stable-diffusion-webui-tensorrt

stable-diffusion-webui-tensorrt copied to clipboard

The problem isn't that it breaks, but that it freezes, without any feedback in the console log, and without crashing. If it gave feedback and failed, that'd be fine, I'd...

left1000

Cannot choose between profiles

2

I have generated several engine profiles for SDXL. However, I have no way of selecting the individual engines - all I can choose is one per base model/checkpoint. I am...

sfingali

amd gpu

1

how do i make it work on amd gpu windows?

303Aki303

Official TensorRT extension from NVIDIA is available now

1

Requires one of these drivers minimum: NVIDIA Studio Driver 537.58, Game Ready Driver 537.58, NVIDIA RTX Enterprise Driver 537.58, and above. https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT https://nvidia.custhelp.com/app/answers/detail/a_id/5487

Jonseed

I have many loras but merge each lora weights with base model to create ONNX file is to expensive. I wander if there is another way to seperately load lora...

FlamingJay

RuntimeError: 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

3

I have this error, when i click on button Convert Unet - RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and...

AdamBlazer

Tensorrt cannot appear on the webui

11

I get this error Error loading script: [trt.py](https://trt.py/) Traceback (most recent call last): File "F:\stable-diffusion-webui\modules\[scripts.py](https://scripts.py/)", line 263, in load_scripts script_module = script_loading.load_module(scriptfile.path) File "F:\stable-diffusion-webui\modules\script_loading.py", line 10, in load_module module_spec.loader.exec_module(module) File...

GitGod76

henbucuoshanghai

found two devices, cpu and cuda:0!

2

When I click on the "Convert Unet to ONNX" button in the "Convert to ONNX" tab, I am prompted with the following error RuntimeError: Expected all tensors to be on...

acergelff

Whenever I try to use Hires. Fix I get the following error: ``Exception: bad shape for TensorRT input x: (2, 4, 192, 128)`` Is there any workaround for this since...

xameryn