after starting to mist, cmd stopped at here

[Labalto]

Just follow up on this - I tested the same files in different laptop setup. It rendered alright. So I guess maybe it's the problem of not meeting the requirement?

---

Hey! Thanks for the new tutorial for new comer like me.
I've tried a lot of times, but somehow CMD just keep stopping at here; is it because of my old driver that it couldn't continue? I felt like I'm so close to successfully complete one run.

Updating Environment...
L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\cuda_init_.py:740: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11020). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ..\c10\cuda\CUDAFunctions.cpp:108.)
return torch._C._cuda_getDeviceCount() if nvml_count < 0 else nvml_count
IMPORTANT: You are using gradio version 4.14.0, however version 4.44.1 is available, please upgrade.

Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\cuda_init_.py:740: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11020). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ..\c10\cuda\CUDAFunctions.cpp:108.)
return torch._C.cuda_getDeviceCount() if nvml_count < 0 else nvml_count
The following values were not passed to accelerate launch and had defaults used instead:
--num_processes was set to a value of 0
--num_machines was set to a value of 1
--mixed_precision was set to a value of 'no'
--dynamo_backend was set to a value of 'no'
To avoid this warning pass in values for each of the problematic parameters or run accelerate config.
L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\cuda_init.py:740: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11020). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ..\c10\cuda\CUDAFunctions.cpp:108.)
return torch._C._cuda_getDeviceCount() if nvml_count < 0 else nvml_count
02/01/2025 02:54:59 - INFO - main - Distributed environment: NO
Num processes: 1
Process index: 0
Local process index: 0
Device: cpu

Mixed precision type: fp16

==precision: torch.float32==
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
{'use_linear_projection', 'time_cond_proj_dim', 'class_embeddings_concat', 'only_cross_attention', 'mid_block_type', 'resnet_time_scale_shift', 'encoder_hid_dim', 'time_embedding_type', 'conv_in_kernel', 'cross_attention_norm', 'upcast_attention', 'class_embed_type', 'resnet_skip_time_act', 'projection_class_embeddings_input_dim', 'num_class_embeds', 'dual_cross_attention', 'time_embedding_act_fn', 'mid_block_only_cross_attention', 'resnet_out_scale_factor', 'timestep_post_act', 'conv_out_kernel'} was not found in config. Values will be initialized to default values.
{'dynamic_thresholding_ratio', 'prediction_type', 'sample_max_value', 'clip_sample_range', 'thresholding'} was not found in config. Values will be initialized to default values.
{'scaling_factor'} was not found in config. Values will be initialized to default values.
Traceback (most recent call last):
File "L:\mist2\mist-v2_gui_free_version\mist-v2\src\attacks\mist.py", line 904, in
main(args)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\src\attacks\mist.py", line 776, in main
).cuda()
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\nn\modules\module.py", line 918, in cuda
return self._apply(lambda t: t.cuda(device))
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply
module._apply(fn)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply
module._apply(fn)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\nn\modules\module.py", line 833, in _apply
param_applied = fn(param)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\nn\modules\module.py", line 918, in
return self.apply(lambda t: t.cuda(device))
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\torch\cuda_init.py", line 298, in _lazy_init
torch._C._cuda_init()
RuntimeError: The NVIDIA driver on your system is too old (found version 11020). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.
Traceback (most recent call last):
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\Scripts\accelerate.exe_main.py", line 7, in
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\accelerate\commands\launch.py", line 986, in launch_command
simple_launcher(args)
File "L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\lib\site-packages\accelerate\commands\launch.py", line 628, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['L:\mist2\mist-v2_gui_free_version\mist-v2\Pysetter\venv\python.exe', 'attacks/mist.py', '--pgd_eps', '0.047058823529411764', '--mode', 'lunet', '--instance_data_dir', 'data/img', '--output_dir', 'output', '--pretrained_model_name_or_path', 'stable-diffusion/stable-diffusion-1-5', '--class_data_dir', 'data/contrast', '--instance_prompt', 'masterpiece, best quality', '--class_prompt', '', '--max_train_steps', '5', '--max_f_train_steps', '10', '--max_adv_train_steps', '30', '--learning_rate', '0.0001', '--pgd_alpha', '0.005', '--lora_rank', '4', '--prior_loss_weight', '0.1', '--fused_weight', '1e-05', '--mixed_precision', 'fp16']' returned non-zero exit status 1.