
    print("Files Already Downloaded.")
    print("You can run `rm -f .clay_file_download_finished`, then redownload files.")
else:
    remove_clay_files()
    for f in [
        "LEOSAM_HelloWorld_SDXL_v7.0.safetensors",
        "convert_original_stable_diffusion_to_diffusers.py",
        "sd_xl_base.yaml", "laion", "openai",
        "ReminiClay_LoRA_Dim128",
        "controlnet-canny-sdxl-1.0",
        "man.jpg", "input_image_demos", "frpc_linux_amd64",
        "opus-mt-zh-en", "gradio_demo.py", "ipywidgets_demo.py"
    ]:
        mox.file.copy_parallel(f"obs://modelarts-labs-bj4-v2/case_zoo/clay_style_demo/{f}", f)
    os.system(command="touch .clay_file_download_finished")
print("\033[32m模型权重和代码文件，下载成功！\033[0m")

Files Already Downloaded.
You can run `rm -f .clay_file_download_finished`, then redownload files.
模型权重和代码文件，下载成功！

步骤2 准备推理环境

1. conda虚拟环境

本案例需要Python3.9以上版本，因此需要先创建conda虚拟环境，然后将notebook的kernel切换为Python3.9，再执行后续代码

运行如下代码，将创建名为python-3.9.15的虚拟环境，并为其安装ipykernel：

!/home/ma-user/anaconda3/bin/conda clean -i
!/home/ma-user/anaconda3/bin/conda create -n python-3.9.15 python=3.9.15 -y --override-channels --channel https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
!/home/ma-user/anaconda3/envs/python-3.9.15/bin/pip install ipykernel

显示 output

/home/ma-user/anaconda3/lib/python3.7/site-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.12) or chardet (3.0.4) doesn't match a supported version!
  RequestsDependencyWarning)
/home/ma-user/anaconda3/lib/python3.7/site-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.12) or chardet (3.0.4) doesn't match a supported version!
  RequestsDependencyWarning)
Collecting package metadata (current_repodata.json): done
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: done

## Package Plan ##

  environment location: /home/ma-user/anaconda3/envs/python-3.9.15

  added / updated specs:
    - python=3.9.15


The following packages will be downloaded:

    package                    |            build
    ---------------------------|-----------------
    _libgcc_mutex-0.1          |             main           3 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    _openmp_mutex-5.1          |            1_gnu          21 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    ca-certificates-2024.11.26 |       h06a4308_0         131 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    ld_impl_linux-64-2.40      |       h12ee557_0         710 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    libffi-3.4.4               |       h6a678d5_1         141 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    libgcc-ng-11.2.0           |       h1234567_1         5.3 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    libgomp-11.2.0             |       h1234567_1         474 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    libstdcxx-ng-11.2.0        |       h1234567_1         4.7 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    ncurses-6.4                |       h6a678d5_0         914 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    openssl-1.1.1w             |       h7f8727e_0         3.7 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    pip-24.2                   |   py39h06a4308_0         2.2 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    python-3.9.15              |       h7a1cb2a_2        25.0 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    readline-8.2               |       h5eee18b_0         357 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    setuptools-75.1.0          |   py39h06a4308_0         1.7 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    sqlite-3.45.3              |       h5eee18b_0         1.2 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    tk-8.6.14                  |       h39e8969_0         3.4 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    tzdata-2024b               |       h04d1e81_0         115 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    wheel-0.44.0               |   py39h06a4308_0         108 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    xz-5.4.6                   |       h5eee18b_1         643 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    zlib-1.2.13                |       h5eee18b_1         111 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    ------------------------------------------------------------
                                           Total:        51.0 MB

The following NEW packages will be INSTALLED:

  _libgcc_mutex      anaconda/pkgs/main/linux-64::_libgcc_mutex-0.1-main
  _openmp_mutex      anaconda/pkgs/main/linux-64::_openmp_mutex-5.1-1_gnu
  ca-certificates    anaconda/pkgs/main/linux-64::ca-certificates-2024.11.26-h06a4308_0
  ld_impl_linux-64   anaconda/pkgs/main/linux-64::ld_impl_linux-64-2.40-h12ee557_0
  libffi             anaconda/pkgs/main/linux-64::libffi-3.4.4-h6a678d5_1
  libgcc-ng          anaconda/pkgs/main/linux-64::libgcc-ng-11.2.0-h1234567_1
  libgomp            anaconda/pkgs/main/linux-64::libgomp-11.2.0-h1234567_1
  libstdcxx-ng       anaconda/pkgs/main/linux-64::libstdcxx-ng-11.2.0-h1234567_1
  ncurses            anaconda/pkgs/main/linux-64::ncurses-6.4-h6a678d5_0
  openssl            anaconda/pkgs/main/linux-64::openssl-1.1.1w-h7f8727e_0
  pip                anaconda/pkgs/main/linux-64::pip-24.2-py39h06a4308_0
  python             anaconda/pkgs/main/linux-64::python-3.9.15-h7a1cb2a_2
  readline           anaconda/pkgs/main/linux-64::readline-8.2-h5eee18b_0
  setuptools         anaconda/pkgs/main/linux-64::setuptools-75.1.0-py39h06a4308_0
  sqlite             anaconda/pkgs/main/linux-64::sqlite-3.45.3-h5eee18b_0
  tk                 anaconda/pkgs/main/linux-64::tk-8.6.14-h39e8969_0
  tzdata             anaconda/pkgs/main/noarch::tzdata-2024b-h04d1e81_0
  wheel              anaconda/pkgs/main/linux-64::wheel-0.44.0-py39h06a4308_0
  xz                 anaconda/pkgs/main/linux-64::xz-5.4.6-h5eee18b_1
  zlib               anaconda/pkgs/main/linux-64::zlib-1.2.13-h5eee18b_1



Downloading and Extracting Packages
ld_impl_linux-64-2.4 | 710 KB    | ##################################### | 100% 
_openmp_mutex-5.1    | 21 KB     | ##################################### | 100% 
setuptools-75.1.0    | 1.7 MB    | ##################################### | 100% 
libstdcxx-ng-11.2.0  | 4.7 MB    | ##################################### | 100% 
python-3.9.15        | 25.0 MB   | ##################################### | 100% 
ca-certificates-2024 | 131 KB    | ##################################### | 100% 
libgcc-ng-11.2.0     | 5.3 MB    | ##################################### | 100% 
openssl-1.1.1w       | 3.7 MB    | ##################################### | 100% 
xz-5.4.6             | 643 KB    | ##################################### | 100% 
libffi-3.4.4         | 141 KB    | ##################################### | 100% 
sqlite-3.45.3        | 1.2 MB    | ##################################### | 100% 
zlib-1.2.13          | 111 KB    | ##################################### | 100% 
_libgcc_mutex-0.1    | 3 KB      | ##################################### | 100% 
ncurses-6.4          | 914 KB    | ##################################### | 100% 
readline-8.2         | 357 KB    | ##################################### | 100% 
tzdata-2024b         | 115 KB    | ##################################### | 100% 
wheel-0.44.0         | 108 KB    | ##################################### | 100% 
tk-8.6.14            | 3.4 MB    | ##################################### | 100% 
libgomp-11.2.0       | 474 KB    | ##################################### | 100% 
pip-24.2             | 2.2 MB    | ##################################### | 100% 
Preparing transaction: done
Verifying transaction: done
Executing transaction: done
#
# To activate this environment, use
#
#     $ conda activate python-3.9.15
#
# To deactivate an active environment, use
#
#     $ conda deactivate

Looking in indexes: http://repo.myhuaweicloud.com/repository/pypi/simple
Collecting ipykernel
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/94/5c/368ae6c01c7628438358e6d337c19b05425727fbb221d2a3c4303c372f42/ipykernel-6.29.5-py3-none-any.whl (117 kB)
Collecting comm>=0.1.1 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e6/75/49e5bfe642f71f272236b5b2d2691cf915a7283cc0ceda56357b61daa538/comm-0.2.2-py3-none-any.whl (7.2 kB)
Collecting debugpy>=1.6.5 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/50/bd/1a90c7800a4e2ddb30beec175e2537a008e863801ccc5747ace42703c60c/debugpy-1.8.9-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.6/3.6 MB 87.3 MB/s eta 0:00:00
Collecting ipython>=7.23.1 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/47/6b/d9fdcdef2eb6a23f391251fde8781c38d42acd82abe84d054cb74f7863b0/ipython-8.18.1-py3-none-any.whl (808 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 808.2/808.2 kB 11.8 MB/s eta 0:00:00
Collecting jupyter-client>=6.1.12 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/11/85/b0394e0b6fcccd2c1eeefc230978a6f8cb0c5df1e4cd3e7625735a0d7d1e/jupyter_client-8.6.3-py3-none-any.whl (106 kB)
Collecting jupyter-core!=5.0.*,>=4.12 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/c9/fb/108ecd1fe961941959ad0ee4e12ee7b8b1477247f30b1fdfd83ceaf017f0/jupyter_core-5.7.2-py3-none-any.whl (28 kB)
Collecting matplotlib-inline>=0.1 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/8f/8e/9ad090d3553c280a8060fbf6e24dc1c0c29704ee7d1c372f0c174aa59285/matplotlib_inline-0.1.7-py3-none-any.whl (9.9 kB)
Collecting nest-asyncio (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a0/c4/c2971a3ba4c6103a3d10c4b0f24f461ddc027f0f09763220cf35ca1401b3/nest_asyncio-1.6.0-py3-none-any.whl (5.2 kB)
Collecting packaging (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/88/ef/eb23f262cca3c0c4eb7ab1933c3b1f03d021f2c48f54763065b6f0e321be/packaging-24.2-py3-none-any.whl (65 kB)
Collecting psutil (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/58/4d/8245e6f76a93c98aab285a43ea71ff1b171bcd90c9d238bf81f7021fb233/psutil-6.1.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (287 kB)
Collecting pyzmq>=24 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/6e/bd/3ff3e1172f12f55769793a3a334e956ec2886805ebfb2f64756b6b5c6a1a/pyzmq-26.2.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (862 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 862.1/862.1 kB 39.2 MB/s eta 0:00:00
Collecting tornado>=6.1 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/22/55/b78a464de78051a30599ceb6983b01d8f732e6f69bf37b4ed07f642ac0fc/tornado-6.4.2-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (437 kB)
Collecting traitlets>=5.4.0 (from ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/00/c0/8f5d070730d7836adc9c9b6408dec68c6ced86b304a9b26a14df072a6e8c/traitlets-5.14.3-py3-none-any.whl (85 kB)
Collecting decorator (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d5/50/83c593b07763e1161326b3b8c6686f0f4b0f24d5526546bee538c89837d6/decorator-5.1.1-py3-none-any.whl (9.1 kB)
Collecting jedi>=0.16 (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/c0/5a/9cac0c82afec3d09ccd97c8b6502d48f165f9124db81b4bcb90b4af974ee/jedi-0.19.2-py2.py3-none-any.whl (1.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 22.2 MB/s eta 0:00:00
Collecting prompt-toolkit<3.1.0,>=3.0.41 (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a9/6a/fd08d94654f7e67c52ca30523a178b3f8ccc4237fce4be90d39c938a831a/prompt_toolkit-3.0.48-py3-none-any.whl (386 kB)
Collecting pygments>=2.4.0 (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f7/3f/01c8b82017c199075f8f788d0d906b9ffbbc5a47dc9918a945e13d5a2bda/pygments-2.18.0-py3-none-any.whl (1.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 18.8 MB/s eta 0:00:00
Collecting stack-data (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f1/7b/ce1eafaf1a76852e2ec9b22edecf1daa58175c090266e9f6c64afcd81d91/stack_data-0.6.3-py3-none-any.whl (24 kB)
Collecting typing-extensions (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/26/9f/ad63fc0248c5379346306f8668cda6e2e2e9c95e01216d2b8ffd9ff037d0/typing_extensions-4.12.2-py3-none-any.whl (37 kB)
Collecting exceptiongroup (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/02/cc/b7e31358aac6ed1ef2bb790a9746ac2c69bcb3c8588b41616914eb106eaf/exceptiongroup-1.2.2-py3-none-any.whl (16 kB)
Collecting pexpect>4.3 (from ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/9e/c3/059298687310d527a58bb01f3b1965787ee3b40dce76752eda8b44e9a2c5/pexpect-4.9.0-py2.py3-none-any.whl (63 kB)
Collecting importlib-metadata>=4.8.3 (from jupyter-client>=6.1.12->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a0/d9/a1e041c5e7caa9a05c925f4bdbdfb7f006d1f74996af53467bc394c97be7/importlib_metadata-8.5.0-py3-none-any.whl (26 kB)
Collecting python-dateutil>=2.8.2 (from jupyter-client>=6.1.12->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl (229 kB)
Collecting platformdirs>=2.5 (from jupyter-core!=5.0.*,>=4.12->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/3c/a6/bc1012356d8ece4d66dd75c4b9fc6c1f6650ddd5991e421177d9f8f671be/platformdirs-4.3.6-py3-none-any.whl (18 kB)
Collecting zipp>=3.20 (from importlib-metadata>=4.8.3->jupyter-client>=6.1.12->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b7/1a/7e4798e9339adc931158c9d69ecc34f5e6791489d469f5e50ec15e35f458/zipp-3.21.0-py3-none-any.whl (9.6 kB)
Collecting parso<0.9.0,>=0.8.4 (from jedi>=0.16->ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/c6/ac/dac4a63f978e4dcb3c6d3a78c4d8e0192a113d288502a1216950c41b1027/parso-0.8.4-py2.py3-none-any.whl (103 kB)
Collecting ptyprocess>=0.5 (from pexpect>4.3->ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/22/a6/858897256d0deac81a172289110f31629fc4cee19b6f01283303e18c8db3/ptyprocess-0.7.0-py2.py3-none-any.whl (13 kB)
Collecting wcwidth (from prompt-toolkit<3.1.0,>=3.0.41->ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fd/84/fd2ba7aafacbad3c4201d395674fc6348826569da3c0937e75505ead3528/wcwidth-0.2.13-py2.py3-none-any.whl (34 kB)
Collecting six>=1.5 (from python-dateutil>=2.8.2->jupyter-client>=6.1.12->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d9/5a/e7c31adbe875f2abbb91bd84cf2dc52d792b5a01506781dbcf25c91daf11/six-1.16.0-py2.py3-none-any.whl (11 kB)
Collecting executing>=1.2.0 (from stack-data->ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b5/fd/afcd0496feca3276f509df3dbd5dae726fcc756f1a08d9e25abe1733f962/executing-2.1.0-py2.py3-none-any.whl (25 kB)
Collecting asttokens>=2.1.0 (from stack-data->ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/25/8a/c46dcc25341b5bce5472c718902eb3d38600a903b14fa6aeecef3f21a46f/asttokens-3.0.0-py3-none-any.whl (26 kB)
Collecting pure-eval (from stack-data->ipython>=7.23.1->ipykernel)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/8e/37/efad0257dc6e593a18957422533ff0f87ede7c9c6ea010a2177d738fb82f/pure_eval-0.2.3-py3-none-any.whl (11 kB)
Installing collected packages: wcwidth, pure-eval, ptyprocess, zipp, typing-extensions, traitlets, tornado, six, pyzmq, pygments, psutil, prompt-toolkit, platformdirs, pexpect, parso, packaging, nest-asyncio, executing, exceptiongroup, decorator, debugpy, asttokens, stack-data, python-dateutil, matplotlib-inline, jupyter-core, jedi, importlib-metadata, comm, jupyter-client, ipython, ipykernel
Successfully installed asttokens-3.0.0 comm-0.2.2 debugpy-1.8.9 decorator-5.1.1 exceptiongroup-1.2.2 executing-2.1.0 importlib-metadata-8.5.0 ipykernel-6.29.5 ipython-8.18.1 jedi-0.19.2 jupyter-client-8.6.3 jupyter-core-5.7.2 matplotlib-inline-0.1.7 nest-asyncio-1.6.0 packaging-24.2 parso-0.8.4 pexpect-4.9.0 platformdirs-4.3.6 prompt-toolkit-3.0.48 psutil-6.1.0 ptyprocess-0.7.0 pure-eval-0.2.3 pygments-2.18.0 python-dateutil-2.9.0.post0 pyzmq-26.2.0 six-1.16.0 stack-data-0.6.3 tornado-6.4.2 traitlets-5.14.3 typing-extensions-4.12.2 wcwidth-0.2.13 zipp-3.21.0

运行如下代码，将注册kernel为python-3.9.15的虚拟环境，主要是把包含环境变量和python解释器路径的kernel.json文件，写入/home/ma-user/anaconda3/share/jupyter/kernels/python-3.9.15目录下

import json
import os

PYTHON_VERSION="3.9.15"
PATH=os.environ.get("PATH")
data = {
   "display_name": f"python-{PYTHON_VERSION}",
   "env": {
      "PATH": f"/home/ma-user/anaconda3/envs/python-{PYTHON_VERSION}/bin:/home/ma-user/anaconda3/envs/python-3.7.10/bin:/home/ma-user/anaconda3/envs/PyTorch-1.8/bin:/usr/local/openmpi/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/modelarts/authoring/notebook-conda/bin:/home/ma-user/modelarts-dev/ma-cli/bin:/modelarts/authoring/script/entrypoint/deps/ssh/bin"
   },
   "language": "python",
   "argv": [
      f"/home/ma-user/anaconda3/envs/python-{PYTHON_VERSION}/bin/python",
      "-m",
      "ipykernel",
      "-f",
      "{connection_file}"
   ]
}

jupyter_kernel_dir = f"/home/ma-user/anaconda3/share/jupyter/kernels/python-{PYTHON_VERSION}"
if not os.path.exists(jupyter_kernel_dir):
    os.mkdir(jupyter_kernel_dir)
with open(os.path.join(jupyter_kernel_dir, "kernel.json"), "w") as f:
    json.dump(data, f, indent=4)

注册完成后，稍等片刻或刷新页面，点击右上角kernel，选择python-3.9.15

查看python版本，❗❗❗ 确保python版本满足要求（python>=3.9）

!python -V

Python 3.9.15

2. 运行依赖环境

运行如下代码，将安装torch2.0.1以及其他第三方依赖

!pip install --upgrade pip
!pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
!pip install diffusers==0.30.0 transformers==4.44.0 accelerate==0.33.0 peft==0.12.0 gradio==3.41.2 safetensors==0.4.2 controlnet-aux==0.0.9 mediapipe==0.10.14 xformers==0.0.21 sentencepiece==0.2.0
!pip install python-multipart==0.0.13 ipywidgets==7.7.1

显示 output

Looking in indexes: http://repo.myhuaweicloud.com/repository/pypi/simple
Requirement already satisfied: pip in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (24.2)
Collecting pip
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ef/7d/500c9ad20238fcfcb4cb9243eede163594d7020ce87bd9610c9e02771876/pip-24.3.1-py3-none-any.whl (1.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.8/1.8 MB 50.5 MB/s eta 0:00:00
Installing collected packages: pip
  Attempting uninstall: pip
    Found existing installation: pip 24.2
    Uninstalling pip-24.2:
      Successfully uninstalled pip-24.2
Successfully installed pip-24.3.1
Looking in indexes: http://repo.myhuaweicloud.com/repository/pypi/simple
Collecting torch==2.0.1
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e5/9a/ce0fe125f226ffce8deba6a18bd8d0b9f589aa236780a83a6d70b5525f56/torch-2.0.1-cp39-cp39-manylinux1_x86_64.whl (619.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 619.9/619.9 MB 91.1 MB/s eta 0:00:0000:0100:01
Collecting torchvision==0.15.2
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/41/9e/8809e45a084680394e8d219fcf8a2c0eed2dddf1ec0a7968f4052826a6e9/torchvision-0.15.2-cp39-cp39-manylinux1_x86_64.whl (6.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.0/6.0 MB 85.3 MB/s eta 0:00:00
Collecting torchaudio==2.0.2
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/eb/b0/b72708eca97014d756e4be2b92eca53e23a202028a24a5e0482adca8d6f7/torchaudio-2.0.2-cp39-cp39-manylinux1_x86_64.whl (4.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.4/4.4 MB 36.2 MB/s eta 0:00:00
Collecting filelock (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b9/f8/feced7779d755758a52d1f6635d990b8d98dc0a29fa568bbe0625f18fdf3/filelock-3.16.1-py3-none-any.whl (16 kB)
Requirement already satisfied: typing-extensions in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch==2.0.1) (4.12.2)
Collecting sympy (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/99/ff/c87e0622b1dadea79d2fb0b25ade9ed98954c9033722eb707053d310d4f3/sympy-1.13.3-py3-none-any.whl (6.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.2/6.2 MB 70.8 MB/s eta 0:00:00
Collecting networkx (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d5/f0/8fbc882ca80cf077f1b246c0e3c3465f7f415439bdea6b899f6b19f61f70/networkx-3.2.1-py3-none-any.whl (1.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 25.8 MB/s eta 0:00:00
Collecting jinja2 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/31/80/3a54838c3fb461f6fec263ebf3a3a41771bd05190238de3486aae8540c36/jinja2-3.1.4-py3-none-any.whl (133 kB)
Collecting nvidia-cuda-nvrtc-cu11==11.7.99 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ef/25/922c5996aada6611b79b53985af7999fc629aee1d5d001b6a22431e18fec/nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl (21.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 21.0/21.0 MB 153.5 MB/s eta 0:00:00
Collecting nvidia-cuda-runtime-cu11==11.7.99 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/36/92/89cf558b514125d2ebd8344dd2f0533404b416486ff681d5434a5832a019/nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl (849 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 849.3/849.3 kB 35.7 MB/s eta 0:00:00
Collecting nvidia-cuda-cupti-cu11==11.7.101 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e6/9d/dd0cdcd800e642e3c82ee3b5987c751afd4f3fb9cc2752517f42c3bc6e49/nvidia_cuda_cupti_cu11-11.7.101-py3-none-manylinux1_x86_64.whl (11.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.8/11.8 MB 125.4 MB/s eta 0:00:00
Collecting nvidia-cudnn-cu11==8.5.0.96 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/dc/30/66d4347d6e864334da5bb1c7571305e501dcb11b9155971421bb7bb5315f/nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl (557.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 557.1/557.1 MB 163.4 MB/s eta 0:00:0000:0100:01
Collecting nvidia-cublas-cu11==11.10.3.66 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ce/41/fdeb62b5437996e841d83d7d2714ca75b886547ee8017ee2fe6ea409d983/nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl (317.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 317.1/317.1 MB 217.9 MB/s eta 0:00:0000:0100:01
Collecting nvidia-cufft-cu11==10.9.0.58 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/64/c8/133717b43182ba063803e983e7680a94826a9f4ff5734af0ca315803f1b3/nvidia_cufft_cu11-10.9.0.58-py3-none-manylinux2014_x86_64.whl (168.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 168.4/168.4 MB 187.4 MB/s eta 0:00:0000:0100:01
Collecting nvidia-curand-cu11==10.2.10.91 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/8f/11/af78d54b2420e64a4dd19e704f5bb69dcb5a6a3138b4465d6a48cdf59a21/nvidia_curand_cu11-10.2.10.91-py3-none-manylinux1_x86_64.whl (54.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 54.6/54.6 MB 125.3 MB/s eta 0:00:0000:0100:01
Collecting nvidia-cusolver-cu11==11.4.0.1 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/3e/77/66149e3153b19312fb782ea367f3f950123b93916a45538b573fe373570a/nvidia_cusolver_cu11-11.4.0.1-2-py3-none-manylinux1_x86_64.whl (102.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 102.6/102.6 MB 201.1 MB/s eta 0:00:0000:0100:01
Collecting nvidia-cusparse-cu11==11.7.4.91 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ea/6f/6d032cc1bb7db88a989ddce3f4968419a7edeafda362847f42f614b1f845/nvidia_cusparse_cu11-11.7.4.91-py3-none-manylinux1_x86_64.whl (173.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 173.2/173.2 MB 213.8 MB/s eta 0:00:0000:0100:01
Collecting nvidia-nccl-cu11==2.14.3 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/55/92/914cdb650b6a5d1478f83148597a25e90ea37d739bd563c5096b0e8a5f43/nvidia_nccl_cu11-2.14.3-py3-none-manylinux1_x86_64.whl (177.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 177.1/177.1 MB 218.7 MB/s eta 0:00:0000:0100:01
Collecting nvidia-nvtx-cu11==11.7.91 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/23/d5/09493ff0e64fd77523afbbb075108f27a13790479efe86b9ffb4587671b5/nvidia_nvtx_cu11-11.7.91-py3-none-manylinux1_x86_64.whl (98 kB)
Collecting triton==2.0.0 (from torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/77/ac/28b74ec1177c730d0da8803eaff5e5025bd532bcf07cadb0fcf661abed97/triton-2.0.0-1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (63.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 63.3/63.3 MB 141.8 MB/s eta 0:00:0000:0100:01
Collecting numpy (from torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b9/14/78635daab4b07c0930c919d451b8bf8c164774e6a3413aed04a6d95758ce/numpy-2.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (19.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 19.5/19.5 MB 124.3 MB/s eta 0:00:00
Collecting requests (from torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f9/9b/335f9764261e915ed497fcdeb11df5dfd6f7bf257d4a6a2a686d80da4d54/requests-2.32.3-py3-none-any.whl (64 kB)
Collecting pillow!=8.3.*,>=5.3.0 (from torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/14/b1/c8f428bae932a27ce9c87e7b21aba8ea3e820aa11413c5a795868c37e039/pillow-11.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.3/4.3 MB 34.1 MB/s eta 0:00:00
Requirement already satisfied: setuptools in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch==2.0.1) (75.1.0)
Requirement already satisfied: wheel in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch==2.0.1) (0.44.0)
Collecting cmake (from triton==2.0.0->torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b8/8d/a7cf7573df4c67de7cb4b2e36cfc790462b90813baa14604c3693a23d89b/cmake-3.31.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (27.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 27.8/27.8 MB 87.3 MB/s eta 0:00:00a 0:00:01
Collecting lit (from triton==2.0.0->torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/96/06/b36f150fa7c5bcc96a31a4d19a20fddbd1d965b6f02510b57a3bb8d4b930/lit-18.1.8-py3-none-any.whl (96 kB)
Collecting MarkupSafe>=2.0 (from jinja2->torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/53/8f/f339c98a178f3c1e545622206b40986a4c3307fe39f70ccd3d9df9a9e425/MarkupSafe-3.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (20 kB)
Collecting charset-normalizer<4,>=2 (from requests->torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/28/89/60f51ad71f63aaaa7e51a2a2ad37919985a341a1d267070f212cdf6c2d22/charset_normalizer-3.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (144 kB)
Collecting idna<4,>=2.5 (from requests->torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl (70 kB)
Collecting urllib3<3,>=1.21.1 (from requests->torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ce/d9/5f4c13cecde62396b0d3fe530a50ccea91e7dfc1ccf0e09c228841bb5ba8/urllib3-2.2.3-py3-none-any.whl (126 kB)
Collecting certifi>=2017.4.17 (from requests->torchvision==0.15.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/12/90/3c9ff0512038035f59d279fddeb79f5f1eccd8859f06d6163c58798b9487/certifi-2024.8.30-py3-none-any.whl (167 kB)
Collecting mpmath<1.4,>=1.1.0 (from sympy->torch==2.0.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl (536 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 536.2/536.2 kB 10.2 MB/s eta 0:00:00
Installing collected packages: mpmath, lit, urllib3, sympy, pillow, nvidia-nvtx-cu11, nvidia-nccl-cu11, nvidia-cusparse-cu11, nvidia-curand-cu11, nvidia-cufft-cu11, nvidia-cuda-runtime-cu11, nvidia-cuda-nvrtc-cu11, nvidia-cuda-cupti-cu11, nvidia-cublas-cu11, numpy, networkx, MarkupSafe, idna, filelock, cmake, charset-normalizer, certifi, requests, nvidia-cusolver-cu11, nvidia-cudnn-cu11, jinja2, triton, torch, torchvision, torchaudio
Successfully installed MarkupSafe-3.0.2 certifi-2024.8.30 charset-normalizer-3.4.0 cmake-3.31.1 filelock-3.16.1 idna-3.10 jinja2-3.1.4 lit-18.1.8 mpmath-1.3.0 networkx-3.2.1 numpy-2.0.2 nvidia-cublas-cu11-11.10.3.66 nvidia-cuda-cupti-cu11-11.7.101 nvidia-cuda-nvrtc-cu11-11.7.99 nvidia-cuda-runtime-cu11-11.7.99 nvidia-cudnn-cu11-8.5.0.96 nvidia-cufft-cu11-10.9.0.58 nvidia-curand-cu11-10.2.10.91 nvidia-cusolver-cu11-11.4.0.1 nvidia-cusparse-cu11-11.7.4.91 nvidia-nccl-cu11-2.14.3 nvidia-nvtx-cu11-11.7.91 pillow-11.0.0 requests-2.32.3 sympy-1.13.3 torch-2.0.1 torchaudio-2.0.2 torchvision-0.15.2 triton-2.0.0 urllib3-2.2.3
Looking in indexes: http://repo.myhuaweicloud.com/repository/pypi/simple
Collecting diffusers==0.30.0
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/74/2b/69bb842f7567cd92a540f8a9a63a20e09304ad8ff84530f26762e7e19626/diffusers-0.30.0-py3-none-any.whl (2.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.6/2.6 MB 64.0 MB/s eta 0:00:00
Collecting transformers==4.44.0
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/62/c0/810e741a6244c0f004be40ccb96486d072f042eabbd4d7e8aa02b81ca1eb/transformers-4.44.0-py3-none-any.whl (9.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 9.5/9.5 MB 119.5 MB/s eta 0:00:00
Collecting accelerate==0.33.0
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/15/33/b6b4ad5efa8b9f4275d4ed17ff8a44c97276171341ba565fdffb0e3dc5e8/accelerate-0.33.0-py3-none-any.whl (315 kB)
Collecting peft==0.12.0
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/62/72/fcabddf222ec938c3cbd5616e5a72796938b5235897e07a1fcc2a8e7735e/peft-0.12.0-py3-none-any.whl (296 kB)
Collecting gradio==3.41.2
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/df/e7/e0b548208ff5db6323ad974f094e9435adb0a377f35274196fb74adaf58a/gradio-3.41.2-py3-none-any.whl (20.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 20.1/20.1 MB 146.6 MB/s eta 0:00:00
Collecting safetensors==0.4.2
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/aa/9a/723fc6eed972b28bbb24241b246005093b3c27340bc8f7b7606d75a92834/safetensors-0.4.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 19.5 MB/s eta 0:00:00
Collecting controlnet-aux==0.0.9
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/9a/2e/3688dea6d9f22ec152fb931c15329c45df4f87078862fadc1fff0064abd4/controlnet_aux-0.0.9-py3-none-any.whl (282 kB)
Collecting mediapipe==0.10.14
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/95/b3/364d02d03afbd5330a4487c1576fd2757d85b061dbce5baff3d02359d2ef/mediapipe-0.10.14-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (35.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 35.7/35.7 MB 180.4 MB/s eta 0:00:00
Collecting xformers==0.0.21
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/4e/79/f4c2b912efc31839e925fad3cecfb9dfa5bd4d5e63109283724c2f1a5b4c/xformers-0.0.21-cp39-cp39-manylinux2014_x86_64.whl (167.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 167.0/167.0 MB 216.0 MB/s eta 0:00:0000:0100:01
Collecting sentencepiece==0.2.0
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/5f/01/c95e42eb86282b2c79305d3e0b0ca5a743f85a61262bb7130999c70b9374/sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 42.7 MB/s eta 0:00:00
Requirement already satisfied: importlib-metadata in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from diffusers==0.30.0) (8.5.0)
Requirement already satisfied: filelock in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from diffusers==0.30.0) (3.16.1)
Collecting huggingface-hub>=0.23.2 (from diffusers==0.30.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/95/9b/3068fb3ae0b498eb66960ca5f4d92a81c91458cacd4dc17bfa6d40ce90fb/huggingface_hub-0.26.3-py3-none-any.whl (447 kB)
Requirement already satisfied: numpy in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from diffusers==0.30.0) (2.0.2)
Collecting regex!=2019.12.17 (from diffusers==0.30.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/86/44/2101cc0890c3621b90365c9ee8d7291a597c0722ad66eccd6ffa7f1bcc09/regex-2024.11.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (780 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 780.9/780.9 kB 25.7 MB/s eta 0:00:00
Requirement already satisfied: requests in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from diffusers==0.30.0) (2.32.3)
Requirement already satisfied: Pillow in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from diffusers==0.30.0) (11.0.0)
Requirement already satisfied: packaging>=20.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from transformers==4.44.0) (24.2)
Collecting pyyaml>=5.1 (from transformers==4.44.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/3d/32/e7bd8535d22ea2874cef6a81021ba019474ace0d13a4819c2a4bce79bd6a/PyYAML-6.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (737 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 737.4/737.4 kB 16.8 MB/s eta 0:00:00
Collecting tokenizers<0.20,>=0.19 (from transformers==4.44.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/0f/cb/8fc733c8f251bac1e5c4ae52458c353b3faa98f41d734c226cad3783da03/tokenizers-0.19.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.6/3.6 MB 37.6 MB/s eta 0:00:00
Collecting tqdm>=4.27 (from transformers==4.44.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl (78 kB)
Collecting numpy (from diffusers==0.30.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/54/30/c2a907b9443cf42b90c17ad10c1e8fa801975f01cb9764f3f8eb8aea638b/numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 18.2/18.2 MB 126.2 MB/s eta 0:00:00
Requirement already satisfied: psutil in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from accelerate==0.33.0) (6.1.0)
Requirement already satisfied: torch>=1.10.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from accelerate==0.33.0) (2.0.1)
Collecting aiofiles<24.0,>=22.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/c5/19/5af6804c4cc0fed83f47bff6e413a98a36618e7d40185cd36e69737f3b0e/aiofiles-23.2.1-py3-none-any.whl (15 kB)
Collecting altair<6.0,>=4.2.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/aa/f3/0b6ced594e51cc95d8c1fc1640d3623770d01e4969d29c0bd09945fafefa/altair-5.5.0-py3-none-any.whl (731 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 731.2/731.2 kB 13.4 MB/s eta 0:00:00
Collecting fastapi (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/54/c4/148d5046a96c428464557264877ae5a9338a83bbe0df045088749ec89820/fastapi-0.115.5-py3-none-any.whl (94 kB)
Collecting ffmpy (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ff/1e/db99aa669eee301966bc6c997d60a0240f9cecae63f044b2e5a5310e4bf7/ffmpy-0.4.0-py3-none-any.whl (5.8 kB)
Collecting gradio-client==0.5.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fe/85/ec0323f39192c4bee04e8e06e64213aff816b9d1b61c3c8367e75b1c7e10/gradio_client-0.5.0-py3-none-any.whl (298 kB)
Collecting httpx (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/8f/fb/a19866137577ba60c6d8b69498dc36be479b13ba454f691348ddf428f185/httpx-0.28.0-py3-none-any.whl (73 kB)
Collecting importlib-resources<7.0,>=1.3 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e1/6a/4604f9ae2fa62ef47b9de2fa5ad599589d28c9fd1d335f32759813dfa91e/importlib_resources-6.4.5-py3-none-any.whl (36 kB)
Requirement already satisfied: jinja2<4.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from gradio==3.41.2) (3.1.4)
Collecting markupsafe~=2.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/5f/5a/360da85076688755ea0cceb92472923086993e86b5613bbae9fbc14136b0/MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)
Collecting matplotlib~=3.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/cc/16/6bbd5e5fe2c120bfcbbafb83cb461f1d8e942df1ecc0fbfcbe418076c3c9/matplotlib-3.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 8.3/8.3 MB 8.5 MB/s eta 0:00:000:00:01
Collecting orjson~=3.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/6f/1f/c8fc64b25e2e4a5fa0fb514a0325719e99461c088a3b659954a57b8c1f3c/orjson-3.10.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (131 kB)
Collecting pandas<3.0,>=1.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/3d/dd/bed19c2974296661493d7acc4407b1d2db4e2a482197df100f8f965b6225/pandas-2.2.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 13.1/13.1 MB 59.8 MB/s eta 0:00:0000:01
Collecting Pillow (from diffusers==0.30.0)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/32/3f/c02268d0c6fb6b3958bdda673c17b315c821d97df29ae6969f20fb49388a/pillow-10.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.4/4.4 MB 93.1 MB/s eta 0:00:00
Collecting pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d5/74/da832196702d0c56eb86b75bfa346db9238617e29b0b7ee3b8b4eccfe654/pydantic-2.10.2-py3-none-any.whl (456 kB)
Collecting pydub (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl (32 kB)
Collecting python-multipart (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e1/f4/ddd0fcdc454cf3870153ae16a818256523d31c3c8136e216bc6836ed4cd1/python_multipart-0.0.19-py3-none-any.whl (24 kB)
Collecting semantic-version~=2.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/6a/23/8146aad7d88f4fcb3a6218f41a60f6c2d4e3a72de72da1825dc7c8f7877c/semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)
Requirement already satisfied: typing-extensions~=4.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from gradio==3.41.2) (4.12.2)
Collecting uvicorn>=0.14.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/50/c1/2d27b0a15826c2b71dcf6e2f5402181ef85acf439617bb2f1453125ce1f3/uvicorn-0.32.1-py3-none-any.whl (63 kB)
Collecting websockets<12.0,>=10.0 (from gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a6/9c/2356ecb952fd3992b73f7a897d65e57d784a69b94bb8d8fd5f97531e5c02/websockets-11.0.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)
Collecting scipy (from controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/35/f5/d0ad1a96f80962ba65e2ce1de6a1e59edecd1f0a7b55990ed208848012e0/scipy-1.13.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 38.6/38.6 MB 175.1 MB/s eta 0:00:0000:01
Collecting opencv-python-headless (from controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d1/09/248f86a404567303cdf120e4a301f389b68e3b18e5c0cc428de327da609c/opencv_python_headless-4.10.0.84-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (49.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 49.9/49.9 MB 192.0 MB/s eta 0:00:0000:01
Collecting einops (from controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/44/5a/f0b9ad6c0a9017e62d4735daaeb11ba3b6c009d69a26141b258cd37b5588/einops-0.8.0-py3-none-any.whl (43 kB)
Requirement already satisfied: torchvision in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from controlnet-aux==0.0.9) (0.15.2)
Collecting timm<=0.6.7 (from controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/72/ed/358a8bc5685c31c0fe7765351b202cf6a8c087893b5d2d64f63c950f8beb/timm-0.6.7-py3-none-any.whl (509 kB)
Collecting scikit-image (from controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f0/cc/1a58efefb9b17c60d15626b33416728003028d5d51f0521482151a222560/scikit_image-0.24.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (14.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.9/14.9 MB 133.5 MB/s eta 0:00:00
Collecting absl-py (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a2/ad/e0d3c824784ff121c03cc031f944bc7e139a8f1870ffd2845cc2dd76f6c4/absl_py-2.1.0-py3-none-any.whl (133 kB)
Collecting attrs>=19.1.0 (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/6a/21/5b6702a7f963e95456c0de2d495f67bf5fd62840ac655dc451586d23d39a/attrs-24.2.0-py3-none-any.whl (63 kB)
Collecting flatbuffers>=2.0 (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/41/f0/7e988a019bc54b2dbd0ad4182ef2d53488bb02e58694cd79d61369e85900/flatbuffers-24.3.25-py2.py3-none-any.whl (26 kB)
Collecting jax (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fd/f2/9dbb75de3058acfd1600cf0839bcce7ea391148c9d2b4fa5f5666e66f09e/jax-0.4.30-py3-none-any.whl (2.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.0/2.0 MB 62.2 MB/s eta 0:00:00
Collecting jaxlib (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/07/3b/a596036325666624ca084df554636fb3777e78e9386b52476d96fa14394e/jaxlib-0.4.30-cp39-cp39-manylinux2014_x86_64.whl (79.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 79.6/79.6 MB 44.2 MB/s eta 0:00:0000:0100:01
Collecting opencv-contrib-python (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b0/e0/8f5d065ebb2e5941d289c5f653f944318f9e418bc5167bc6a346ab5e0f6a/opencv_contrib_python-4.10.0.84-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (68.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 68.7/68.7 MB 197.1 MB/s eta 0:00:00a 0:00:01
Collecting protobuf<5,>=4.25.3 (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/05/a6/094a2640be576d760baa34c902dcb8199d89bce9ed7dd7a6af74dcbbd62d/protobuf-4.25.5-cp37-abi3-manylinux2014_x86_64.whl (294 kB)
Collecting sounddevice>=0.4.4 (from mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/06/d1/464b5fca3decdd0cfec8c47f7b4161a0b12972453201c1bf03811f367c5e/sounddevice-0.5.1-py3-none-any.whl (32 kB)
Collecting fsspec (from gradio-client==0.5.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/c6/b2/454d6e7f0158951d8a78c2e1eb4f69ae81beb8dca5fee9809c6c99e9d0d0/fsspec-2024.10.0-py3-none-any.whl (179 kB)
Requirement already satisfied: sympy in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (1.13.3)
Requirement already satisfied: networkx in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (3.2.1)
Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.7.99)
Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.7.99)
Requirement already satisfied: nvidia-cuda-cupti-cu11==11.7.101 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.7.101)
Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (8.5.0.96)
Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.10.3.66)
Requirement already satisfied: nvidia-cufft-cu11==10.9.0.58 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (10.9.0.58)
Requirement already satisfied: nvidia-curand-cu11==10.2.10.91 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (10.2.10.91)
Requirement already satisfied: nvidia-cusolver-cu11==11.4.0.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.4.0.1)
Requirement already satisfied: nvidia-cusparse-cu11==11.7.4.91 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.7.4.91)
Requirement already satisfied: nvidia-nccl-cu11==2.14.3 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (2.14.3)
Requirement already satisfied: nvidia-nvtx-cu11==11.7.91 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (11.7.91)
Requirement already satisfied: triton==2.0.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from torch>=1.10.0->accelerate==0.33.0) (2.0.0)
Requirement already satisfied: setuptools in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.10.0->accelerate==0.33.0) (75.1.0)
Requirement already satisfied: wheel in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.10.0->accelerate==0.33.0) (0.44.0)
Requirement already satisfied: cmake in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from triton==2.0.0->torch>=1.10.0->accelerate==0.33.0) (3.31.1)
Requirement already satisfied: lit in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from triton==2.0.0->torch>=1.10.0->accelerate==0.33.0) (18.1.8)
Collecting jsonschema>=3.0 (from altair<6.0,>=4.2.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/69/4a/4f9dbeb84e8850557c02365a0eee0649abe5eb1d84af92a25731c6c0f922/jsonschema-4.23.0-py3-none-any.whl (88 kB)
Collecting narwhals>=1.14.2 (from altair<6.0,>=4.2.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b0/5e/7cc8d864b4a9d00aaffdb708c420f74f50b46f9b5a806ec7b109143aa6fe/narwhals-1.15.1-py3-none-any.whl (232 kB)
Requirement already satisfied: zipp>=3.1.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from importlib-resources<7.0,>=1.3->gradio==3.41.2) (3.21.0)
Collecting contourpy>=1.0.1 (from matplotlib~=3.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/05/11/57335544a3027e9b96a05948c32e566328e3a2f84b7b99a325b7a06d2b06/contourpy-1.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (321 kB)
Collecting cycler>=0.10 (from matplotlib~=3.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e7/05/c19819d5e3d95294a6f5947fb9b9629efb316b96de511b418c53d245aae6/cycler-0.12.1-py3-none-any.whl (8.3 kB)
Collecting fonttools>=4.22.0 (from matplotlib~=3.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/1d/3e/0841e7bf38ad317c960992dd03bac041899a1c21396013e6ddcfd2bc48c5/fonttools-4.55.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.6/4.6 MB 41.9 MB/s eta 0:00:00
Collecting kiwisolver>=1.3.1 (from matplotlib~=3.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/21/b1/40655f6c3fa11ce740e8a964fa8e4c0479c87d6a7944b95af799c7a55dfe/kiwisolver-1.4.7-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 27.3 MB/s eta 0:00:00
Collecting pyparsing>=2.3.1 (from matplotlib~=3.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/be/ec/2eb3cd785efd67806c46c13a17339708ddc346cbb684eade7a6e6f79536a/pyparsing-3.2.0-py3-none-any.whl (106 kB)
Requirement already satisfied: python-dateutil>=2.7 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from matplotlib~=3.0->gradio==3.41.2) (2.9.0.post0)
Collecting pytz>=2020.1 (from pandas<3.0,>=1.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/11/c3/005fcca25ce078d2cc29fd559379817424e94885510568bc1bc53d7d5846/pytz-2024.2-py2.py3-none-any.whl (508 kB)
Collecting tzdata>=2022.7 (from pandas<3.0,>=1.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a6/ab/7e5f53c3b9d14972843a647d8d7a853969a58aecc7559cb3267302c94774/tzdata-2024.2-py2.py3-none-any.whl (346 kB)
Collecting annotated-types>=0.6.0 (from pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl (13 kB)
Collecting pydantic-core==2.27.1 (from pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/85/d7/936846087424c882d89c853711687230cd60179a67c79c34c99b64f92625/pydantic_core-2.27.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.1/2.1 MB 26.2 MB/s eta 0:00:00
Requirement already satisfied: charset-normalizer<4,>=2 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from requests->diffusers==0.30.0) (3.4.0)
Requirement already satisfied: idna<4,>=2.5 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from requests->diffusers==0.30.0) (3.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from requests->diffusers==0.30.0) (2.2.3)
Requirement already satisfied: certifi>=2017.4.17 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from requests->diffusers==0.30.0) (2024.8.30)
Collecting CFFI>=1.0 (from sounddevice>=0.4.4->mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/bd/62/a1f468e5708a70b1d86ead5bab5520861d9c7eacce4a885ded9faa7729c3/cffi-1.17.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (445 kB)
Collecting click>=7.0 (from uvicorn>=0.14.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/00/2e/d53fa4befbf2cfa713304affc7ca780ce4fc1fd8710527771b58311a3229/click-8.1.7-py3-none-any.whl (97 kB)
Collecting h11>=0.8 (from uvicorn>=0.14.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/95/04/ff642e65ad6b90db43e668d70ffb6736436c7ce41fcc549f4e9472234127/h11-0.14.0-py3-none-any.whl (58 kB)
Collecting starlette<0.42.0,>=0.40.0 (from fastapi->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/96/00/2b325970b3060c7cecebab6d295afe763365822b1306a12eeab198f74323/starlette-0.41.3-py3-none-any.whl (73 kB)
Collecting anyio (from httpx->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e4/f5/f2b75d2fc6f1a260f340f0e7c6a060f4dd2961cc16884ed851b0d18da06a/anyio-4.6.2.post1-py3-none-any.whl (90 kB)
Collecting httpcore==1.* (from httpx->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/87/f5/72347bc88306acb359581ac4d52f23c0ef445b57157adedb9aee0cd689d2/httpcore-1.0.7-py3-none-any.whl (78 kB)
Collecting ml-dtypes>=0.2.0 (from jax->mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a8/6f/49effaafbc24c7665bcea42cacb22e7198bbab5b473d908c5900c6bb6a59/ml_dtypes-0.5.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.5/4.5 MB 36.6 MB/s eta 0:00:00
Collecting opt-einsum (from jax->mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/23/cd/066e86230ae37ed0be70aae89aabf03ca8d9f39c8aea0dec8029455b5540/opt_einsum-3.4.0-py3-none-any.whl (71 kB)
Collecting imageio>=2.33 (from scikit-image->controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/5c/f9/f78e7f5ac8077c481bf6b43b8bc736605363034b3d5eb3ce8eb79f53f5f1/imageio-2.36.1-py3-none-any.whl (315 kB)
Collecting tifffile>=2022.8.12 (from scikit-image->controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/3a/4f/73714b1c1d339b1545cac28764e39f88c69468b5e10e51f327f9aa9d55b9/tifffile-2024.8.30-py3-none-any.whl (227 kB)
Collecting lazy-loader>=0.4 (from scikit-image->controlnet-aux==0.0.9)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/83/60/d497a310bde3f01cb805196ac61b7ad6dc5dcf8dce66634dc34364b20b4f/lazy_loader-0.4-py3-none-any.whl (12 kB)
Collecting pycparser (from CFFI>=1.0->sounddevice>=0.4.4->mediapipe==0.10.14)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/13/a3/a812df4e2dd5696d1f351d58b8fe16a405b234ad2886a0dab9183fb78109/pycparser-2.22-py3-none-any.whl (117 kB)
Collecting jsonschema-specifications>=2023.03.6 (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d1/0f/8910b19ac0670a0f80ce1008e5e751c4a57e14d2c4c13a482aa6079fa9d6/jsonschema_specifications-2024.10.1-py3-none-any.whl (18 kB)
Collecting referencing>=0.28.4 (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b7/59/2056f61236782a2c86b33906c025d4f4a0b17be0161b63b70fd9e8775d36/referencing-0.35.1-py3-none-any.whl (26 kB)
Collecting rpds-py>=0.7.1 (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/3f/7e/fbf8a0a4beeca1adccf79b7e26e752c643cf32e9303f523d77d14ce0ba56/rpds_py-0.22.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (382 kB)
Requirement already satisfied: six>=1.5 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio==3.41.2) (1.16.0)
Collecting sniffio>=1.1 (from anyio->httpx->gradio==3.41.2)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl (10 kB)
Requirement already satisfied: exceptiongroup>=1.0.2 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from anyio->httpx->gradio==3.41.2) (1.2.2)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from sympy->torch>=1.10.0->accelerate==0.33.0) (1.3.0)
Installing collected packages: sentencepiece, pytz, pydub, flatbuffers, websockets, tzdata, tqdm, sniffio, semantic-version, safetensors, rpds-py, regex, pyyaml, python-multipart, pyparsing, pydantic-core, pycparser, protobuf, Pillow, orjson, opt-einsum, numpy, narwhals, markupsafe, lazy-loader, kiwisolver, importlib-resources, h11, fsspec, fonttools, ffmpy, einops, cycler, click, attrs, annotated-types, aiofiles, absl-py, uvicorn, tifffile, scipy, referencing, pydantic, pandas, opencv-python-headless, opencv-contrib-python, ml-dtypes, imageio, huggingface-hub, httpcore, contourpy, CFFI, anyio, tokenizers, starlette, sounddevice, scikit-image, matplotlib, jsonschema-specifications, jaxlib, httpx, diffusers, transformers, jsonschema, jax, gradio-client, fastapi, mediapipe, altair, gradio, timm, accelerate, xformers, peft, controlnet-aux
  Attempting uninstall: Pillow
    Found existing installation: pillow 11.0.0
    Uninstalling pillow-11.0.0:
      Successfully uninstalled pillow-11.0.0
  Attempting uninstall: numpy
    Found existing installation: numpy 2.0.2
    Uninstalling numpy-2.0.2:
      Successfully uninstalled numpy-2.0.2
  Attempting uninstall: markupsafe
    Found existing installation: MarkupSafe 3.0.2
    Uninstalling MarkupSafe-3.0.2:
      Successfully uninstalled MarkupSafe-3.0.2
Successfully installed CFFI-1.17.1 Pillow-10.4.0 absl-py-2.1.0 accelerate-0.33.0 aiofiles-23.2.1 altair-5.5.0 annotated-types-0.7.0 anyio-4.6.2.post1 attrs-24.2.0 click-8.1.7 contourpy-1.3.0 controlnet-aux-0.0.9 cycler-0.12.1 diffusers-0.30.0 einops-0.8.0 fastapi-0.115.5 ffmpy-0.4.0 flatbuffers-24.3.25 fonttools-4.55.0 fsspec-2024.10.0 gradio-3.41.2 gradio-client-0.5.0 h11-0.14.0 httpcore-1.0.7 httpx-0.28.0 huggingface-hub-0.26.3 imageio-2.36.1 importlib-resources-6.4.5 jax-0.4.30 jaxlib-0.4.30 jsonschema-4.23.0 jsonschema-specifications-2024.10.1 kiwisolver-1.4.7 lazy-loader-0.4 markupsafe-2.1.5 matplotlib-3.9.3 mediapipe-0.10.14 ml-dtypes-0.5.0 narwhals-1.15.1 numpy-1.26.4 opencv-contrib-python-4.10.0.84 opencv-python-headless-4.10.0.84 opt-einsum-3.4.0 orjson-3.10.12 pandas-2.2.3 peft-0.12.0 protobuf-4.25.5 pycparser-2.22 pydantic-2.10.2 pydantic-core-2.27.1 pydub-0.25.1 pyparsing-3.2.0 python-multipart-0.0.19 pytz-2024.2 pyyaml-6.0.2 referencing-0.35.1 regex-2024.11.6 rpds-py-0.22.0 safetensors-0.4.2 scikit-image-0.24.0 scipy-1.13.1 semantic-version-2.10.0 sentencepiece-0.2.0 sniffio-1.3.1 sounddevice-0.5.1 starlette-0.41.3 tifffile-2024.8.30 timm-0.6.7 tokenizers-0.19.1 tqdm-4.67.1 transformers-4.44.0 tzdata-2024.2 uvicorn-0.32.1 websockets-11.0.3 xformers-0.0.21
Looking in indexes: http://repo.myhuaweicloud.com/repository/pypi/simple
Collecting python-multipart==0.0.13
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ad/9e/865280a37d64d314fb0a33c7e6021a5cc06174c4488b277e46b8ac9cc708/python_multipart-0.0.13-py3-none-any.whl (24 kB)
Collecting ipywidgets==7.7.1
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fa/b2/4af75a543f6c3475a982e814fecd9bf13ba06210c64a6da85475a39bd16b/ipywidgets-7.7.1-py2.py3-none-any.whl (123 kB)
Requirement already satisfied: ipykernel>=4.5.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipywidgets==7.7.1) (6.29.5)
Collecting ipython-genutils~=0.2.0 (from ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fa/bc/9bd3b5c2b4774d5f33b2d544f1460be9df7df2fe42f352135381c347c69a/ipython_genutils-0.2.0-py2.py3-none-any.whl (26 kB)
Requirement already satisfied: traitlets>=4.3.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipywidgets==7.7.1) (5.14.3)
Collecting widgetsnbextension~=3.6.0 (from ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/93/1b/25d570ee8dce0f2ddadb967d6242cf6e10516db7897c7d9a6e3853b56bfc/widgetsnbextension-3.6.10-py2.py3-none-any.whl (1.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 59.4 MB/s eta 0:00:00
Requirement already satisfied: ipython>=4.0.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipywidgets==7.7.1) (8.18.1)
Collecting jupyterlab-widgets>=1.0.0 (from ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a9/93/858e87edc634d628e5d752ba944c2833133a28fa87bb093e6832ced36a3e/jupyterlab_widgets-3.0.13-py3-none-any.whl (214 kB)
Requirement already satisfied: comm>=0.1.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (0.2.2)
Requirement already satisfied: debugpy>=1.6.5 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (1.8.9)
Requirement already satisfied: jupyter-client>=6.1.12 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (8.6.3)
Requirement already satisfied: jupyter-core!=5.0.*,>=4.12 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (5.7.2)
Requirement already satisfied: matplotlib-inline>=0.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (0.1.7)
Requirement already satisfied: nest-asyncio in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (1.6.0)
Requirement already satisfied: packaging in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (24.2)
Requirement already satisfied: psutil in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (6.1.0)
Requirement already satisfied: pyzmq>=24 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (26.2.0)
Requirement already satisfied: tornado>=6.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipykernel>=4.5.1->ipywidgets==7.7.1) (6.4.2)
Requirement already satisfied: decorator in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (5.1.1)
Requirement already satisfied: jedi>=0.16 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (0.19.2)
Requirement already satisfied: prompt-toolkit<3.1.0,>=3.0.41 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (3.0.48)
Requirement already satisfied: pygments>=2.4.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (2.18.0)
Requirement already satisfied: stack-data in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (0.6.3)
Requirement already satisfied: typing-extensions in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (4.12.2)
Requirement already satisfied: exceptiongroup in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (1.2.2)
Requirement already satisfied: pexpect>4.3 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from ipython>=4.0.0->ipywidgets==7.7.1) (4.9.0)
Collecting notebook>=4.4.1 (from widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/46/77/53732fbf48196af9e51c2a61833471021c1d77d335d57b96ee3588c0c53d/notebook-7.2.2-py3-none-any.whl (5.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.0/5.0 MB 101.7 MB/s eta 0:00:00
Requirement already satisfied: parso<0.9.0,>=0.8.4 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets==7.7.1) (0.8.4)
Requirement already satisfied: importlib-metadata>=4.8.3 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets==7.7.1) (8.5.0)
Requirement already satisfied: python-dateutil>=2.8.2 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets==7.7.1) (2.9.0.post0)
Requirement already satisfied: platformdirs>=2.5 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyter-core!=5.0.*,>=4.12->ipykernel>=4.5.1->ipywidgets==7.7.1) (4.3.6)
Collecting jupyter-server<3,>=2.4.0 (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/57/e1/085edea6187a127ca8ea053eb01f4e1792d778b4d192c74d32eb6730fed6/jupyter_server-2.14.2-py3-none-any.whl (383 kB)
Collecting jupyterlab-server<3,>=2.27.1 (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/54/09/2032e7d15c544a0e3cd831c51d77a8ca57f7555b2e1b2922142eddb02a84/jupyterlab_server-2.27.3-py3-none-any.whl (59 kB)
Collecting jupyterlab<4.3,>=4.2.0 (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f0/04/853abc46fef36afd4e5f9a4fd1fbc1b477f910a29bb71711b6653098b703/jupyterlab-4.2.6-py3-none-any.whl (11.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.6/11.6 MB 63.9 MB/s eta 0:00:00
Collecting notebook-shim<0.3,>=0.2 (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f9/33/bd5b9137445ea4b680023eb0469b2bb969d61303dedb2aac6560ff3d14a1/notebook_shim-0.2.4-py3-none-any.whl (13 kB)
Requirement already satisfied: ptyprocess>=0.5 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from pexpect>4.3->ipython>=4.0.0->ipywidgets==7.7.1) (0.7.0)
Requirement already satisfied: wcwidth in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from prompt-toolkit<3.1.0,>=3.0.41->ipython>=4.0.0->ipywidgets==7.7.1) (0.2.13)
Requirement already satisfied: executing>=1.2.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from stack-data->ipython>=4.0.0->ipywidgets==7.7.1) (2.1.0)
Requirement already satisfied: asttokens>=2.1.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from stack-data->ipython>=4.0.0->ipywidgets==7.7.1) (3.0.0)
Requirement already satisfied: pure-eval in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from stack-data->ipython>=4.0.0->ipywidgets==7.7.1) (0.2.3)
Requirement already satisfied: zipp>=3.20 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from importlib-metadata>=4.8.3->jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets==7.7.1) (3.21.0)
Requirement already satisfied: anyio>=3.1.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (4.6.2.post1)
Collecting argon2-cffi>=21.1 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a4/6a/e8a041599e78b6b3752da48000b14c8d1e8a04ded09c88c714ba047f34f5/argon2_cffi-23.1.0-py3-none-any.whl (15 kB)
Requirement already satisfied: jinja2>=3.0.3 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (3.1.4)
Collecting jupyter-events>=0.9.0 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a5/94/059180ea70a9a326e1815176b2370da56376da347a796f8c4f0b830208ef/jupyter_events-0.10.0-py3-none-any.whl (18 kB)
Collecting jupyter-server-terminals>=0.4.4 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/07/2d/2b32cdbe8d2a602f697a649798554e4f072115438e92249624e532e8aca6/jupyter_server_terminals-0.5.3-py3-none-any.whl (13 kB)
Collecting nbconvert>=6.4.4 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b8/bb/bb5b6a515d1584aa2fd89965b11db6632e4bdc69495a52374bcc36e56cfa/nbconvert-7.16.4-py3-none-any.whl (257 kB)
Collecting nbformat>=5.3.0 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/a9/82/0340caa499416c78e5d8f5f05947ae4bc3cba53c9f038ab6e9ed964e22f1/nbformat-5.10.4-py3-none-any.whl (78 kB)
Collecting overrides>=5.0 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/2c/ab/fc8290c6a4c722e5514d80f62b2dc4c4df1a68a41d1364e625c35990fcf3/overrides-7.7.0-py3-none-any.whl (17 kB)
Collecting prometheus-client>=0.9 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/84/2d/46ed6436849c2c88228c3111865f44311cff784b4aabcdef4ea2545dbc3d/prometheus_client-0.21.0-py3-none-any.whl (54 kB)
Collecting send2trash>=1.8.2 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/40/b0/4562db6223154aa4e22f939003cb92514c79f3d4dccca3444253fd17f902/Send2Trash-1.8.3-py3-none-any.whl (18 kB)
Collecting terminado>=0.8.3 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/6a/9e/2064975477fdc887e47ad42157e214526dcad8f317a948dee17e1659a62f/terminado-0.18.1-py3-none-any.whl (14 kB)
Collecting websocket-client>=1.7 (from jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/5a/84/44687a29792a70e111c5c477230a72c4b957d88d16141199bf9acb7537a3/websocket_client-1.8.0-py3-none-any.whl (58 kB)
Collecting async-lru>=1.0.0 (from jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fa/9f/3c3503693386c4b0f245eaf5ca6198e3b28879ca0a40bde6b0e319793453/async_lru-2.0.4-py3-none-any.whl (6.1 kB)
Requirement already satisfied: httpx>=0.25.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (0.28.0)
Collecting jupyter-lsp>=2.0.0 (from jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/07/e0/7bd7cff65594fd9936e2f9385701e44574fc7d721331ff676ce440b14100/jupyter_lsp-2.2.5-py3-none-any.whl (69 kB)
Requirement already satisfied: setuptools>=40.1.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (75.1.0)
Collecting tomli>=1.2.2 (from jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/6e/c2/61d3e0f47e2b74ef40a68b9e6ad5984f6241a942f7cd3bbfbdbd03861ea9/tomli-2.2.1-py3-none-any.whl (14 kB)
Collecting babel>=2.10 (from jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ed/20/bc79bc575ba2e2a7f70e8a1155618bb1301eaa5132a8271373a6903f73f8/babel-2.16.0-py3-none-any.whl (9.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 9.6/9.6 MB 123.0 MB/s eta 0:00:00
Collecting json5>=0.9.0 (from jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/aa/42/797895b952b682c3dafe23b1834507ee7f02f4d6299b65aaa61425763278/json5-0.10.0-py3-none-any.whl (34 kB)
Requirement already satisfied: jsonschema>=4.18.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (4.23.0)
Requirement already satisfied: requests>=2.31 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (2.32.3)
Requirement already satisfied: six>=1.5 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from python-dateutil>=2.8.2->jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets==7.7.1) (1.16.0)
Requirement already satisfied: idna>=2.8 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from anyio>=3.1.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (3.10)
Requirement already satisfied: sniffio>=1.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from anyio>=3.1.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (1.3.1)
Collecting argon2-cffi-bindings (from argon2-cffi>=21.1->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ec/f7/378254e6dd7ae6f31fe40c8649eea7d4832a42243acaf0f1fff9083b2bed/argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (86 kB)
Requirement already satisfied: certifi in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from httpx>=0.25.0->jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (2024.8.30)
Requirement already satisfied: httpcore==1.* in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from httpx>=0.25.0->jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (1.0.7)
Requirement already satisfied: h11<0.15,>=0.13 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from httpcore==1.*->httpx>=0.25.0->jupyterlab<4.3,>=4.2.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (0.14.0)
Requirement already satisfied: MarkupSafe>=2.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jinja2>=3.0.3->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (2.1.5)
Requirement already satisfied: attrs>=22.2.0 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (24.2.0)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (2024.10.1)
Requirement already satisfied: referencing>=0.28.4 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (0.35.1)
Requirement already satisfied: rpds-py>=0.7.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (0.22.0)
Collecting python-json-logger>=2.0.4 (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/35/a6/145655273568ee78a581e734cf35beb9e33a370b29c5d3c8fee3744de29f/python_json_logger-2.0.7-py3-none-any.whl (8.1 kB)
Requirement already satisfied: pyyaml>=5.3 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (6.0.2)
Collecting rfc3339-validator (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/7b/44/4e421b96b67b2daff264473f7465db72fbdf36a07e05494f50300cc7b0c6/rfc3339_validator-0.1.4-py2.py3-none-any.whl (3.5 kB)
Collecting rfc3986-validator>=0.1.1 (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/9e/51/17023c0f8f1869d8806b979a2bffa3f861f26a3f1a66b094288323fba52f/rfc3986_validator-0.1.1-py2.py3-none-any.whl (4.2 kB)
Collecting beautifulsoup4 (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b1/fe/e8c672695b37eecc5cbf43e1d0638d88d66ba3a44c4d321c796f4e59167f/beautifulsoup4-4.12.3-py3-none-any.whl (147 kB)
Collecting bleach!=5.0.0 (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/fc/55/96142937f66150805c25c4d0f31ee4132fd33497753400734f9dfdcbdc66/bleach-6.2.0-py3-none-any.whl (163 kB)
Collecting defusedxml (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/07/6c/aa3f2f849e01cb6a001cd8554a88d4c77c5c1a31c95bdf1cf9301e6d9ef4/defusedxml-0.7.1-py2.py3-none-any.whl (25 kB)
Collecting jupyterlab-pygments (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/b1/dd/ead9d8ea85bf202d90cc513b533f9c363121c7792674f78e0d8a854b63b4/jupyterlab_pygments-0.3.0-py3-none-any.whl (15 kB)
Collecting mistune<4,>=2.0.3 (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f0/74/c95adcdf032956d9ef6c89a9b8a5152bf73915f8c633f3e3d88d06bd699c/mistune-3.0.2-py3-none-any.whl (47 kB)
Collecting nbclient>=0.5.0 (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/26/1a/ed6d1299b1a00c1af4a033fdee565f533926d819e084caf0d2832f6f87c6/nbclient-0.10.1-py3-none-any.whl (25 kB)
Collecting pandocfilters>=1.4.1 (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/ef/af/4fbc8cab944db5d21b7e2a5b8e9211a03a79852b1157e2c102fcc61ac440/pandocfilters-1.5.1-py2.py3-none-any.whl (8.7 kB)
Collecting tinycss2 (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e6/34/ebdc18bae6aa14fbee1a08b63c015c72b64868ff7dae68808ab500c492e2/tinycss2-1.4.0-py3-none-any.whl (26 kB)
Collecting fastjsonschema>=2.15 (from nbformat>=5.3.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/90/2b/0817a2b257fe88725c25589d89aec060581aabf668707a8d03b2e9e0cb2a/fastjsonschema-2.21.1-py3-none-any.whl (23 kB)
Requirement already satisfied: charset-normalizer<4,>=2 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from requests>=2.31->jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (3.4.0)
Requirement already satisfied: urllib3<3,>=1.21.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from requests>=2.31->jupyterlab-server<3,>=2.27.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (2.2.3)
Collecting webencodings (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f4/24/2a3e3df732393fed8b3ebf2ec078f05546de641fe1b667ee316ec1dcf3b7/webencodings-0.5.1-py2.py3-none-any.whl (11 kB)
Collecting fqdn (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/cf/58/8acf1b3e91c58313ce5cb67df61001fc9dcd21be4fadb76c1a2d540e09ed/fqdn-1.5.1-py3-none-any.whl (9.1 kB)
Collecting isoduration (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/7b/55/e5326141505c5d5e34c5e0935d2908a74e4561eca44108fbfb9c13d2911a/isoduration-20.11.0-py3-none-any.whl (11 kB)
Collecting jsonpointer>1.13 (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/71/92/5e77f98553e9e75130c78900d000368476aed74276eb8ae8796f65f00918/jsonpointer-3.0.0-py2.py3-none-any.whl (7.6 kB)
Collecting uri-template (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/e7/00/3fca040d7cf8a32776d3d81a00c8ee7457e00f80c649f1e4a863c8321ae9/uri_template-1.3.0-py3-none-any.whl (11 kB)
Collecting webcolors>=24.6.0 (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/60/e8/c0e05e4684d13459f93d312077a9a2efbe04d59c393bc2b8802248c908d4/webcolors-24.11.1-py3-none-any.whl (14 kB)
Requirement already satisfied: cffi>=1.0.1 in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from argon2-cffi-bindings->argon2-cffi>=21.1->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (1.17.1)
Collecting soupsieve>1.2 (from beautifulsoup4->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/d1/c2/fe97d779f3ef3b15f05c94a2f1e3d21732574ed441687474db9d342a7315/soupsieve-2.6-py3-none-any.whl (36 kB)
Requirement already satisfied: pycparser in /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi>=21.1->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1) (2.22)
Collecting arrow>=0.15.0 (from isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/f8/ed/e97229a566617f2ae958a6b13e7cc0f585470eac730a73e9e82c32a3cdd2/arrow-1.3.0-py3-none-any.whl (66 kB)
Collecting types-python-dateutil>=2.8.10 (from arrow>=0.15.0->isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1)
  Downloading http://repo.myhuaweicloud.com/repository/pypi/packages/35/d6/ba5f61958f358028f2e2ba1b8e225b8e263053bd57d3a79e2d2db64c807b/types_python_dateutil-2.9.0.20241003-py3-none-any.whl (9.7 kB)
Installing collected packages: webencodings, ipython-genutils, fastjsonschema, websocket-client, webcolors, uri-template, types-python-dateutil, tomli, tinycss2, terminado, soupsieve, send2trash, rfc3986-validator, rfc3339-validator, python-multipart, python-json-logger, prometheus-client, pandocfilters, overrides, mistune, jupyterlab-widgets, jupyterlab-pygments, jsonpointer, json5, fqdn, defusedxml, bleach, babel, async-lru, jupyter-server-terminals, beautifulsoup4, arrow, argon2-cffi-bindings, isoduration, argon2-cffi, nbformat, nbclient, jupyter-events, nbconvert, jupyter-server, notebook-shim, jupyterlab-server, jupyter-lsp, jupyterlab, notebook, widgetsnbextension, ipywidgets
  Attempting uninstall: python-multipart
    Found existing installation: python-multipart 0.0.19
    Uninstalling python-multipart-0.0.19:
      Successfully uninstalled python-multipart-0.0.19
Successfully installed argon2-cffi-23.1.0 argon2-cffi-bindings-21.2.0 arrow-1.3.0 async-lru-2.0.4 babel-2.16.0 beautifulsoup4-4.12.3 bleach-6.2.0 defusedxml-0.7.1 fastjsonschema-2.21.1 fqdn-1.5.1 ipython-genutils-0.2.0 ipywidgets-7.7.1 isoduration-20.11.0 json5-0.10.0 jsonpointer-3.0.0 jupyter-events-0.10.0 jupyter-lsp-2.2.5 jupyter-server-2.14.2 jupyter-server-terminals-0.5.3 jupyterlab-4.2.6 jupyterlab-pygments-0.3.0 jupyterlab-server-2.27.3 jupyterlab-widgets-3.0.13 mistune-3.0.2 nbclient-0.10.1 nbconvert-7.16.4 nbformat-5.10.4 notebook-7.2.2 notebook-shim-0.2.4 overrides-7.7.0 pandocfilters-1.5.1 prometheus-client-0.21.0 python-json-logger-2.0.7 python-multipart-0.0.13 rfc3339-validator-0.1.4 rfc3986-validator-0.1.1 send2trash-1.8.3 soupsieve-2.6 terminado-0.18.1 tinycss2-1.4.0 tomli-2.2.1 types-python-dateutil-2.9.0.20241003 uri-template-1.3.0 webcolors-24.11.1 webencodings-0.5.1 websocket-client-1.8.0 widgetsnbextension-3.6.10

运行如下代码，将用于生成共享链接的可执行文件frpc_linux_amd64拷贝到gradio包环境下，并赋予其可执行权限

!cp ./frpc_linux_amd64 /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages/gradio/frpc_linux_amd64_v0.2
!chmod +x /home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages/gradio/frpc_linux_amd64_v0.2

步骤3 转换模型权重并推理

运行如下代码，将safetensors格式的模型权重转换为diffusers库支持的格式，出现Convert Success即表示转换成功。

!python convert_original_stable_diffusion_to_diffusers.py \
    --checkpoint_path LEOSAM_HelloWorld_SDXL_v7.0.safetensors \
    --original_config_file sd_xl_base.yaml \
    --dump_path LEOSAM_HelloWorld_SDXL_v7.0 \
    --from_safetensors \
    --to_safetensors
!echo "Convert Success!"

The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.
0it [00:00, ?it/s]
/home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
  warnings.warn(
Convert Success!

运行如下代码，将使用man.jpg和默认提示词作为条件输入，生成一张粘土风格的图片，并保存为demo.jpg在当前目录下
- 注意：此demo没有使用controlnet模型

from PIL import Image
import torch
from diffusers import StableDiffusionXLImg2ImgPipeline
import matplotlib.pyplot as plt

model_id = "LEOSAM_HelloWorld_SDXL_v7.0"
device = "cuda" if torch.cuda.is_available() else "cpu"
model_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(model_id, torch_dtype=model_dtype)
pipe = pipe.to(device)
pipe.load_lora_weights("ReminiClay_LoRA_Dim128",
                        weight_name="ReminiClay_SDXL_LoRA_Dim128.safetensors",
                        adapter_name="clay")

init_image = Image.open('man.jpg').convert("RGB")
prompt = "Clay World,best quality,masterpiece,real"
negative_prompt = "bad hand,bad anatomy,worst quality,ai generated images,low quality,average quality,bad eye"
generator = torch.Generator(device=device).manual_seed(0)

image = pipe(prompt=prompt,
             image=init_image,
             negative_prompt=negative_prompt,
             generator=generator,
             num_inference_steps=20,
             strength=0.5, guidance_scale=7,
            ).images[0]

%matplotlib inline
plt.axis("off")
plt.imshow(image)
image.save("demo.jpg")
# free GPU for running gradio_demo.py
del pipe
torch.cuda.empty_cache()

Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]

  0%|          | 0/10 [00:00<?, ?it/s]

注意：下面提供的两种交互界面，二选一运行即可。

步骤4 Gradio交互界面（优先推荐）

运行如下代码，将在当前目录生成gradio_demo.py文件。该文件主要包含五部分：①对输入图片和canny图片做预处理的函数；②给定pipeline和输入参数时的采样函数；③给定中文提示词的翻译函数；④gradio界面的交互逻辑；⑤读取模型权重、Lora模型和controlnet模型，并创建SD pipeline。

%%writefile gradio_demo.py

import random
import re
from functools import partial

import gradio as gr
import numpy as np
import torch
import transformers
from controlnet_aux import CannyDetector
from diffusers import (ControlNetModel,
                       StableDiffusionXLControlNetImg2ImgPipeline,
                       UniPCMultistepScheduler)
from PIL import Image


def preprocess_images(input_image: Image, resolution: int=512) -> Image:
    H = input_image.height
    W = input_image.width
    ratio = float(resolution) / min(H, W)
    H_resize = int(round(H * ratio / 64)) * 64
    W_resize = int(round(W * ratio / 64)) * 64
    image = input_image.resize((W_resize, H_resize), Image.LANCZOS)
    return image


@torch.inference_mode()
def sample(init_image: Image,
           prompt: str, negative_prompt: str,
           seed: int, strength: float, guidance_scale: float, num_inference_steps: int,
           lora_scale: float, controlnet_scale: float, controlnet_start: float, controlnet_end: float,
           max_seed: int, device: str, pipeline,
):
    if seed == -1:
        seed = random.randint(0, max_seed)
    generator = torch.Generator(device=device).manual_seed(seed)
    init_image = preprocess_images(init_image)
    canny_image = CannyDetector()(init_image)
    if 0.0 < lora_scale <= 1.0:
        pipeline.enable_lora()
        cross_attention_kwargs = {"scale": lora_scale}
    else:
        pipeline.disable_lora()
        cross_attention_kwargs = {}     # scale does not work, after `disable_lora`

    image = pipeline(image=init_image,
                     prompt=prompt, negative_prompt=negative_prompt,
                     control_image=canny_image,
                     controlnet_conditioning_scale=controlnet_scale,
                     control_guidance_start=controlnet_start,
                     control_guidance_end=controlnet_end,
                     generator=generator,
                     strength=strength,
                     guidance_scale=guidance_scale,
                     num_inference_steps=num_inference_steps,
                     cross_attention_kwargs=cross_attention_kwargs,
                    ).images[0]
    # torch.cuda.empty_cache()    # IMPORTANT for OOM
    return image, seed


@torch.inference_mode()
def translate_zh2en(source: str, translator):
    if not source: return ""
    regex_content = re.compile(r'([\u4e00-\u9fa5，？！。]+)(.*)')
    match_results_list = []     # [(english, chinese), (...)]
    current_source = source
    while True:
        match = regex_content.search(current_source)
        if not match:   # current_source = "" or "only_english_words"
            if current_source:
                match_results_list.append([current_source, ""])
            break
        if match.start() > 0:
            english_words = "".join(list(current_source)[:match.start()])
        else:
            english_words = ""
        match_results_list.append([english_words, match.group(1)])
        current_source = match.group(2)

    translate_results = []
    for english_words, chinese_words in match_results_list:
        if english_words != "":
            translate_results.append(english_words.strip(','))
        if chinese_words == "" or chinese_words == "，":
            continue
        target = translator(chinese_words)[0].get("translation_text")
        translate_results.append(target.rstrip("."))
    return ",".join(translate_results).rstrip(".") + "."


def gradio_demo(PIPELINE, TRANSLATOR, DEVICE: str):
    with gr.Blocks() as gui_demo:
        gr.HTML("""<h1 align="center">粘土风格图生图</h1>""")
        with gr.Accordion("帮助文档", open=False):
            gr.Markdown(
            """
            # 模型信息
            - 基础模型：LEOSAM_HelloWorld_SDXL_v7.0
            - Lora模型：ReminiClay_LoRA_Dim128
            - controlnet模型：controlnet-canny-sdxl-1.0
            # 功能说明
            - 输入图片，支持上传/摄像头拍照
            - 正/负面提示词支持中英文混用，并返回提示词的翻译结果
            - 注意：在当前英文提示词后面，直接添加中文即可，否则中英混翻不准确
            # 参数说明
            1. prompt：建议给短语而非长句，negative-prompt同理，可参考默认值
            2. negative-prompt：如果生成的图片中有您看到不想要的内容，请将其置于负提示词中
            3. seed：值为-1表示随机生成，并返回当前随机种子，方便复现结果
            4. strength：表示降噪强度，值越大生成图片与输入图片关联性越弱
            5. guidance-scale：生成的图像与提示词的紧密程度，值越大与提示词关联性越强
            6. inference-steps：扩散步数，值越大耗时越久图片越精细，反之越粗糙
            7. lora-scale：控制LoRA模型对生成图片的影响程度，值为0表示不使用Lora模型
            8. 注意：controlnet参数，controlnet-end不得小于或等于controlnet-start
            """)
        IMAGE_HEIGHT = 512
        MAX_SEED = np.iinfo(np.int32).max
        with gr.Tab("upload"):
            with gr.Row():
                init_image_upload = gr.Image(source="upload", type="pil", image_mode="RGB", height=IMAGE_HEIGHT)
                result_upload = gr.Image(label="result", show_label=True, height=IMAGE_HEIGHT)
                run_button_upload = gr.Button("生成", scale=0, size="lg")

        with gr.Tab("camera"):
            with gr.Row():
                init_image_camera = gr.Image(source="webcam", type="pil", image_mode="RGB", height=IMAGE_HEIGHT)
                result_camera = gr.Image(label="result", show_label=True, height=IMAGE_HEIGHT)
                run_button_camera = gr.Button("生成", scale=0, size="lg")

        with gr.Accordion("更多参数", open=True):
            with gr.Row():
                prompt = gr.Textbox(label="prompt", max_lines=1,
                                    value="Clay World,best quality,masterpiece,real")
                translate_button_prompt = gr.Button("翻译", scale=0, size="lg")
            with gr.Row():
                # negative_prompt reference: https://www.liblib.art/modelinfo/506c46c91b294710940bd4b183f3ecd7
                negative_prompt = gr.Textbox(label="negative prompt", max_lines=1,
                                            value="bad hand,bad anatomy,worst quality," + \
                                                "ai generated images,low quality,average quality,bad eye")
                translate_button_neg_prompt = gr.Button("翻译", scale=0, size="lg")

            with gr.Row():
                seed = gr.Slider(
                    label="seed",
                    minimum=-1, maximum=MAX_SEED, step=1, value=0,
                )
                strength = gr.Slider(
                    label="strength",
                    minimum=0.0, maximum=1.0, step=0.01, value=0.45,
                )
                guidance_scale = gr.Slider(
                    label="guidance scale",
                    minimum=0.0, maximum=10.0, step=0.1, value=7,
                )
                num_inference_steps = gr.Slider(
                    label="inference steps",
                    minimum=1, maximum=50, step=1, value=20,
                )

            with gr.Row():
                lora_scale = gr.Slider(
                    label="lora scale",
                    minimum=0.0, maximum=1.0, step=0.01, value=1.0,
                )
                controlnet_scale = gr.Slider(
                    label="controlnet scale",
                    minimum=0.01, maximum=1.0, step=0.01, value=0.5,
                )
                controlnet_start = gr.Slider(
                    label="controlnet start",
                    minimum=0.0, maximum=1.0, step=0.01, value=0.0,
                )
                controlnet_end = gr.Slider(
                    label="controlnet end",
                    minimum=0.01, maximum=1.0, step=0.01, value=0.8,
                )

        run_button_upload.click(
            fn=partial(sample, max_seed=MAX_SEED, device=DEVICE, pipeline=PIPELINE),
            inputs=[init_image_upload, prompt, negative_prompt, seed, strength, guidance_scale,
                    num_inference_steps, lora_scale, controlnet_scale, controlnet_start, controlnet_end],
            outputs=[result_upload, seed],
            queue=False
        )
        run_button_camera.click(
            fn=partial(sample, max_seed=MAX_SEED, device=DEVICE, pipeline=PIPELINE),
            inputs=[init_image_camera, prompt, negative_prompt, seed, strength, guidance_scale,
                    num_inference_steps, lora_scale, controlnet_scale, controlnet_start, controlnet_end],
            outputs=[result_camera, seed],
            queue=False
        )
        translate_button_prompt.click(fn=partial(translate_zh2en, translator=TRANSLATOR),
                                      inputs=[prompt], outputs=[prompt], queue=False)
        translate_button_neg_prompt.click(fn=partial(translate_zh2en, translator=TRANSLATOR),
                                          inputs=[negative_prompt], outputs=[negative_prompt], queue=False)
    return gui_demo


def memory_efficient_pipeline(pipeline):
    # pipeline.enable_vae_slicing()  # batch
    # pipeline.enable_vae_tiling()
    pipeline.enable_xformers_memory_efficient_attention()
    # pipeline.enable_model_cpu_offload()   # 2G, inference-slow


if __name__ == "__main__":
    DEVICE = "cuda"
    model_id = "LEOSAM_HelloWorld_SDXL_v7.0"
    PIPELINE = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
        model_id, torch_dtype=torch.float16,
        controlnet=ControlNetModel.from_pretrained(
            "controlnet-canny-sdxl-1.0", torch_dtype=torch.float16,
        )
    )
    PIPELINE.scheduler = UniPCMultistepScheduler.from_config(PIPELINE.scheduler.config)
    PIPELINE = PIPELINE.to(DEVICE)
    PIPELINE.load_lora_weights("ReminiClay_LoRA_Dim128",
                               weight_name="ReminiClay_SDXL_LoRA_Dim128.safetensors",
                               adapter_name="clay")
    memory_efficient_pipeline(PIPELINE)

    TRANSLATOR = transformers.pipeline(task="translation",
                                       model="opus-mt-zh-en", device=DEVICE)
    gradio_demo(PIPELINE, TRANSLATOR, DEVICE).launch(share=True)

Overwriting gradio_demo.py

运行如下代码，即可开启gradio的交互界面。查看输出结果，其中，“Running on public URL”后面的内容即为共享链接，可点击在电脑端运行或分享到手机端使用

❗❗❗如果链接无法打开或者GPU资源选不到，可以重启kernel并尝试候选方案，“步骤5 Jupyter Widgets交互界面”

!python gradio_demo.py

显示 output

Loading pipeline components...: 100%|█████████████| 7/7 [00:05<00:00,  1.27it/s]
Blocksparse is not available: the current GPU does not expose Tensor cores
/home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages/torch/_utils.py:776: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
  return self.fget.__get__(instance, owner)()
/home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages/transformers/models/marian/tokenization_marian.py:175: UserWarning: Recommended: pip install sacremoses.
  warnings.warn("Recommended: pip install sacremoses.")
/home/ma-user/anaconda3/envs/python-3.9.15/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
  warnings.warn(
Running on local URL:  http://127.0.0.1:7860
IMPORTANT: You are using gradio version 3.41.2, however version 4.44.1 is available, please upgrade.
--------
Running on public URL: https://4394a3dc14c0ad4b03.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)
100%|█████████████████████████████████████████████| 9/9 [00:11<00:00,  1.32s/it]
^C
Keyboard interruption in main thread... closing server.
Killing tunnel 127.0.0.1:7860 <> https://4394a3dc14c0ad4b03.gradio.live

gradio交互界面展示，可打开帮助文档查看使用说明

步骤5 Jupyter Widgets交互界面（可选）

运行如下代码，将在当前目录生成ipywidgets_demo.py文件。该文件主要包含四部分：①从gradio_demo.py导入采样、翻译、图片预处理等函数；②定义ipywidgets组件的布局；③定义生成、翻译等按钮的交互逻辑函数；④读取模型权重、Lora模型和controlnet模型，并创建SD pipeline。

%%writefile ipywidgets_demo.py

import io
import os
from functools import partial

import ipywidgets as widgets
import numpy as np
import torch
import transformers
from diffusers import (ControlNetModel,
                       StableDiffusionXLControlNetImg2ImgPipeline,
                       UniPCMultistepScheduler)
from IPython.display import display
from PIL import Image
from gradio_demo import memory_efficient_pipeline, sample, translate_zh2en

# ======================= 1. 组件布局 ======================= #
"""
    输入图像，输出图像
    输入图片路径，生成按钮，一键保存
    debug-view-output
    Prompt，翻译按钮
    Neg-Prompt，翻译按钮
    seed，strength，guidance_scale，num_inference_steps
    lora_scale，controlnet_scale，controlnet_start，controlnet_end
"""
# 1.1.定义图像相关的控件
IMAGE_HEIGHT = 512
input_image = widgets.Image(format="png", width=400)
output_image = widgets.Image(format="png", width=400)
output_image.corresponding_image = ""   # for save output image
input_img_path = widgets.Combobox(
    placeholder="输入或选择一个路径",
    options=["man.jpg", "input_image_demos/gril1.jpg", "input_image_demos/gril2.jpg"],
    description="Input Image",
    ensure_option=False,
    layout={"width": "400px"},
)

submit_button = widgets.Button(description="生成", layout={"width": "200px"})
submit_button.style.button_color = "lightgreen"
save_image_button = widgets.Button(description="一键保存", layout={"width": "200px"})
save_image_button.style.button_color = "lightpink"
image_boxes = widgets.VBox([widgets.HBox([input_image, output_image]),
                            widgets.HBox([input_img_path, submit_button, save_image_button])],
                            layout={"border": "1px solid black", "width": "800px"},
                        )
# 1.2.提示词相关的控件
def customize_box_factory(wigt, name, layout={"width": "200px"}):
    wigt.layout.width = layout["width"]
    wigt_label = widgets.Label(value=name, layout=layout)
    box = widgets.VBox([wigt_label, wigt], layout=layout)
    return box
prompt = widgets.Text(value="Clay World,best quality,masterpiece,real", placeholder="正提示词")
prompt_box = customize_box_factory(prompt, "prompt", layout={"width": "600px"})
zh2en_button_pos = widgets.Button(description="翻译", layout={"width": "200px", "height": "60px"})
zh2en_button_pos.name = "pp"
zh2en_button_pos.style.button_color = "lavender"

neg_prompt = widgets.Text(value="bad hand,bad anatomy,worst quality," + \
                                "ai generated images,low quality,average quality,bad eye",
                          placeholder="负提示词")
neg_prompt_box = customize_box_factory(neg_prompt, "negative prompt", layout={"width": "600px"})
zh2en_button_neg = widgets.Button(description="翻译", layout={"width": "200px", "height": "60px"})
zh2en_button_neg.name = "np"
zh2en_button_neg.style.button_color = "lavender"

prompt_boxes = widgets.VBox([widgets.HBox([prompt_box, zh2en_button_pos]),
                             widgets.HBox([neg_prompt_box, zh2en_button_neg])],
                             layout={"border": "1px solid black", "width": "800px"},
                        )
# 1.3.参数配置相关的控件
MAX_SEED = np.iinfo(np.int32).max
seed = widgets.IntSlider(value=0, min=-1, max=MAX_SEED, step=1)
strength = widgets.FloatSlider(value=0.45, min=0.0, max=1.0, step=0.01)
guidance_scale = widgets.FloatSlider(value=7, min=0.0, max=10.0, step=0.1)
num_inference_steps = widgets.IntSlider(value=20, min=1, max=50, step=1)
lora_scale = widgets.FloatSlider(value=1.0, min=0.0, max=1.0, step=0.01)
controlnet_scale = widgets.FloatSlider(value=0.5, min=0.01, max=1.0, step=0.01)
controlnet_start = widgets.FloatSlider(value=0.0, min=0.0, max=1.0, step=0.01)
controlnet_end = widgets.FloatSlider(value=0.8, min=0.01, max=1.0, step=0.01)

seed_box = customize_box_factory(seed, name="seed")
strength_box = customize_box_factory(strength, name="strength")
guidance_scale_box = customize_box_factory(guidance_scale, "guidance scale")
num_inference_steps_box = customize_box_factory(num_inference_steps, "inference steps")
lora_scale_box = customize_box_factory(lora_scale, "lora scale")
controlnet_scale_box = customize_box_factory(controlnet_scale, "controlnet scale")
controlnet_start_box = customize_box_factory(controlnet_start, "controlnet start")
controlnet_end_box = customize_box_factory(controlnet_end, "controlnet end")
config_boxes = widgets.VBox([widgets.HBox([seed_box, strength_box,
                                           guidance_scale_box, num_inference_steps_box]),
                             widgets.HBox([lora_scale_box, controlnet_scale_box,
                                           controlnet_start_box, controlnet_end_box])],
                             layout={"border": "1px solid black", "width": "800px"},
                        )
# 1.4.输出日志展示
debug_view = widgets.Output(layout={"border": "1px solid black", "width": "800px"},)
display(widgets.VBox([image_boxes, debug_view, prompt_boxes, config_boxes]))
# ======================= 2. 交互逻辑 ======================= #
@debug_view.capture(clear_output=True)
def input_img_refresh(event):
    image_path = event.owner.value      # event.owner -> input_img_path
    if os.path.exists(image_path) and os.path.isfile(image_path):
        file = open(image_path, "rb")
        input_image.value = file.read()
    else:
        input_image.value = b""
        print("\033[31m无效的图片路径或文件不存在！\033[0m")
input_img_path.observe(input_img_refresh)

@debug_view.capture(clear_output=True)
def submit_button_callback_fn(event, pipeline, device):
    print("\033[31m图片生成中...\033[0m")
    output_image.value = b""
    init_image = Image.open(io.BytesIO(input_image.value), formats=["png", "jpeg"]).convert("RGB")
    out_image, out_seed = sample(
                    init_image=init_image,
                    prompt=prompt.value,
                    negative_prompt=neg_prompt.value,
                    seed=seed.value, strength=strength.value,
                    guidance_scale=guidance_scale.value,
                    num_inference_steps=num_inference_steps.value,
                    lora_scale=lora_scale.value,
                    controlnet_scale=controlnet_scale.value,
                    controlnet_start=controlnet_start.value,
                    controlnet_end=controlnet_end.value,
                    max_seed=MAX_SEED,
                    device=device,
                    pipeline=pipeline,
                )
    with io.BytesIO() as buffer:
        out_image.save(buffer, format="png")
        output_image.value = buffer.getvalue()
        output_image.corresponding_image = os.path.basename(input_img_path.value)
    if seed.value == -1:
        print(f"\033[31m注意: 当前随机种子为{out_seed}, 记得重置seed为-1！\033[0m")
    seed.value = out_seed
    print("\033[32m图片已生成，点击一键保存\033[0m")

@debug_view.capture(clear_output=True)
def translate_button_callback_fn(event, translator):
    if event.name == "pp":
        result_text = translate_zh2en(prompt.value, translator)
        prompt.value = result_text
    elif event.name == "np":
        result_text = translate_zh2en(neg_prompt.value, translator)
        neg_prompt.value = result_text
    else:
        print(event.name)

@debug_view.capture(clear_output=True)
def save_button_callback_fn(event):
    os.makedirs("output_image_demos", exist_ok=True)
    out_image = Image.open(io.BytesIO(output_image.value))
    out_image_file = f"output_image_demos/{output_image.corresponding_image}"
    out_image.save(out_image_file, format="png")
    print("\033[32m图片保存成功，请查看目录：output_image_demos\033[0m")


if __name__ == "__main__":
    if torch.cuda.is_available():
        DEVICE = "cuda"
        MODEL_LOAD_DTYPE = torch.float16
    else:
        DEVICE = "cpu"
        MODEL_LOAD_DTYPE = torch.float32
        print("\033[31mWarning: GPU unavailable, run inference on CPU!\033[0m")
    model_id = "LEOSAM_HelloWorld_SDXL_v7.0"
    PIPELINE = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
        model_id, torch_dtype=MODEL_LOAD_DTYPE,
        controlnet=ControlNetModel.from_pretrained(
            "controlnet-canny-sdxl-1.0", torch_dtype=MODEL_LOAD_DTYPE)
    )
    PIPELINE.scheduler = UniPCMultistepScheduler.from_config(PIPELINE.scheduler.config)
    PIPELINE = PIPELINE.to(DEVICE)
    PIPELINE.load_lora_weights("ReminiClay_LoRA_Dim128",
                            weight_name="ReminiClay_SDXL_LoRA_Dim128.safetensors",
                            adapter_name="clay")
    if torch.cuda.is_available():
        memory_efficient_pipeline(PIPELINE)
    TRANSLATOR = transformers.pipeline(task="translation",
                                       model="opus-mt-zh-en", device=DEVICE)
    # ======================= 按钮交互逻辑 ======================= #
    submit_button.on_click(partial(submit_button_callback_fn, pipeline=PIPELINE, device=DEVICE))
    zh2en_button_pos.on_click(partial(translate_button_callback_fn, translator=TRANSLATOR))
    zh2en_button_neg.on_click(partial(translate_button_callback_fn, translator=TRANSLATOR))
    save_image_button.on_click(save_button_callback_fn)

Writing ipywidgets_demo.py

运行如下代码，即可开启Jupyter Widgets的交互界面，尽管它兼容CPU和GPU规格，仍然推荐使用GPU来获得更好的体验。
❗❗❗在输出栏里修改参数即可，不需要反复运行cell或修改cell中内容，如出现报错可以尝试重启kernel

%run ipywidgets_demo.py

Jupyter Widgets交互界面展示，使用方法与gradio界面基本一致

🧨使用示例参考🧨

粘土风格生成提示

	相关参数	描述
LoRA模型	`lora scale`	使得生成的人物更贴近粘土风格
ControlNet模型	`controlnet scale`	使得生成的人物衣物、动作更贴合输入图片
基础模型	`strength`	值越接近1，生成的人物更贴合提示词，而远离输入图片
正/负提示词	`prompt`、`negative_prompt`	推荐使用英文提示词，推荐使用短语而非长句
随机种子	`seed`	当生成图片不符合预期可以调整参数或改变随机种子

❗❗❗ 推荐使用默认参数直接生成，不符合预期可以优先改变随机种子，然后再调整参数

❗❗❗ 下面我们将以三张不同的输入图片为例，展示如何使用粘土风格生成，并分别给出原图（左）、默认参数下（中）和修改参数后（右）的生成图片对比。

示例一

输入一个粘土风格的人物照片，帅气男孩。，点击翻译，得到提示词翻译结果A clay-style photo of people, handsome boy.，点击生成。
注意：可以在英文提示词基础上，追加中文提示词，再点击翻译。

原图

默认参数

修改参数后

示例二

在英文提示词基础上，追加提示词粘土风格的美女，点击翻译，得到提示词翻译结果Clay World,best quality,masterpiece,real,It's a clay-like beauty.。并调整controlnet scale值为0.8，点击生成。

原图

默认参数

修改参数后

可以看到，在增强ControlNet作用后，衣服纹理与原图更接近且额头没有多余的头发。

示例三

在默认参数下，生成的人物牙齿有点异常且眼睛是蓝色，如果这时我不希望人物是蓝色眼睛，该怎么解决呢？把“蓝色眼睛”加入负提示词！！
在负提示词后追加坏牙和蓝色的眼睛，点击翻译，得到提示词翻译结果bad hand,bad anatomy,worst quality,ai generated images,low quality,average quality,Bad teeth and blue eyes.，点击生成。

原图

默认参数

修改参数后

可以看到，生成的人物更自然且眼睛不再是蓝色

😉按照示例修改参数，定制你的粘土风照片吧😉

> 模型版权声明： > > HelloWorld系列模型（以下简称“本模型”）是由我（以下简称“所有者”）在LiblibAI平台支持下开发，并在LiblibAI平台上独家首发的XL大模型。除LiblibAI平台和Civitai平台外，任何个人或实体在其他平台所发布本模型均未经所有者授权。 > > 所有者授权个人或机构可免费使用本模型所生成的图像用于非商业性质的教育或信息传播目的，并且： > > - 遵守相关法律规定，不侵犯本模型或任何第三方的合法权益。 > > - 在使用图像时需注明图像来源为“由LEOSAM's HelloWorld大模型生成”。 > > 对于商业目的的使用，必须先与所有者签署商用授权协议。有关商业授权和模型定制事宜，请通过所有者在LiblibAI平台的主页信息联系。 > > SDXL模型的训练和开源分享是一项耗时耗力、具有挑战性的工作。所有者将持续为个人玩家免费提供HelloWorld模型的更新，以此表达对社区开源贡献者的支持和感谢。商业用户的有偿合作是推动本模型开发和持续改进的重要动力。感谢每一位用户的理解与支持。 >

请注意，任何未经授权的使用行为都可能违反相关法律规定，并可能承担法律责任。本声明的最终解释权归所有者所有，并受中华人民共和国相关法律法规的约束。