Issues
- 0
Advanced Tab not displaying
#87 opened by damionismyname - 1
RuntimeError
#83 opened by KelvinSoh8 - 3
- 0
Lora Exports are 1kb and don't work
#86 opened by SamoraHunter - 0
tensorrt errors ,tab not appearing
#85 opened by Rinox89 - 7
- 2
- 5
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.
#73 opened by left1000 - 2
Runtime Error - FAILED TensorRT.trtexec
#54 opened by 78Alpha - 3
How do I create an engine profile for adetailer? or is rttensor incompatiable with adetailer?
#71 opened by left1000 - 0
going higher than 768x768 gives an error but if batch size is 2 then one image gens correctly
#82 opened by Dargunsh - 1
- 6
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! (when checking argument for argument mat1 in method wrapper_CUDA_addmm) Traceback (most recent call last):
#76 opened by left1000 - 2
No real speedup
#57 opened by Ph0rk0z - 0
- 0
inpainting models don't work
#64 opened by yuvraj108c - 0
new version
#79 opened by kalle07 - 0
RuntimeError: cpu gpu
#78 opened by kalle07 - 1
- 4
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 that worked moments ago.
#75 opened by left1000 - 8
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? also is my cpu being treated as a secondary cuda choice and that is ruining the code? is there anyway to tell this extension to ignore my cpu's built in graphics functionalities that I never use?
#69 opened by left1000 - 0
Making a profile can freeze forever.
#74 opened by left1000 - 2
Generate Default Engines
#72 opened by Cigoler - 0
I can't create a custom TensorRT Engine Profile with a custom name, I can merely open advanced settings and alter one of the names that already exists.
#70 opened by left1000 - 2
Cannot choose between profiles
#68 opened by sfingali - 1
- 1
- 1
tensorrt-8.6.1-cp310-none-linux_x86_64.whl is not a supported wheel on this platform.
#39 opened by yuvraj108c - 0
- 3
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
#50 opened by AdamBlazer - 0
- 0
how can i increase Maximum prompt token count?
#49 opened by yjymickey - 0
Can't use Hires Fix
#63 opened by xameryn - 0
- 0
- 0
Cannot run img2img on SDXL
#59 opened by aferlo78 - 9
Anyone managed to setup/use on linux?
#43 opened by yuvraj108c - 3
SDXL Support
#58 opened by CyberTimon - 2
- 0
not working on SDXL
#56 opened by Shaistrong - 2
stable-diffusion-webui-tensorrt\scripts\trt.py", line 6, in <module> from modules import script_callbacks, sd_unet, devices, shared, paths_internal ImportError: cannot import name 'sd_unet' from 'modules' (unknown location)
#47 opened by lucasjinreal - 1
Does SD model matter?
#51 opened by dxwarlock - 3
TensorRT official webui
#46 opened by lucasjinreal - 1
- 0
Does webui have a plan to support onnx runtime for stable diffusion accerlating?
#52 opened by yjymickey - 1
How to clear pytorch base model GPU memory? Tensorrt GPU memory larger than pytorch.
#45 opened by WudiJoey - 3
- 3
TracerWarning
#34 opened by jebarpg - 0
- 3
Cannot generate at higher res than 512x512
#38 opened by ellugia