• Home
  • Categories
  • WIKI
  • LANGUAGE: en
    • [ Content contribution] R7 7840HS 780m核显成功运行Stable Diffusion生成图片
    Technology Exchange 4878 views · 23 replies ·
    Tofloor
    poster avatar
    neko
    deepin
    Ecological co-builder
    2024-05-13 18:09
    Author

    先看效果图
    截图_deepin-terminal_20240513174539.png

    image.png

    搭建教程：

    一、安装AMDGPU 驱动

    参考之前的帖子：https://bbs.deepin.org.cn/post/271384

    二、安装pyenv并创建python3.10.6环境

    参考之前的帖子：https://bbs.deepin.org.cn/post/267350

    三、安装Stable Diffusion和配置环境

    • 前置
      image.png 
      pyenv global 3.10.6 #切换到python3.10.6 环境
    • 下载Stable Diffusion 
      git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui && cd stable-diffusion-webui
    • 配置环境 
      #配置PIP清华源
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple

pip install wheel

pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/rocm5.7

#设置环境变量使其能够正常工作，根据不同显卡型号设置版本780m可以用11.0.0,要在SD启动前设置。

export HSA_OVERRIDE_GFX_VERSION=11.0.0

#启动Stable Diffusion
#启动的同时会自动安装依赖和sd模型，由于模型在国外网站下载会比较慢，建议代理加速
python launch.py --precision full --no-half

#PS:
#建议先在BIOS修改APU显存大小我的已经改成了16G显存，不然可能因为内存不够启动不了
#启动成功后会弹出浏览器到webui页面，现在快试试生成你的第一张AI图吧！
    Reply Favorite View the author
    All Replies
    1 / 2
    To page
    流浪的加菲
    deepin
    2024-05-13 18:35
    #1

    珍惜SD吧，创始团队陆陆续续都走了，传闻可能要被收购了😂

    难道曾经的王者Stable Diffusion要走向末路了吗？－论坛－深度科技 (deepin.org)

    Reply View the author
    192******85
    deepin
    2024-05-14 23:36
    #2

    牛😧

    Reply View the author
    192******85
    deepin
    2024-05-14 23:50
    #3

    rocm-windows也支持gfx1100,1101,1102,有办法让780m能在windows上用rocm麻,

    仿照上面貌似没有用

    @echo off
    SET HSA_OVERRIDE_GFX_VERSION=11.0.0
    start "" "C:\Users\M1175\AppData\Local\LM-Studio\LM Studio.exe"

    Reply View the author
    neko
    deepin
    Ecological co-builder
    2024-05-15 11:14
    #4
    192******85：

    rocm-windows也支持gfx1100,1101,1102,有办法让780m能在windows上用rocm麻,

    仿照上面貌似没有用

    @echo off
    SET HSA_OVERRIDE_GFX_VERSION=11.0.0
    start "" "C:\Users\M1175\AppData\Local\LM-Studio\LM Studio.exe"

    Reply View the author
    192******85
    deepin
    2024-05-15 21:40
    #5
    neko：

    按issue里的替换library和rocblas也没成功，不过在ollama上面使用rocm成功了。linux那边没想到rocm要占用30个G，安装直接把系统整崩溃了😭

    Reply View the author
    neko
    deepin
    Ecological co-builder
    2024-05-15 22:30
    #6
    192******85：

    按issue里的替换library和rocblas也没成功，不过在ollama上面使用rocm成功了。linux那边没想到rocm要占用30个G，安装直接把系统整崩溃了😭

    确实，之前我参考amd文档里用docker.好家伙装完吃掉我67GB的硬盘

    Reply View the author
    caoyuUU
    deepin
    2024-05-27 21:57
    #7

    ERROR:bitsandbytes.cextension:Could not load bitsandbytes native library: 'NoneType' object has no attribute 'split'
    Traceback (most recent call last):
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cextension.py", line 109, in
    lib = get_native_library()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cextension.py", line 88, in get_native_library
    cuda_specs = get_cuda_specs()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 39, in get_cuda_specs
    cuda_version_string=(get_cuda_version_string()),
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 29, in get_cuda_version_string
    major, minor = get_cuda_version_tuple()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 24, in get_cuda_version_tuple
    major, minor = map(int, torch.version.cuda.split("."))
    AttributeError: 'NoneType' object has no attribute 'split'
    WARNING:bitsandbytes.cextension:
    CUDA Setup failed despite CUDA being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

    2024-05-27 21:54:14.420272: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
    2024-05-27 21:54:14.422645: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
    2024-05-27 21:54:14.453005: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
    To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
    2024-05-27 21:54:15.112230: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
    no module 'xformers'. Processing without...
    no module 'xformers'. Processing without...
    No module 'xformers'. Proceeding without it.
    Traceback (most recent call last):
    File "/home/caoyuUU/stable-diffusion-webui/launch.py", line 48, in
    main()
    File "/home/caoyuUU/stable-diffusion-webui/launch.py", line 44, in main
    start()
    File "/home/caoyuUU/stable-diffusion-webui/modules/launch_utils.py", line 465, in start
    import webui
    File "/home/caoyuUU/stable-diffusion-webui/webui.py", line 13, in
    initialize.imports()
    File "/home/caoyuUU/stable-diffusion-webui/modules/initialize.py", line 39, in imports
    from modules import processing, gradio_extensons, ui # noqa: F401
    File "/home/caoyuUU/stable-diffusion-webui/modules/processing.py", line 14, in
    import cv2
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/cv2/init.py", line 181, in
    bootstrap()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/cv2/init.py", line 153, in bootstrap
    native_module = importlib.import_module("cv2")
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/importlib/init.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
    ImportError: libpng16-7379b3c3.so.16.40.0: cannot open shared object file: No such file or directory

    报这个错是啥原因？

    Reply View the author
    caoyuUU
    deepin
    2024-05-27 21:58
    #8
    caoyuUU：

    ERROR:bitsandbytes.cextension:Could not load bitsandbytes native library: 'NoneType' object has no attribute 'split'
    Traceback (most recent call last):
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cextension.py", line 109, in
    lib = get_native_library()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cextension.py", line 88, in get_native_library
    cuda_specs = get_cuda_specs()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 39, in get_cuda_specs
    cuda_version_string=(get_cuda_version_string()),
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 29, in get_cuda_version_string
    major, minor = get_cuda_version_tuple()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 24, in get_cuda_version_tuple
    major, minor = map(int, torch.version.cuda.split("."))
    AttributeError: 'NoneType' object has no attribute 'split'
    WARNING:bitsandbytes.cextension:
    CUDA Setup failed despite CUDA being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

    2024-05-27 21:54:14.420272: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
    2024-05-27 21:54:14.422645: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
    2024-05-27 21:54:14.453005: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
    To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
    2024-05-27 21:54:15.112230: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
    no module 'xformers'. Processing without...
    no module 'xformers'. Processing without...
    No module 'xformers'. Proceeding without it.
    Traceback (most recent call last):
    File "/home/caoyuUU/stable-diffusion-webui/launch.py", line 48, in
    main()
    File "/home/caoyuUU/stable-diffusion-webui/launch.py", line 44, in main
    start()
    File "/home/caoyuUU/stable-diffusion-webui/modules/launch_utils.py", line 465, in start
    import webui
    File "/home/caoyuUU/stable-diffusion-webui/webui.py", line 13, in
    initialize.imports()
    File "/home/caoyuUU/stable-diffusion-webui/modules/initialize.py", line 39, in imports
    from modules import processing, gradio_extensons, ui # noqa: F401
    File "/home/caoyuUU/stable-diffusion-webui/modules/processing.py", line 14, in
    import cv2
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/cv2/init.py", line 181, in
    bootstrap()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/cv2/init.py", line 153, in bootstrap
    native_module = importlib.import_module("cv2")
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/importlib/init.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
    ImportError: libpng16-7379b3c3.so.16.40.0: cannot open shared object file: No such file or directory

    报这个错是啥原因？

    AMD 6600XT

    Reply View the author
    neko
    deepin
    Ecological co-builder
    2024-05-28 05:45
    #9
    caoyuUU：

    ERROR:bitsandbytes.cextension:Could not load bitsandbytes native library: 'NoneType' object has no attribute 'split'
    Traceback (most recent call last):
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cextension.py", line 109, in
    lib = get_native_library()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cextension.py", line 88, in get_native_library
    cuda_specs = get_cuda_specs()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 39, in get_cuda_specs
    cuda_version_string=(get_cuda_version_string()),
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 29, in get_cuda_version_string
    major, minor = get_cuda_version_tuple()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/bitsandbytes/cuda_specs.py", line 24, in get_cuda_version_tuple
    major, minor = map(int, torch.version.cuda.split("."))
    AttributeError: 'NoneType' object has no attribute 'split'
    WARNING:bitsandbytes.cextension:
    CUDA Setup failed despite CUDA being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

    2024-05-27 21:54:14.420272: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
    2024-05-27 21:54:14.422645: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
    2024-05-27 21:54:14.453005: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
    To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
    2024-05-27 21:54:15.112230: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
    no module 'xformers'. Processing without...
    no module 'xformers'. Processing without...
    No module 'xformers'. Proceeding without it.
    Traceback (most recent call last):
    File "/home/caoyuUU/stable-diffusion-webui/launch.py", line 48, in
    main()
    File "/home/caoyuUU/stable-diffusion-webui/launch.py", line 44, in main
    start()
    File "/home/caoyuUU/stable-diffusion-webui/modules/launch_utils.py", line 465, in start
    import webui
    File "/home/caoyuUU/stable-diffusion-webui/webui.py", line 13, in
    initialize.imports()
    File "/home/caoyuUU/stable-diffusion-webui/modules/initialize.py", line 39, in imports
    from modules import processing, gradio_extensons, ui # noqa: F401
    File "/home/caoyuUU/stable-diffusion-webui/modules/processing.py", line 14, in
    import cv2
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/cv2/init.py", line 181, in
    bootstrap()
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/site-packages/cv2/init.py", line 153, in bootstrap
    native_module = importlib.import_module("cv2")
    File "/home/caoyuUU/.pyenv/versions/3.10.6/lib/python3.10/importlib/init.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
    ImportError: libpng16-7379b3c3.so.16.40.0: cannot open shared object file: No such file or directory

    报这个错是啥原因？

    环境没配好
    https://rocm.docs.amd.com/projects/radeon/en/latest/docs/install/install-pytorch.html
    按后面步骤检查

    Reply View the author
    caoyuUU
    deepin
    2024-05-28 19:55
    #10
    neko：

    环境没配好
    https://rocm.docs.amd.com/projects/radeon/en/latest/docs/install/install-pytorch.html
    按后面步骤检查

    谢谢老哥，可以了

    Reply View the author
    158******93
    deepin
    2024-07-02 21:04
    #11

    rocBLAS error: Cannot read /home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary.dat: Illegal seek for GPU arch : gfx1103
    List of available TensileLibrary Files :
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat"

    使用的linux，pytorch，gpu也是780m，torch.cuda.is_avaliable()显示true，但是运行就显示这个错误，环境变量我也在.bashrc里设置了

    这是为什么呀

    Reply View the author
    neko
    deepin
    Ecological co-builder
    2024-07-02 21:52
    #12
    158******93：

    rocBLAS error: Cannot read /home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary.dat: Illegal seek for GPU arch : gfx1103
    List of available TensileLibrary Files :
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat"

    使用的linux，pytorch，gpu也是780m，torch.cuda.is_avaliable()显示true，但是运行就显示这个错误，环境变量我也在.bashrc里设置了

    这是为什么呀

    export HSA_OVERRIDE_GFX_VERSION=11.0.0

    设置了这个吗，必须是11.0.0

    Reply View the author
    158******93
    deepin
    2024-07-02 22:08
    #13
    neko：

    export HSA_OVERRIDE_GFX_VERSION=11.0.0

    设置了这个吗，必须是11.0.0

    设置了，在.bashrc 文件的最后一行里添加了

    Reply View the author
    Lin🌴
    deepin
    2024-08-17 13:38
    #14

    大神，我的笔记本CPU R9-7940hs，没有独显，核显是Radeon 780M，系统Deepin V23最新稳定版本。按照你的教程操作：

    1. sudo apt install ./amdgpu-install_6.1.60103-1_all.deb
    2. python3.10.6

    驱动和ROCm按照你给链接都按照好了，也都安装成功了，rocm-smi和rocminfo输出的信息都是对的。

    image.png

    image.png

    stable diffusion依赖的包、模型都正确安装了，先 export HSA_OVERRIDE_GFX_VERSION=11.0.0，

    然后 python launch.py --precision full --no-half，执行报错如下：

    image.png

    执行 python launch.py --precision full --no-half --skip-torch-cuda-test，stable diffusion可以运行了，也能正常文本生成图像，但是使用的却是CPU，而CPU的核显并没有被调用起来。按照教程安装的rocm5.7，会不会是rocm5.7版本太低了的缘故呢？

    image.png

    我发现按照你的教程安装的pytorch：pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/rocm5.7，当然这个也可以使用CPU，而我查阅资料，发现AMD 7000系列显卡部署Stable Diffusion（Ubuntu 22.04）：https://blog.csdn.net/dr_chenseu/article/details/138233189，这篇文章使用的pytorch针对ROCm定制的，这个pytorch是CPU版本的。
    大家能帮我看看我应该如何操作才能让stable diffusion把我的CPU核显Radeon 780M调用起来呢？谢谢了！

    Reply View the author
    Lin🌴
    deepin
    2024-08-17 14:29
    #15
    158******93：

    rocBLAS error: Cannot read /home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary.dat: Illegal seek for GPU arch : gfx1103
    List of available TensileLibrary Files :
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat"
    "/home/jie/anaconda3/envs/rocm6/lib/python3.10/site-packages/torch/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat"

    使用的linux，pytorch，gpu也是780m，torch.cuda.is_avaliable()显示true，但是运行就显示这个错误，环境变量我也在.bashrc里设置了

    这是为什么呀

    我的CPU是R9-7940hs，核显也是780M，但是torch.cuda.is_avaliable()显示false，SD作画时无法调用核显。

    Reply View the author
    neko
    deepin
    Ecological co-builder
    2024-08-17 15:08
    #16
    Lin🌴：

    我的CPU是R9-7940hs，核显也是780M，但是torch.cuda.is_avaliable()显示false，SD作画时无法调用核显。

    export HSA_OVERRIDE_GFX_VERSION=11.0.0

    这个报错应该是环境变量没设置，加上这个试试。

    Reply View the author
    Lin🌴
    deepin
    2024-08-17 19:55
    #17
    192******85：

    rocm-windows也支持gfx1100,1101,1102,有办法让780m能在windows上用rocm麻,

    仿照上面貌似没有用

    @echo off
    SET HSA_OVERRIDE_GFX_VERSION=11.0.0
    start "" "C:\Users\M1175\AppData\Local\LM-Studio\LM Studio.exe"

    windows 我使用directx ML成功在R9-7940hs的核显上成功运行了stable diffusion，但是我没有尝试在windows上使用ROCm，但是我查阅了一些信息发现在windows上使用AMD的HIP实现ROCm。

    Reply View the author
    Lin🌴
    deepin
    2024-08-17 20:01
    #18
    neko：

    export HSA_OVERRIDE_GFX_VERSION=11.0.0

    这个报错应该是环境变量没设置，加上这个试试。

    image.png

    老哥，还是不行啊。

    Reply View the author
    neko
    deepin
    Ecological co-builder
    2024-08-18 07:12
    #19
    Lin🌴：

    image.png

    老哥，还是不行啊。

    玄学emm

    Reply View the author
    历史的维列斯c17
    deepin
    2024-08-30 12:00
    #20

    请问为什么需要 --no-half呢，我不加这个的确会报错，但理由是什么

    Reply View the author
    1 / 2
    To page