tldream
tldream copied to clipboard
Published
20 hours ago •
Sanster
Sanster
Torch not compiled with CUDA enabled
I am using the 1-Click Windows Installer When I run 'win_config.bat' it was all good and no errors. However, when I run 'win_start.bat' it show Torch not compiled with CUDA enabled...
Log:
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.0.0+cu118 with CUDA 1108 (you have 2.0.0+cpu)
Python 3.10.10 (you have 3.10.9)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
2023-04-09 20:16:31.534 | INFO | tldream.server:main:153 - tldream 0.6.1
2023-04-09 20:16:31.535 | INFO | tldream.server:main:154 - Model cache dir: C:\Users\xxx\.cache\huggingface\hub
2023-04-09 20:16:31.540 | INFO | tldream.util:init_pipe:102 - Loading model: runwayml/stable-diffusion-v1-5
vae\diffusion_pytorch_model.safetensors not found
Fetching 15 files: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 15001.09it/s]
E:\lama-tldream\installer\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ E:\lama-tldream\installer\lib\site-packages\tldream\__init__.py:86 in start │
│ │
│ 83 │ │
│ 84 │ from .server import main │
│ 85 │ │
│ ❱ 86 │ main( │
│ 87 │ │ listen=listen, │
│ 88 │ │ port=port, │
│ 89 │ │ device=device, │
│ │
│ E:\lama-tldream\installer\lib\site-packages\tldream\server.py:167 in main │
│ │
│ 164 │ _torch_dtype = torch_dtype │
│ 165 │ │
│ 166 │ # TODO: lazy load model after server started to get download progress │
│ ❱ 167 │ controlled_model = init_pipe( │
│ 168 │ │ model, │
│ 169 │ │ device, │
│ 170 │ │ torch_dtype=torch_dtype, │
│ │
│ E:\lama-tldream\installer\lib\site-packages\tldream\util.py:124 in init_pipe │
│ │
│ 121 │ if cpu_offload: │
│ 122 │ │ pipe.enable_sequential_cpu_offload() │
│ 123 │ else: │
│ ❱ 124 │ │ pipe.to(device) │
│ 125 │ │
│ 126 │ if shared.use_xformers: │
│ 127 │ │ pipe.enable_xformers_memory_efficient_attention() │
│ │
│ E:\lama-tldream\installer\lib\site-packages\diffusers\pipelines\pipeline_utils.py:39 │
│ 6 in to │
│ │
│ 393 │ │ │ │ │ │ " support for`float16` operations on this device in PyTorch. Ple │
│ 394 │ │ │ │ │ │ " `torch_dtype=torch.float16` argument, or use another device fo │
│ 395 │ │ │ │ │ ) │
│ ❱ 396 │ │ │ │ module.to(torch_device) │
│ 397 │ │ return self │
│ 398 │ │
│ 399 │ @property │
│ │
│ E:\lama-tldream\installer\lib\site-packages\transformers\modeling_utils.py:1811 in │
│ to │
│ │
│ 1808 │ │ │ │ " model has already been set to the correct devices and casted to the co │
│ 1809 │ │ │ ) │
│ 1810 │ │ else: │
│ ❱ 1811 │ │ │ return super().to(*args, **kwargs) │
│ 1812 │ │
│ 1813 │ def half(self, *args): │
│ 1814 │ │ # Checks if the model has been loaded in 8-bit │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\nn\modules\module.py:1145 in to │
│ │
│ 1142 │ │ │ │ │ │ │ non_blocking, memory_format=convert_to_format) │
│ 1143 │ │ │ return t.to(device, dtype if t.is_floating_point() or t.is_complex() else No │
│ 1144 │ │ │
│ ❱ 1145 │ │ return self._apply(convert) │
│ 1146 │ │
│ 1147 │ def register_full_backward_pre_hook( │
│ 1148 │ │ self, │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\nn\modules\module.py:797 in _apply │
│ │
│ 794 │ │
│ 795 │ def _apply(self, fn): │
│ 796 │ │ for module in self.children(): │
│ ❱ 797 │ │ │ module._apply(fn) │
│ 798 │ │ │
│ 799 │ │ def compute_should_use_set_data(tensor, tensor_applied): │
│ 800 │ │ │ if torch._has_compatible_shallow_copy_type(tensor, tensor_applied): │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\nn\modules\module.py:797 in _apply │
│ │
│ 794 │ │
│ 795 │ def _apply(self, fn): │
│ 796 │ │ for module in self.children(): │
│ ❱ 797 │ │ │ module._apply(fn) │
│ 798 │ │ │
│ 799 │ │ def compute_should_use_set_data(tensor, tensor_applied): │
│ 800 │ │ │ if torch._has_compatible_shallow_copy_type(tensor, tensor_applied): │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\nn\modules\module.py:797 in _apply │
│ │
│ 794 │ │
│ 795 │ def _apply(self, fn): │
│ 796 │ │ for module in self.children(): │
│ ❱ 797 │ │ │ module._apply(fn) │
│ 798 │ │ │
│ 799 │ │ def compute_should_use_set_data(tensor, tensor_applied): │
│ 800 │ │ │ if torch._has_compatible_shallow_copy_type(tensor, tensor_applied): │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\nn\modules\module.py:820 in _apply │
│ │
│ 817 │ │ │ # track autograd history of `param_applied`, so we have to use │
│ 818 │ │ │ # `with torch.no_grad():` │
│ 819 │ │ │ with torch.no_grad(): │
│ ❱ 820 │ │ │ │ param_applied = fn(param) │
│ 821 │ │ │ should_use_set_data = compute_should_use_set_data(param, param_applied) │
│ 822 │ │ │ if should_use_set_data: │
│ 823 │ │ │ │ param.data = param_applied │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\nn\modules\module.py:1143 in │
│ convert │
│ │
│ 1140 │ │ │ if convert_to_format is not None and t.dim() in (4, 5): │
│ 1141 │ │ │ │ return t.to(device, dtype if t.is_floating_point() or t.is_complex() els │
│ 1142 │ │ │ │ │ │ │ non_blocking, memory_format=convert_to_format) │
│ ❱ 1143 │ │ │ return t.to(device, dtype if t.is_floating_point() or t.is_complex() else No │
│ 1144 │ │ │
│ 1145 │ │ return self._apply(convert) │
│ 1146 │
│ │
│ E:\lama-tldream\installer\lib\site-packages\torch\cuda\__init__.py:239 in _lazy_init │
│ │
│ 236 │ │ │ │ "Cannot re-initialize CUDA in forked subprocess. To use CUDA with " │
│ 237 │ │ │ │ "multiprocessing, you must use the 'spawn' start method") │
│ 238 │ │ if not hasattr(torch._C, '_cuda_getDeviceCount'): │
│ ❱ 239 │ │ │ raise AssertionError("Torch not compiled with CUDA enabled") │
│ 240 │ │ if _cudart is None: │
│ 241 │ │ │ raise AssertionError( │
│ 242 │ │ │ │ "libcudart functions unavailable. It looks like you have a broken build? │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
AssertionError: Torch not compiled with CUDA enabled
Press any key to continue . . .
Thanks for your support! Fixing the version of xformers in win_config will solve this problem
@call pip install xformers==0.0.16
Full win_config.bat script
@echo off
set PATH=C:\Windows\System32;%PATH%
@call installer\Scripts\activate.bat
@call conda-unpack
@call conda install -y -c conda-forge cudatoolkit=11.7
@call pip install torch==1.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
@call pip install xformers==0.0.16
@call pip3 install -U tldream
tldream --start-web-config --config-file %0\..\installer_config.json
PAUSE
Thanks @Sanster it fixed it however now I am getting some warning:
E:\tldream\installer\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` wil
And some items not found on the log:
INFO: Uvicorn running on http://127.0.0.1:4242 (Press CTRL+C to quit)
INFO: 127.0.0.1:65174 - "GET / HTTP/1.1" 200 OK
INFO: 127.0.0.1:65174 - "GET /_next/static/css/fb13a1146f6a82a5.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:65174 - "GET /_next/static/chunks/webpack-a45dcddfcffa5992.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65175 - "GET /_next/static/chunks/framework-0f4b6e2ddffaf68b.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65178 - "GET /_next/static/chunks/main-93d21f3896dc1d91.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65179 - "GET /_next/static/chunks/pages/_app-86df0457e8e08c70.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65180 - "GET /_next/static/chunks/pages/index-0f8676ad5175418d.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65181 - "GET /_next/static/UfOBmMuC1Vh5Vh3fh-WnP/_buildManifest.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65174 - "GET /_next/static/UfOBmMuC1Vh5Vh3fh-WnP/_ssgManifest.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65175 - "GET /_next/static/UfOBmMuC1Vh5Vh3fh-WnP/_middlewareManifest.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65175 - "GET /_next/static/chunks/7dae1ac5.882dda22b44f960b.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65174 - "GET /_next/static/chunks/147.f78af6f868637eea.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65181 - "GET /_next/static/chunks/256.a1d9847890eda152.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:65178 - "GET /_next/static/css/7ee352fbfec876f3.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:65178 - "GET /favicon.ico HTTP/1.1" 404 Not Found
INFO: ('127.0.0.1', 65187) - "WebSocket /socket.io/?EIO=4&transport=websocket" [accepted]
INFO: connection open
INFO: 127.0.0.1:65181 - "GET /_next/static/media/recursive-latin-400-normal.ad5f3e31.woff2 HTTP/1.1" 200 OK
INFO: 127.0.0.1:65189 - "GET /manifest.json HTTP/1.1" 404 Not Found
INFO: 127.0.0.1:65181 - "GET /favicon.ico HTTP/1.1" 404 Not Found
INFO: 127.0.0.1:65174 - "GET /sw.js HTTP/1.1" 404 Not Found
You can ignore these logs and access 127.0.0.1:4242 in the browser to use tldream
Thank you @Sanster
One thing, if you can add auto launch and to chose desktopmode or web it will be amazing just like in lama-cleaner