GitHub / automatic1111/stable-diffusion-webui-tensorrt issues and pull requests
#87 - Advanced Tab not displaying
Issue -
State: open - Opened by damionismyname about 1 year ago
#86 - Lora Exports are 1kb and don't work
Issue -
State: open - Opened by SamoraHunter over 1 year ago
#85 - tensorrt errors ,tab not appearing
Issue -
State: open - Opened by Rinox89 over 1 year ago
#84 - Anyone get TensorRT Extension running with usefull image sizes ?
Issue -
State: open - Opened by XPHUPZHJ over 1 year ago
- 3 comments
#83 - RuntimeError
Issue -
State: open - Opened by KelvinSoh8 over 1 year ago
- 1 comment
#82 - going higher than 768x768 gives an error but if batch size is 2 then one image gens correctly
Issue -
State: open - Opened by Dargunsh over 1 year ago
#81 - ERROR:root:Failed to build engine: [Errno 2] No such file or directory
Issue -
State: closed - Opened by Dargunsh over 1 year ago
- 1 comment
#80 - Going above 2048x2048 with tensorrt using hires_fix possible?
Issue -
State: open - Opened by PmNz8 over 1 year ago
#79 - new version
Issue -
State: open - Opened by kalle07 over 1 year ago
#78 - RuntimeError: cpu gpu
Issue -
State: open - Opened by kalle07 over 1 year ago
#77 - Input shape must be divisible by 64 in both dimensions
Issue -
State: open - Opened by NoteToSelfFindGoodNickname almost 2 years ago
- 1 comment
#76 - 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):
Issue -
State: open - Opened by left1000 almost 2 years ago
- 6 comments
#75 - 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.
Issue -
State: open - Opened by left1000 almost 2 years ago
- 4 comments
#74 - Making a profile can freeze forever.
Issue -
State: open - Opened by left1000 almost 2 years ago
#73 - 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.
Issue -
State: open - Opened by left1000 almost 2 years ago
- 5 comments
#72 - Generate Default Engines
Issue -
State: closed - Opened by Cigoler almost 2 years ago
- 2 comments
#71 - How do I create an engine profile for adetailer? or is rttensor incompatiable with adetailer?
Issue -
State: open - Opened by left1000 almost 2 years ago
- 3 comments
#70 - 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.
Issue -
State: closed - Opened by left1000 almost 2 years ago
#69 - 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?
Issue -
State: open - Opened by left1000 almost 2 years ago
- 8 comments
#68 - Cannot choose between profiles
Issue -
State: open - Opened by sfingali almost 2 years ago
- 2 comments
#67 - Official TensorRT extension from NVIDIA is available now
Issue -
State: open - Opened by Jonseed almost 2 years ago
- 1 comment
#66 - Need the feature to load LoRA and base model seperately
Issue -
State: open - Opened by FlamingJay almost 2 years ago
#65 - can i run the official webui in code?not the UI?
Issue -
State: open - Opened by henbucuoshanghai almost 2 years ago
#64 - inpainting models don't work
Issue -
State: closed - Opened by yuvraj108c almost 2 years ago
#63 - Can't use Hires Fix
Issue -
State: open - Opened by xameryn almost 2 years ago
#62 - amd gpu
Issue -
State: open - Opened by 303Aki303 almost 2 years ago
- 1 comment
#61 - urgent: SDXL TensorRT for guinea pig photo production
Issue -
State: closed - Opened by rustrust almost 2 years ago
#60 - (today) https://huggingface.co/stabilityai/stable-diffusion-xl-1.0-tensorrt
Issue -
State: open - Opened by LockMan007 almost 2 years ago
#59 - Cannot run img2img on SDXL
Issue -
State: open - Opened by aferlo78 almost 2 years ago
#58 - SDXL Support
Issue -
State: open - Opened by CyberTimon almost 2 years ago
- 3 comments
#57 - No real speedup
Issue -
State: open - Opened by Ph0rk0z about 2 years ago
- 2 comments
#56 - not working on SDXL
Issue -
State: open - Opened by Shaistrong about 2 years ago
#55 - Cast binding shape to tensorrt.Dims before setting
Pull Request -
State: closed - Opened by rajeevsrao about 2 years ago
#54 - Runtime Error - FAILED TensorRT.trtexec
Issue -
State: closed - Opened by 78Alpha about 2 years ago
- 2 comments
#53 - Can't use any trt that isn't 512x512 batch 1
Issue -
State: open - Opened by BuffMcBigHuge about 2 years ago
- 2 comments
#52 - Does webui have a plan to support onnx runtime for stable diffusion accerlating?
Issue -
State: open - Opened by yjymickey about 2 years ago
#51 - Does SD model matter?
Issue -
State: open - Opened by dxwarlock about 2 years ago
- 1 comment
#50 - 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
Issue -
State: open - Opened by AdamBlazer about 2 years ago
- 3 comments
#49 - how can i increase Maximum prompt token count?
Issue -
State: closed - Opened by yjymickey about 2 years ago
#48 - unable to use ControlNet extensions when tensorRTs are in use
Issue -
State: open - Opened by randomname1212 about 2 years ago
- 1 comment
#47 - 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)
Issue -
State: open - Opened by lucasjinreal about 2 years ago
- 2 comments
#46 - TensorRT official webui
Issue -
State: open - Opened by lucasjinreal about 2 years ago
- 3 comments
#45 - How to clear pytorch base model GPU memory? Tensorrt GPU memory larger than pytorch.
Issue -
State: open - Opened by WudiJoey about 2 years ago
- 1 comment
#44 - Added Batch Processing, Shape appending, Dynamic alert for too large of a shape for converting trt models.
Pull Request -
State: open - Opened by jebarpg about 2 years ago
#43 - Anyone managed to setup/use on linux?
Issue -
State: closed - Opened by yuvraj108c about 2 years ago
- 9 comments
#42 - "System cannot find path specified" when trying to convert to onnx
Issue -
State: open - Opened by DuckersMcQuack about 2 years ago
- 2 comments
#41 - SD Web UI - Loading Old Prompts During Generation.
Issue -
State: open - Opened by ClipSkipper about 2 years ago
#40 - What is meaning "Loras are baked in into the converted model. "?
Issue -
State: open - Opened by edisonchan about 2 years ago
- 3 comments
#39 - tensorrt-8.6.1-cp310-none-linux_x86_64.whl is not a supported wheel on this platform.
Issue -
State: closed - Opened by yuvraj108c about 2 years ago
- 1 comment
#38 - Cannot generate at higher res than 512x512
Issue -
State: closed - Opened by ellugia about 2 years ago
- 3 comments
#37 - Uncaught exception detected: Unable to open library: nvinfer_plugin.dll
Issue -
State: open - Opened by deeyonn about 2 years ago
- 7 comments
#36 - Add Batch mode + Limit calculation
Pull Request -
State: open - Opened by wizz13150 about 2 years ago
- 1 comment
#35 - Add a batch mode + Conversion limit calculation
Pull Request -
State: closed - Opened by wizz13150 about 2 years ago
- 12 comments
#34 - TracerWarning
Issue -
State: open - Opened by jebarpg about 2 years ago
- 3 comments
#33 - Fails to convert as soon as it starts on the onnx model
Issue -
State: open - Opened by DuckersMcQuack about 2 years ago
- 2 comments
#32 - Add a batch mode + Conversion limit calculation
Pull Request -
State: closed - Opened by wizz13150 about 2 years ago
- 21 comments
#31 - successful conversion, fail the next
Issue -
State: open - Opened by 4lt3r3go about 2 years ago
- 1 comment
#30 - No batch option to run over a group or directory of models
Issue -
State: open - Opened by jebarpg about 2 years ago
- 1 comment
#29 - fix: "found two devices, cpu and cuda:0!"
Pull Request -
State: open - Opened by emirhnergn about 2 years ago
- 1 comment
#28 - Only 75 Tokens possible?
Issue -
State: open - Opened by Devalinor about 2 years ago
- 10 comments
#27 - found two devices, cpu and cuda:0!
Issue -
State: open - Opened by acergelff about 2 years ago
- 2 comments
#26 - Tiling?
Issue -
State: open - Opened by DennLie about 2 years ago
#25 - 32FP TRT models not working with xformers/sdp
Issue -
State: closed - Opened by ec111 about 2 years ago
- 1 comment
#24 - Error while converting ONNX to TRT
Issue -
State: open - Opened by dustydecapod about 2 years ago
- 10 comments
#23 - I do not see TensorRT in Stable Diffusion
Issue -
State: open - Opened by ExecuteAI about 2 years ago
- 3 comments
#22 - ONNX Model Not Found
Issue -
State: closed - Opened by ClipSkipper about 2 years ago
#21 - Can't find TensorRT Directory?
Issue -
State: open - Opened by briwil about 2 years ago
- 6 comments
#20 - Minimum Batch Size locked to 2
Issue -
State: open - Opened by MxDeWitt about 2 years ago
- 3 comments
#19 - fix typo && add VRAM limits
Pull Request -
State: closed - Opened by yoinked-h about 2 years ago
- 1 comment
#18 - Unknown compiler version
Issue -
State: closed - Opened by Devalinor about 2 years ago
- 1 comment
#17 - Module onnx is not installed!
Issue -
State: open - Opened by mattieshadow about 2 years ago
- 1 comment
#16 - Error loading script: trt.py
Issue -
State: open - Opened by sunwukong0727 about 2 years ago
- 13 comments
#15 - weird error? "TensorRT was linked against cuDNN 8.9.0 but loaded cuDNN 8.7.0" & something about "CUDA lazy loading"
Issue -
State: open - Opened by Appolonius001 about 2 years ago
#14 - no converting to TensorRT with RTX 2060 6gb vram it seems. i was wrong! does work with a rtx 2060!! though a very very small boost.
Issue -
State: open - Opened by Appolonius001 about 2 years ago
- 5 comments
#13 - Can only create TensorRT models using default settings
Issue -
State: closed - Opened by CptGabok about 2 years ago
- 1 comment
#12 - Not loading at all
Issue -
State: open - Opened by kriimakt about 2 years ago
- 5 comments
#11 - Failed to build pycuda
Issue -
State: closed - Opened by Kaiten10 about 2 years ago
- 4 comments
#10 - can't generate images above 768x768 resolution
Issue -
State: open - Opened by pellaaa93 about 2 years ago
- 12 comments
#9 - pycuda not installing properly
Issue -
State: open - Opened by zaazii about 2 years ago
- 5 comments
#8 - RuntimeError: Expected all tensors to be on the same device
Issue -
State: closed - Opened by JilekJosef about 2 years ago
- 3 comments
#7 - Tensorrt cannot appear on the webui
Issue -
State: open - Opened by GitGod76 about 2 years ago
- 11 comments
#6 - Can't install Pycuda
Issue -
State: closed - Opened by theoretischer about 2 years ago
- 5 comments
#5 - VRAM requirements?
Issue -
State: closed - Opened by sashasubbbb about 2 years ago
#4 - LD_LIBRARY_PATH for linux
Pull Request -
State: closed - Opened by szhublox about 2 years ago
- 1 comment
#3 - [05/27/2023-19:14:07] [TRT] [W] TensorRT was linked against cuDNN 8.9.0 but loaded cuDNN 8.7.0
Issue -
State: open - Opened by Cubey42 about 2 years ago
- 1 comment
#2 - ImportError: cannot import name 'sd_unet' from 'modules' (unknown location)
Issue -
State: closed - Opened by Cubey42 about 2 years ago
- 4 comments
#1 - Just wonder how you deal with dynamic shape using tensorRT 8.6
Issue -
State: open - Opened by tianyu-sz about 2 years ago