RuntimeError about CuDA

[jesenzhang]

output_path G:\Workspace\AI\ComfyUI\custom_nodes\ComfyUI-MuseV\results\m=majicmixRealv6Fp16_rm=no_case=cluw94l5w000090vb68w0lrcn_w=512_h=704_t=120_nb=1_s=77_p=a9aa5_w=0.001_ms=8.0_s=0.8_g=1.5_c-i=cluw9_r-c=False_w=0.5_V2_r=no_ip=no_f=no.mp4
2024-04-12 13:55:42,267- root:179- ERROR- !!! Exception during processing !!!
2024-04-12 13:55:42,435- root:180- ERROR- Traceback (most recent call last):
File "G:\Workspace\AI\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI\custom_nodes\ComfyUI-MuseV\nodes.py", line 1393, in run
out_videos = sd_predictor.run_pipe_text2video(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI/custom_nodes/ComfyUI-MuseV\musev\pipelines\pipeline_controlnet_predictor.py", line 655, in run_pipe_text2video
out = self.pipeline(
^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI/custom_nodes/ComfyUI-MuseV\musev\pipelines\pipeline_controlnet.py", line 1646, in call
) = self.prepare_condition_latents_and_index(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI/custom_nodes/ComfyUI-MuseV\musev\pipelines\pipeline_controlnet.py", line 980, in prepare_condition_latents_and_index
condition_latents = self.vae.encode(condition_images).latent_dist.mean
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI/custom_nodes/ComfyUI-MuseV/diffusers/src\MuseVdiffusers\utils\accelerate_utils.py", line 46, in wrapper
return method(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI/custom_nodes/ComfyUI-MuseV/diffusers/src\MuseVdiffusers\models\autoencoder_kl.py", line 282, in encode
h = self.encoder(x)
^^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\Workspace\AI\ComfyUI/custom_nodes/ComfyUI-MuseV/diffusers/src\MuseVdiffusers\models\vae.py", line 136, in forward
sample = self.conv_in(sample)
^^^^^^^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\MiniConda\envs\comfy\Lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: free_upper_bound + pytorch_used_bytes[device] <= device_total INTERNAL ASSERT FAILED at "..\c10\cuda\CUDAMallocAsyncAllocator.cpp":540, please report a bug to PyTorch.

[Heimerdinger]

The same