stable-diffusion-webui-tensorrt
stable-diffusion-webui-tensorrt copied to clipboard
[E] 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::validateInputBindings::2046] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::nvinfer1::rt::ExecutionContext::validateInputBindings::2046, condition: profileMinDims.d[i]
Trying to create an rttensor for a lora, I got the error ERROR:root:Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!...
I had hoped this would help make generation faster on my P40. Unfortunately it only seems to add a few seconds to generation time. I made the model work from...
Hi all, I have model that can quite good generate output of 2560x1440 using 2x upscale from 1280x720 using lower denoise. My question is - is there any way to...
try to rebuild my tensor Exporting SDXL_juggernautXL_version6Rundiffusion to TensorRT {'sample': [(2, 4, 85, 128), (2, 4, 85, 128), (2, 4, 85, 128)], 'timesteps': [(2,), (2,), (2,)], 'encoder_hidden_states': [(2, 77, 2048),...
(win10- rtx4060 16gb) all runign fine without tensor ( i do not change any standart settings) if i choose in settings my compiled model *** Error completing request *** Arguments:...
Perhaps a problem that only occurs with Tensor RT? FABRIC v0.6.3 File "C:\Users\UserName\sd\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\scripts\trt.py", line 84, in forward raise ValueError( ValueError: Input shape must be divisible by 64 in both dimensions....
I seem to somehow end up stuck in a situation where I cannot generate images at all, it claims no profile can be found, despite me using the same settings...
from what I can tell install.py requires importlib_metadata but pip is installing importlib_metadata by the name importlib-metadata and so it can't be found? That's just my guess as to what...
No matter which settings I choose, the only thing that's working is the minimum and maximum resolution, but sadly not the maximum amount of tokens. Is this already known, or...