This can happen when the client cannot fetch the server parameters because the request times out or has been rejected
by the server.
This often means that the requested API server is not running.
#### Parameter version error
This can happen when the version in the server parameters is too old for the current client or missing entirely, which
was the case before version v0.5.0.
This often means that the API server is running but out-of-date.
### Server Errors
If your image fails to render without any other error messages on the client, check the server logs for errors (if you
have access).
#### Very slow with high CPU usage, max fan speed during image generation
This can happen when you attempt to use a platform that is not supported by the current hardware.
This often means that you need to select a different platform or install the correct drivers for your GPU and operating
system.
Example error:
```none
loading different pipeline
C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py:54: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'DmlExecutionProvider, CPUExecutionProvider'
```
The `CPUExecutionProvider` is used as a fallback, but has a tendency to max out all of your real CPU cores.
#### ONNXRuntimeError: The parameter is incorrect
This can happen when you attempt to use an inpainting model with txt2img or img2img mode, or a regular model for inpaint
mode.
This often means that you are using an invalid model for the current tab.
Example error:
```none
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_web\pipeline.py", line 181, in run_inpaint_pipeline
image = pipe(
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_inpaint.py", line 427, in __call__
noise_pred = self.unet(
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\diffusers\onnx_utils.py", line 61, in __call__
return self.model.run(None, inputs)
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 200, in run
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/conv_in/Conv' Status Message: D:\a\_work\1\s\onnx
runtime\core\providers\dml\DmlExecutionProvider\src\MLOperatorAuthorImpl.cpp(1878)\onnxruntime_pybind11_state.pyd!00007FFB8404F72D: (caller: 00007FFB84050AEF) Exception(15) tid(2428) 80070057 The parameter is incorrect
```
#### The expanded size of the tensor must match the existing size
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\realesrgan\utils.py", line 228, in enhance
self.tile_process()
File "C:\Users\ssube\stabdiff\onnx-web\api\onnx_env\lib\site-packages\realesrgan\utils.py", line 182, in tile_process
self.output[:, :, output_start_y:output_end_y,
RuntimeError: The expanded size of the tensor (2048) must match the existing size (1024) at non-singleton dimension 3. Target sizes: [1, 3, 2048, 2048]. Tensor sizes: [3, 1024, 1024]