comfyanonymous / ComfyUI_TensorRT

MIT License
514 stars 34 forks source link

"Exception during processing!!! ONNX export failed. Could not open file or directory." #37

Open Reno0vacio opened 5 months ago

Reno0vacio commented 5 months ago

I just pressed "Queue Prompt".

SDXL Trubo

Error occurred when executing DYNAMIC_TRT_MODEL_CONVERSION:

ONNX export failed. Could not open file or directory: D:/Új mappa/ComfyUI/temp/1718729921.6965177/unet.time_embed.0.weight

File "D:\Új mappa\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Új mappa\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 "D:\Új mappa\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Új mappa\ComfyUI\custom_nodes\ComfyUI_TensorRT\tensorrt_convert.py", line 517, in convert
return super()._convert(
^^^^^^^^^^^^^^^^^
File "D:\Új mappa\ComfyUI\custom_nodes\ComfyUI_TensorRT\tensorrt_convert.py", line 264, in _convert
torch.onnx.export(
File "D:\Új mappa\ComfyUI\venv\Lib\site-packages\torch\onnx\utils.py", line 516, in export
_export(
File "D:\Új mappa\ComfyUI\venv\Lib\site-packages\torch\onnx\utils.py", line 1653, in _export
) = graph._export_onnx( # type: ignore[attr-defined]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Similar with 1.5:

Efficient Loader Models Cache:
Ckpt:
  [1] analogMadness_v60
Lora:
  [1] base_ckpt: analogMadness_v60
      lora(mod,clip): l0r4n4m3h3r3-000005(0.6,1.0)
Requested to load BaseModel
Loading 1 new model
ERROR lora diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight shape '[640, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight shape '[640, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight shape '[640, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight shape '[640, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight shape '[1280, 768]' is invalid for input of size 2621440
ERROR lora diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight shape '[1280, 768]' is invalid for input of size 2621440
ERROR lora diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight shape '[1280, 768]' is invalid for input of size 2621440
ERROR lora diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight shape '[1280, 768]' is invalid for input of size 2621440
ERROR lora diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_k.weight shape '[1280, 768]' is invalid for input of size 2621440
ERROR lora diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_v.weight shape '[1280, 768]' is invalid for input of size 2621440
ERROR lora diffusion_model.output_blocks.3.1.proj_in.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight shape '[10240, 1280]' is invalid for input of size 3276800
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.weight shape '[1280, 5120]' is invalid for input of size 1638400
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight shape '[1280, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight shape '[1280, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.3.1.proj_out.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.proj_in.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight shape '[10240, 1280]' is invalid for input of size 3276800
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.weight shape '[1280, 5120]' is invalid for input of size 1638400
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight shape '[1280, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight shape '[1280, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.4.1.proj_out.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.proj_in.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight shape '[10240, 1280]' is invalid for input of size 3276800
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.weight shape '[1280, 5120]' is invalid for input of size 1638400
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight shape '[1280, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight shape '[1280, 768]' is invalid for input of size 1310720
ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight shape '[1280, 1280]' is invalid for input of size 409600
ERROR lora diffusion_model.output_blocks.5.1.proj_out.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600
[06/18/2024-19:03:13] [TRT] [I] The logger passed into createInferBuilder differs from one already provided for an existing builder, runtime, or refitter. Uses of the global logger, returned by nvinfer1::getLogger(), will return the existing value.
[06/18/2024-19:03:14] [TRT] [I] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 17267, GPU 1270 (MiB)
[06/18/2024-19:03:23] [TRT] [I] [MemUsageChange] Init builder kernel library: CPU +2689, GPU +288, now: CPU 20180, GPU 1558 (MiB)
Could not open file D:\Új mappa\ComfyUI\temp\1718730169.6639657\model.onnx
[06/18/2024-19:03:23] [TRT] [E] ModelImporter.cpp:914: Failed to parse ONNX model from file: D:\Új mappa\ComfyUI\temp\1718730169.6639657\model.onnx!
ONNX load ERROR
Prompt executed in 41.30 seconds