Stable-Diffusion-WebUI-TensorRT: Failed to parse ONNX model. Does the model file exist and contain a valid ONNX model?

the error is as follows

Disabling attention optimization
Exporting mix18.fp16 to TensorRT using - Batch Size: 1-1-4
Height: 512-512-768
Width: 512-512-768
Token Count: 75-75-150
{'sample': [(1, 4, 64, 64), (2, 4, 64, 64), (8, 4, 96, 96)], 'timesteps': [(1,), (2,), (8,)], 'encoder_hidden_states': [(1, 77, 768), (2, 77, 768), (8, 154, 768)]}
============= Diagnostic Run torch.onnx.export version 2.0.1+cu118 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

ERROR:root:Exporting to ONNX failed. Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)
============= Diagnostic Run torch.onnx.export version 2.0.1+cu118 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

ERROR:root:Exporting to ONNX failed. Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument weight in method wrapper_CUDA__native_group_norm)
Building TensorRT engine... This can take a while, please check the progress in the terminal.
Building TensorRT engine for A:\AI\Packages\A1111\models\Unet-onnx\mix18.fp16.onnx\encoder.onnx: A:\AI\Packages\A1111\models\Unet-trt\cc86\unet\mix18.fp16\id11a1472e3471eb1aa75d8acec6ea290\encoder.trt
Could not open file A:\AI\Packages\A1111\models\Unet-onnx\mix18.fp16.onnx\encoder.onnx
[E] ModelImporter.cpp:773: Failed to parse ONNX model from file: A:\AI\Packages\A1111\models\Unet-onnx\mix18.fp16.onnx\encoder.onnx
Could not open file A:\AI\Packages\A1111\models\Unet-onnx\mix18.fp16.onnx\encoder.onnx
[!] Failed to parse ONNX model. Does the model file exist and contain a valid ONNX model?
Traceback (most recent call last):
  File "A:\AI\Packages\A1111\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "A:\AI\Packages\A1111\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api
    result = await self.call_function(
  File "A:\AI\Packages\A1111\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "A:\AI\Packages\A1111\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "A:\AI\Packages\A1111\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "A:\AI\Packages\A1111\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "A:\AI\Packages\A1111\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper
    response = f(*args, **kwargs)
  File "A:\AI\Packages\A1111\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 249, in export_unet_to_trt
    ret = export_trt(
  File "A:\AI\Packages\A1111\extensions\Stable-Diffusion-WebUI-TensorRT\exporter.py", line 234, in export_trt
    ret = engine.build(
  File "A:\AI\Packages\A1111\extensions\Stable-Diffusion-WebUI-TensorRT\utilities.py", line 251, in build
    network = network_from_onnx_path(
  File "<string>", line 3, in network_from_onnx_path
  File "A:\AI\Packages\A1111\venv\lib\site-packages\polygraphy\backend\base\loader.py", line 40, in __call__
    return self.call_impl(*args, **kwargs)
  File "A:\AI\Packages\A1111\venv\lib\site-packages\polygraphy\util\util.py", line 710, in wrapped
    return func(*args, **kwargs)
  File "A:\AI\Packages\A1111\venv\lib\site-packages\polygraphy\backend\trt\loader.py", line 227, in call_impl
    trt_util.check_onnx_parser_errors(parser, success)
  File "A:\AI\Packages\A1111\venv\lib\site-packages\polygraphy\backend\trt\util.py", line 86, in check_onnx_parser_errors
    G_LOGGER.critical("Failed to parse ONNX model. Does the model file exist and contain a valid ONNX model?")
  File "A:\AI\Packages\A1111\venv\lib\site-packages\polygraphy\logger\logger.py", line 605, in critical
    raise ExceptionType(message) from None
polygraphy.exception.exception.PolygraphyException: Failed to parse ONNX model. Does the model file exist and contain a valid ONNX model?

which i’ve gotten around it by force rebuilding a before 0.2.0 version trt model of the same checkpoint, another odd thing is that after you make one, you can make any other one just fine. also pytorch fallback is weird, you need double the batch size to make it function properly. Idk whats wrong so any help as to making a model (for the first time) in V 0.2.0 would be appreciated.