AUTOMATIC1111 / stable-diffusion-webui-tensorrt

AUTOMATIC1111/stable-diffusion-webui-tensorrt Issues

Advanced Tab not displaying
Updated 12 days ago
RuntimeError
Updated 2 months ago1
Anyone get TensorRT Extension running with usefull image sizes ?
Updated 2 months ago3
Lora Exports are 1kb and don't work
Updated 2 months ago
tensorrt errors ,tab not appearing
Updated 3 months ago
Uncaught exception detected: Unable to open library: nvinfer_plugin.dll
Updated 3 months ago7
Can't use any trt that isn't 512x512 batch 1
Updated 4 months ago2
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.
Updated 4 months ago5
Runtime Error - FAILED TensorRT.trtexec
Closed 10 months ago2
How do I create an engine profile for adetailer? or is rttensor incompatiable with adetailer?
Updated 5 months ago3
going higher than 768x768 gives an error but if batch size is 2 then one image gens correctly
Updated 5 months ago
ERROR:root:Failed to build engine: [Errno 2] No such file or directory
Closed 5 months ago1
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):
Updated 5 months ago6
No real speedup
Updated 6 months ago2
Going above 2048x2048 with tensorrt using hires_fix possible?
Updated 6 months ago
inpainting models don't work
Closed 7 months ago
new version
Updated 7 months ago
RuntimeError: cpu gpu
Updated 7 months ago
Input shape must be divisible by 64 in both dimensions
Updated 7 months ago1
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.
Updated 7 months ago4
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?
Updated 7 months ago8
Making a profile can freeze forever.
Updated 7 months ago
Generate Default Engines
Closed 7 months ago2
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.
Closed 7 months ago
Cannot choose between profiles
Updated 8 months ago2
amd gpu
Updated 8 months ago1
Official TensorRT extension from NVIDIA is available now
Updated 8 months ago1
tensorrt-8.6.1-cp310-none-linux_x86_64.whl is not a supported wheel on this platform.
Closed a year ago1
Need the feature to load LoRA and base model seperately
Updated 8 months ago
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
Updated 8 months ago3
can i run the official webui in code?not the UI?
Updated 8 months ago
how can i increase Maximum prompt token count?
Closed 8 months ago
Can't use Hires Fix
Updated 9 months ago
(today) https://huggingface.co/stabilityai/stable-diffusion-xl-1.0-tensorrt
Updated 9 months ago
urgent: SDXL TensorRT for guinea pig photo production
Closed 9 months ago
Cannot run img2img on SDXL
Updated 9 months ago
Anyone managed to setup/use on linux?
Closed a year ago9
SDXL Support
Updated 10 months ago3
"System cannot find path specified" when trying to convert to onnx
Updated 10 months ago2
not working on SDXL
Updated 10 months ago
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)
Updated 10 months ago2
Does SD model matter?
Updated 10 months ago1
TensorRT official webui
Updated 10 months ago3
unable to use ControlNet extensions when tensorRTs are in use
Updated a year ago1
Does webui have a plan to support onnx runtime for stable diffusion accerlating?
Updated a year ago
How to clear pytorch base model GPU memory? Tensorrt GPU memory larger than pytorch.
Updated a year ago1
What is meaning "Loras are baked in into the converted model. "?
Updated a year ago3
TracerWarning
Updated a year ago3
SD Web UI - Loading Old Prompts During Generation.
Updated a year ago
Cannot generate at higher res than 512x512
Closed a year ago3