找回密码
 立即注册
搜索
热搜: 活动 交友 discuz
楼主: 哨箭勇度

单图换脸VisoMaster大师版v3.0版解压即用N卡整合版_250510

[复制链接]

0

主题

3

回帖

9

零食

入门显卡4G

积分
12
发表于 4 天前 | 显示全部楼层
本帖最后由 mv562676 于 2025-6-8 14:02 编辑

启动错误了 提示:
E:\AI\VisoMaster_v3.0_124_250510\env\lib\site-packages\torch\cuda\__init__.py:230: UserWarning:
NVIDIA GeForce RTX 5090 D with CUDA capability sm_120 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90.
If you want to use the NVIDIA GeForce RTX 5090 D GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

  warnings.warn(
Traceback (most recent call last):
  File "E:\AI\VisoMaster_v3.0_124_250510\main.py", line 16, in <module>
    window = main_ui.MainWindow()
  File "E:\AI\VisoMaster_v3.0_124_250510\app\ui\main_ui.py", line 224, in __init__
    self.initialize_variables()
  File "E:\AI\VisoMaster_v3.0_124_250510\app\ui\main_ui.py", line 50, in initialize_variables
    self.models_processor = ModelsProcessor(self)
  File "E:\AI\VisoMaster_v3.0_124_250510\app\processors\models_processor.py", line 98, in __init__
    self.face_editors = FaceEditors(self)
  File "E:\AI\VisoMaster_v3.0_124_250510\app\processors\face_editors.py", line 22, in __init__
    self.lp_mask_crop = faceutil.create_faded_inner_mask(size=(512, 512), border_thickness=5, fade_thickness=15, blur_radius=5, device=self.models_processor.device)
  File "E:\AI\VisoMaster_v3.0_124_250510\app\processors\utils\faceutil.py", line 1372, in create_faded_inner_mask
    mask = torch.zeros((height, width), dtype=torch.float32, device=device)  # Start with a black mask
RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

请按任意键继续. . .

我的5090D显卡不兼容,能给做个整合包一类的吗?

回复

使用道具 举报

0

主题

2

回帖

6

零食

入门显卡4G

积分
8
发表于 4 天前 | 显示全部楼层
启动提示:
Traceback (most recent call last):
  File "D:\VisoMaster_rope\VisoMaster_v3.0_124_250510\main.py", line 16, in <module>
    window = main_ui.MainWindow()
  File "D:\VisoMaster_rope\VisoMaster_v3.0_124_250510\app\ui\main_ui.py", line 224, in __init__
    self.initialize_variables()
  File "D:\VisoMaster_rope\VisoMaster_v3.0_124_250510\app\ui\main_ui.py", line 50, in initialize_variables
    self.models_processor = ModelsProcessor(self)
  File "D:\VisoMaster_rope\VisoMaster_v3.0_124_250510\app\processors\models_processor.py", line 69, in __init__
    self.syncvec = torch.empty((1, 1), dtype=torch.float32, device=self.device)
  File "D:\VisoMaster_rope\VisoMaster_v3.0_124_250510\env\lib\site-packages\torch\cuda\__init__.py", line 314, in _lazy_init
    torch._C._cuda_init()
RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
请按任意键继续. . .

这是什么原因造成的啊?花了1000食物买了不能用
回复

使用道具 举报

0

主题

1

回帖

9

零食

入门显卡4G

积分
10
发表于 3 天前 来自手机 | 显示全部楼层
非常感谢分享
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

QQ|Archiver|手机版|小黑屋|圈圈AI吧

GMT+8, 2025-6-12 20:46 , Processed in 0.104088 second(s), 19 queries .

Powered by Discuz! X3.5

© 2001-2025 Discuz! Team.

快速回复 返回顶部 返回列表