|
|
使用下面的命令运行ControlNet的pose2image功能。
```
python gradio_pose2image.py
```
等待初始化完成后，命令行将回馈一个网址，将其中的```0.0.0.0```改为```127.0.0.1```并使用浏览器打开。
--------------------------------------
这一步
出现
(control) PS C:\Users\feimiao\controlnet> python gradio_pose2image.py
logging improved.
cuda
cuda
No module 'xformers'. Proceeding without it.
ControlLDM: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Loaded model config from [./models/cldm_v15.yaml]
Traceback (most recent call last):
File "gradio_pose2image.py", line 21, in <module>
model.load_state_dict(load_state_dict('./models/control_sd15_openpose.pth', location='cuda'))
File "C:\Users\feimiao\controlnet\cldm\model.py", line 18, in load_state_dict
state_dict = get_state_dict(torch.load(ckpt_path, map_location=torch.device(location)))
File "C:\Users\feimiao\.conda\envs\control\lib\site-packages\torch\serialization.py", line 699, in load
with _open_file_like(f, 'rb') as opened_file:
File "C:\Users\feimiao\.conda\envs\control\lib\site-packages\torch\serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "C:\Users\feimiao\.conda\envs\control\lib\site-packages\torch\serialization.py", line 211, in __init__
super(_open_file, self).__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './models/control_sd15_openpose.pth'
请问是哪里有问题哈哈哈 快到最后一步了 |
|
楼主: 我輩樹である
310112100042806
发表于 2023-2-19 23:32
