Read Troubleshoot
[x] I admit that I have read the Troubleshoot before making this issue.
Describe the problem
I have an AMD Radeon 5700 XT 8GB and i get this error upon running a command "python entry_with_update.py":
"RuntimeError: No CUDA GPUs are available"
Full Console Log
(fooocus_env) artix:[artix]:~/Applications/fooocus$ python entry_with_update.py
Already up-to-date
Update succeeded.
[System ARGV] ['entry_with_update.py']
Python 3.11.6 (main, Nov 14 2023, 18:04:26) [GCC 13.2.1 20230801]
Fooocus version: 2.1.859
Running on local URL: http://127.0.0.1:7865
To create a public link, set share=True in launch().
Exception in thread Thread-2 (worker):
Traceback (most recent call last):
File "/usr/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
File "/usr/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
File "/home/artix/Applications/fooocus/modules/async_worker.py", line 25, in worker
import modules.default_pipeline as pipeline
File "/home/artix/Applications/fooocus/modules/default_pipeline.py", line 1, in
import modules.core as core
File "/home/artix/Applications/fooocus/modules/core.py", line 1, in
from modules.patch import patch_all
File "/home/artix/Applications/fooocus/modules/patch.py", line 5, in
import ldm_patched.modules.model_base
File "/home/artix/Applications/fooocus/ldm_patched/modules/model_base.py", line 2, in
from ldm_patched.ldm.modules.diffusionmodules.openaimodel import UNetModel
File "/home/artix/Applications/fooocus/ldm_patched/ldm/modules/diffusionmodules/openaimodel.py", line 18, in
from ..attention import SpatialTransformer, SpatialVideoTransformer, default
File "/home/artix/Applications/fooocus/ldm_patched/ldm/modules/attention.py", line 12, in
from .sub_quadratic_attention import efficient_dot_product_attention
File "/home/artix/Applications/fooocus/ldm_patched/ldm/modules/sub_quadratic_attention.py", line 27, in
from ldm_patched.modules import model_management
File "/home/artix/Applications/fooocus/ldm_patched/modules/model_management.py", line 118, in
total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/ldm_patched/modules/model_management.py", line 87, in get_torch_device
return torch.device(torch.cuda.current_device())
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/torch/cuda/init.py", line 769, in current_device
_lazy_init()
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/torch/cuda/init.py", line 298, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available
Traceback (most recent call last):
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/blocks.py", line 1431, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/blocks.py", line 1117, in call_function
prediction = await utils.async_iteration(iterator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/utils.py", line 350, in async_iteration
return await iterator.anext()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/utils.py", line 343, in anext
return await anyio.to_thread.run_sync(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 851, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/utils.py", line 326, in run_sync_iterator_async
return next(iterator)
^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/gradio/utils.py", line 695, in gen_wrapper
yield from f(*args, **kwargs)
File "/home/artix/Applications/fooocus/webui.py", line 27, in generate_clicked
import ldm_patched.modules.model_management as model_management
File "/home/artix/Applications/fooocus/ldm_patched/modules/model_management.py", line 118, in
total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/ldm_patched/modules/model_management.py", line 87, in get_torch_device
return torch.device(torch.cuda.current_device())
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/torch/cuda/init.py", line 769, in current_device
_lazy_init()
File "/home/artix/Applications/fooocus/fooocus_env/lib/python3.11/site-packages/torch/cuda/init.py", line 298, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available
Please follow the official installation instructions and use --directml after setup adjustments.
See https://github.com/lllyasviel/Fooocus?tab=readme-ov-file#windowsamd-gpus, closed as duplicate.
Ok, but instruction is bad because this paragraph:
Linux (AMD GPUs)
Note that the minimal requirement for different platforms is different.
Same with the above instructions. You need to change torch to the AMD version
pip uninstall torch torchvision torchaudio torchtext functorch xformers
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.6
is after command to run it.
Check if you ROCM works.
My 5700XT can run Fooocus without issue. Although it's slow (2 minutes an image for extreme mode, 3 minutes an image for Speed mode). I also made a video at https://youtu.be/HgGZyNRA1Ns
lllyasviel
