stable-diffusion-webui-tensorrt
stable-diffusion-webui-tensorrt copied to clipboard
AUTOMATIC1111
attempt to fix #27 tested with rtx2070/cuda11.8 after the changes
RuntimeError: The expanded size of the tensor (1) must match the existing size (2) at non-singleton dimension 0. Target sizes: 【1, 4, 96, 64】. Tensor sizes: 【2, 4, 96, 64】...
I keep getting this, even though (see attachment) I have the Tensor directory where it should be- Error running install.py for extension C:\SD\extensions\stable-diffusion-webui-tensorrt. Command: "C:\SD\venv\Scripts\python.exe" "C:\SD\extensions\stable-diffusion-webui-tensorrt\install.py" Error code: 1 stdout:...
has anyone got the TensorRT Extension run on another model than SD 1.5? ----------------------------------------------------------------------------------------------- on my system the TensorRT extension is running and generating with the default engines like (512x512...
With particular checkpoints selected, lora exports are 1kb. Fixed by selecting working checkpoint, then exporting lora. Switch back to checkpoint and generate.
Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Version: v1.8.0-72-g45b8a499 Commit hash: 45b8a499a7e6d732b1711a0016c211f2b3c19232 *** Error running install.py for extension C:\Data\Packages\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT. *** Command: "C:\Data\Packages\stable-diffusion-webui\venv\Scripts\python.exe" "C:\Data\Packages\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\install.py" *** Error...
I'm currently following a [video guide](https://www.youtube.com/watch?v=NVyvejpzzZQ) and I'm getting this error after clicking on `Convert ONNX to TensorRT`. Here's a snippet of the output: ``` [06/06/2023-01:57:53] [I] === Device Information...
Anytime I try and and build a .trt model that isn't 512x512 batch 1 from an .onnx, the .trt is created without issues, but upon inference, I get: ``` 0%|...
How do I delete a tensorrt profile? If I delete the file it continues to show up in the webgui, and throws errors, because it realizes a profile is missing.
How do I create an engine profile for adetailer? or is rttensor incompatiable with adetailer? It autodetects a region and so uses a variable resolution at all times, right? Would...