Home
Artists
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register
Partychan Telegram Live Sex ThePornDude
Home Artists Posts Import Register

1 Click Installer for Automatic1111 SD Web UI, SDXL, ControlNet, All ControlNet Models, TensorRT (RTX Accelerator) on Windows (Patreon)

Published:
2024-06-05 22:45:00
Edited:
2024-06-06 20:18:39
Imported:
Tags:

Downloads

Content

Join discord and tell me your discord username to get a special rank : SECourses Discord

Patreon exclusive posts index

6 June 2024 Update

  • Zip files updated to V8 : Auto1111_V8.zip

  • TensorRT repo updated and now supports LoRAs too perfectly

  • Always installs latest version of Automatic1111, After Detailer (ADetailer), TensorRT, Reactor, ControlNet and it's all models, best SDXL and SD 1.5 models

  • Torch version upgraded to 2.3.0 and xFormers upgraded to 0.0.26.post1

  • All errors fixed, working perfect with amazing speeds

  • The files are renamed as below

  • After installing TensorRT start Automatic1111, then close it, and run TensorRT installer again to fix that error message

  • Before running installers close your running Automatic1111 CMD

  • Double click on .bat files to start installers

  • Automatically downloaded models are sd_xl_base_1.0_0.9vae (fixed VAE and named as sd_xl_base_1.0), Realistic_Vision_6, RealVisXL_V4, Hyper_Realism_V3

  • It downloads all ControlNet models including IpAdapters, Face ID, InstantId for both SD 1.5 and SDXL

  • ControlNet auto download list updated to latest

  • Edit download_models .py file if you want to add remove models before starting to install

  • How to use TensorRT properly check these 2 below images

  • sd_unet_enable_TensorRT.png , tensor_RT_settings.png

17 January 2024 Update

TensorRT - Huge Speed Up

  • Watch below tutorial to learn more about TensorRT and its auto installer

  • https://youtu.be/kvxX6NrPtEk

  • Only 64 by 64 pixel increment and decrement of TensorRT profiles will work

  • If you want to do high res fix, make sure that your resolutions include them as well

  • The updated downloader file will display download status like below

Requirements

  • Follow below tutorial to install Python 3.10.11, Git, FFmpeg and C++ tools

  • https://youtu.be/-NjNy7afOQ0

  • I suggest to install directly into your C drive as shown in video

  • C++ tools super important to use Face IP Adapter in ControlNet since we need to install insight face library

  • You can also edit webui-user .bat file inside stable-diffusion-webui folder and add remove command line arguments if you need

  • You can find command line arguments here : https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings

  • At a later time if you decide to update your web ui, open a cmd in your Automatic1111 web UI folder and do git pull as shown in below video

  • https://youtu.be/-NjNy7afOQ0

  • You can have multiple Automatic1111 installation and each one of them will be unique and will not conflict with others since each one will have their own venv (virtual environment) folder

How To Install ControlNet & Download Models

  • ControlNet is the very best extension of Stable Diffusion community. Extension repo : https://github.com/Mikubill/sd-webui-controlnet

  • If you want to learn ControlNet watch below amazing 90 minute video

  • https://youtu.be/3E5fhFQUVLo

  • Make sure that you have installed C++ tools before as shown in below video to be able to install insight face and use IP-Adapter-FaceID models

  • https://youtu.be/-NjNy7afOQ0

  • After installing Automatic1111 Web UI, close it, run install_controlNet_and_download_models .bat file

  • It will install insight face library on your Auto1111 installation venv and also download IP-Adapter-FaceID LoRA models

  • Then it will execute control_net_downloader .py file and download 52+ ControlNet models

  • If you don't want some of them models to be downloaded, edit control_net_downloader .py file before and remove the ones that you don't need

  • control_net_downloader .py file will download all existing known ControlNet models for both SD 1.5 and SDXL models like shown in this screenshot : controlnet downloader.png

  • After all download is completed, start your Automatic1111 SD Web UI and enjoy using all available ControlNet models including latest IP-Adapter-FaceID and InstantId

  • To learn more about how to use IP-Adapter-FaceID read below thread:

  • https://github.com/Mikubill/sd-webui-controlnet/discussions/2442

  • Alternatively we have a standalone amazing Gradio Web UI and 1 click installer for IP-Adapter-FaceID shared in below Patreon post

  • https://www.patreon.com/posts/ip-adapter-0-app-95759342

  • To learn more about how to use InstantId read below thread:

  • https://github.com/Mikubill/sd-webui-controlnet/discussions/2589

  • Alternatively we have a standalone amazing Gradio Web UI and 1 click installer for InstantId shared in below Patreon post. Our Gradio Web APP is more optimized and supports FP16 and lower VRAM as well

  • https://www.patreon.com/posts/1-click-very-gui-97769887

  • Total file size downloaded will be close to 50GB so be ready



Files

Comments

Rafał Ryniak

"Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check" Czy to znaczy że na mojej karcie Radeon r280 SDXL nie ruszy?

Furkan Gözükara
>>114930224

ah you are using AMD gpu. for AMD gpus i never worked but there is this fork can you test it? https://github.com/lshqqytiger/stable-diffusion-webui-directml

Rafał Ryniak

Dziękuję bardzo jutro nad tym popracuje

Anonymous

Is there a way to place all models in the same folder and refer the GUI to them? for example, I have one installation for img2img/txt2img and another installation for Deforum, so I don't want to have duplicates of models/lora/controlnet folders. is there a way to place them all in one place and tell the installers where to find them?

Furkan Gözükara
>>115924768

it depends on each extension. but you can tell automatic1111 to look where for each model. it has starting parameters : https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings

Anonymous

I am using python 3.10/12150.1013 and I run the bat and it downloads the models completely, and exits terminal automatically. When I navigate back to the execution location, the models folder is filled and seems finished. 12 or so gigs size-wise. When I try to run auto_1111_sdxl.bat again it immediately removes all data from the installer script and starts over again. This is driving me up the wall with the quality of my internet connection. What gives?

Furkan Gözükara
>>117196962

yes it will terminate CMD once installation has been completed . if you run again it deletes and start from 0. but i can modify script. how you would like it to behave? by the way after it is completed you run Automatic1111 Web UI instance from inside the folder automatic_web_ui with webui-user.bat

Michael Harleman

I got annoying startup errors having something to do with cudnn three times before the interface would start. I found this post that describes a fix which seemed to work: https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT/issues/27#issuecomment-1767570566. I used the fix and it seemed to get rid of the errors, but the model won't generate. It gets stuck on the last step and never generates the ONNX model file. I ended up restarting the process from the beginning of the tutorial. I'll see if the automatic installer works if I don't make any mistakes. If I may offer a suggestion, I think you clearly know what you are doing, but your students have never seen any of the things you are demonstrating done before, so they can't absorb it nearly as fast as you can cram it into an hour and a half video presentation. I have calculated that for every 30 minutes of your tutorials it will take me 8 to 10 hours to understand what I need to do and fix all the errors I manage to create. Not everyone that takes your classes is fit for Harvard or MIT.

Furkan Gözükara
>>122244204

you have error during generating tensorRT or when using can you clarify that? if you have error when using try to switch to the dev branch of automatic1111

Michael Harleman

TensorRT seems to be working fine. I'm not sure why I get the errors, but I spoke to you on Discord and you told me to just ignore the errors. The fix was working however when I tried it, so you might want to look at it.

Furkan Gözükara
>>122262927

hello again. i just tested scripts. worked fine. what was the error you were getting with scripts and how you solved? I tested with dev branch of automatic1111

Hassan Alhassan

am getting stuck here, Building wheels for collected packages: tensorrt Building wheel for tensorrt (pyproject.toml) ... /

Furkan Gözükara
>>124739841

hello. what is your python version and how did you install? i just made a video to show how to install properly : https://youtu.be/-NjNy7afOQ0

Hassan Alhassan

ill reinstall it again while going through the video, it was working on the previous version fine. python 3.10.11

Anonymous

Hi Mate, could you make easy installation and tutorial for X-adapter ? Im to stupid to make it run :D anyway love your stuff, regards

Furkan Gözükara
>>130053495

Hello I just checked and no extensions are made for it yet. We need firs either Automatic1111 extension or Forge extension. I started following both

Pallavi Chauhan

Have you made an installer for DRAG GAN gradio app?

C. Jonas

Hi Mate, the installation of install_automatic1111_Web_UI.bat gives the following error: installing stuff stuff stuff then: Collecting mpmath>=0.19 Using cached https://download.pytorch.org/whl/mpmath-1.3.0-py3-none-any.whl (536 kB) Installing collected packages: mpmath, urllib3, typing-extensions, sympy, pillow, numpy, networkx, MarkupSafe, idna, fsspec, filelock, charset-normalizer, certifi, requests, jinja2, torch, torchvision Successfully installed MarkupSafe-2.1.5 certifi-2024.2.2 charset-normalizer-3.3.2 filelock-3.13.1 fsspec-2024.2.0 idna-3.6 jinja2-3.1.3 mpmath-1.3.0 networkx-3.2.1 numpy-1.26.4 pillow-10.2.0 requests-2.31.0 sympy-1.12 torch-2.1.2+cu121 torchvision-0.16.2+cu121 typing-extensions-4.10.0 urllib3-2.2.1 [notice] A new release of pip available: 22.3.1 -> 24.0 [notice] To update, run: g:\Auto1111_secourses\stable-diffusion-webui\venv\Scripts\python.exe -m pip install --upgrade pip Installing clip Installing open_clip Installing xformers Cloning assets into G:\Auto1111_secourses\stable-diffusion-webui\repositories\stable-diffusion-webui-assets... Cloning into 'G:\Auto1111_secourses\stable-diffusion-webui\repositories\stable-diffusion-webui-assets'... remote: Enumerating objects: 20, done. remote: Counting objects: 100% (20/20), done. remote: Compressing objects: 100% (18/18), done. remote: Total 20 (delta 0), reused 20 (delta 0), pack-reused 0 Receiving objects: 100% (20/20), 132.70 KiB | 310.00 KiB/s, done. Traceback (most recent call last): File "g:\Auto1111_secourses\stable-diffusion-webui\launch.py", line 48, in main() File "g:\Auto1111_secourses\stable-diffusion-webui\launch.py", line 39, in main prepare_environment() File "g:\Auto1111_secourses\stable-diffusion-webui\modules\launch_utils.py", line 410, in prepare_environment git_clone(assets_repo, repo_dir('stable-diffusion-webui-assets'), "assets", assets_commit_hash) File "g:\Auto1111_secourses\stable-diffusion-webui\modules\launch_utils.py", line 197, in git_clone run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}") File "g:\Auto1111_secourses\stable-diffusion-webui\modules\launch_utils.py", line 115, in run raise RuntimeError("\n".join(error_bits)) RuntimeError: Couldn't checkout {name}'s hash: {commithash}. Command: "git" -C "G:\Auto1111_secourses\stable-diffusion-webui\repositories\stable-diffusion-webui-assets" checkout 6f7db241d2f8ba7457bac5ca9753331f0c266917 Error code: 128 stderr: fatal: detected dubious ownership in repository at 'G:/Auto1111_secourses/stable-diffusion-webui/repositories/stable-diffusion-webui-assets' 'G:/Auto1111_secourses/stable-diffusion-webui/repositories/stable-diffusion-webui-assets' is on a file system that does not record ownership To add an exception for this directory, call: git config --global --add safe.directory G:/Auto1111_secourses/stable-diffusion-webui/repositories/stable-diffusion-webui-assets Press any key . . .

Furkan Gözükara
>>131245521

try to install another disk. looks like you have permission issues for some reason on your computer. stderr: fatal: detected dubious ownership in repository at

C. Jonas

Thanks for the update for windows and thanks for your hard work! I really learned so much with your tutorials and programs / scripts!

C. Jonas

Another question: Can i use tensorrt with controlnet? I read that many controlnet models or preproccessors do not work with tensorrt installed.

Franco Acosta Diaz

Hello I Have this Error: A tensor with all NaNs was produced in VAE. Web UI will now convert VAE into 32-bit float and retry. To disable this behavior, disable the 'Automatically revert VAE to 32-bit floats' setting. To always start with 32-bit VAE, use --no-half-vae commandline flag. ========================================================================================== *** Error running process_batch: /workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py Traceback (most recent call last): File "/workspace/stable-diffusion-webui/modules/scripts.py", line 808, in process_batch script.process_batch(p, *script_args, **kwargs) File "/workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py", line 302, in process_batch if self.idx != sd_unet.current_unet.profile_idx: AttributeError: 'NoneType' object has no attribute 'profile_idx' --- 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 *** Error running process_batch: /workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py<03:36, 3.51it/s] Traceback (most recent call last): File "/workspace/stable-diffusion-webui/modules/scripts.py", line 808, in process_batch script.process_batch(p, *script_args, **kwargs) File "/workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py", line 302, in process_batch if self.idx != sd_unet.current_unet.profile_idx: AttributeError: 'NoneType' object has no attribute 'profile_idx' --- 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:05<00:00, 3.79it/s] *** Error running process_batch: /workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py<03:05, 3.98it/s] Traceback (most recent call last): File "/workspace/stable-diffusion-webui/modules/scripts.py", line 808, in process_batch script.process_batch(p, *script_args, **kwargs) File "/workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py", line 302, in process_batch if self.idx != sd_unet.current_unet.profile_idx: AttributeError: 'NoneType' object has no attribute 'profile_idx' --- 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:05<00:00, 3.82it/s] Reusing loaded model model/francoV1-step00001856.safetensors [549bc545a3] to load model/francoV1-step00003712.safetensors:54<03:11, 3.75it/s] Calculating sha256 for /workspace/stable-diffusion-webui/models/Stable-diffusion/model/francoV1-step00003712.safetensors: d81dc5a6b805f24f533d97d787dd9e2ab105cea38731b275126c3b71ccb04b4f Loading weights [d81dc5a6b8] from /workspace/stable-diffusion-webui/models/Stable-diffusion/model/francoV1-step00003712.safetensors Applying attention optimization: xformers... done. Weights loaded in 297.5s (send model to cpu: 3.4s, calculate hash: 8.8s, load weights from disk: 0.2s, apply weights to model: 252.2s, apply half(): 15.3s, apply dtype to VAE: 15.3s, move model to device: 2.3s). *** Error running process_batch: /workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py Traceback (most recent call last): File "/workspace/stable-diffusion-webui/modules/scripts.py", line 808, in process_batch script.process_batch(p, *script_args, **kwargs) File "/workspace/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py", line 302, in process_batch if self.idx != sd_unet.current_unet.profile_idx: AttributeError: 'NoneType' object has no attribute 'profile_idx'

Furkan Gözükara
>>132219086

when did you exactly got this error? without using TensorRT? it was giving error but still working last time i tried unless you compile TensorRT on that specific model. please give more context

・F・リュウ ゼリアス

Latest version as of March 14, 2024 auto installer Open the installer_auto1111_v6 ZIP file sequentially install_automatic1111_Web_UI ↓ install_controlNet_and_download_models ↓ install_TensorRT If you do ↓ WARNING: Skipping nvidia-cudnn-cu11 as it is not installed. A message appears saying that CUDA11 is not installed. Is it okay to install CUDA? Since it says +cu121, is CUDA12.1 good? Is it okay to download and install CUDA11.6 normally? Skip it for now update_torch_xformers_install_adetailer ↓ download_TensorRT_optional ↓ Here too, it was written on WEB/YouTube that it says 0.1.2.3.4.5. When I run 0. Download all models 1. Download Realistic Vision 5.1 Tensor files 2. Download SD 1.5 Base Tensor files 3. Download Rev Animated Base 1.2.2 Tensor files 4. Download SDXL Base 1.0 Tensor files There were only 5 items. For now, I pressed 0 and converted everything, but if If you run this also on the SDXL model downloaded later in Civitai Will it be added to the WEB-UI TensorRT profile? Currently, even if I start the WEB-UI without being able to run this install_TensorRT batch file, the TensorRT tab will appear this time. In the webui-user batch file Although only --xformers is written, Do I need to include --no-half-vae, --medvram, and --lowvram? YouTube said that if I don't include them, a bug will occur, but is it okay to not include them? --opt-sdp-no-mem-attention f Can I include it? lastly Is stable-diffusion-webui-forge applicable? Thank you in advance.

C. Jonas

Hi Furkan, when selecting Controlnet -> IP-Adapter -> IP-Adapter-Auto Preprocessor and ip-adapter-faceid-plusv2_sd15 [6e14fc1a] Model, i get the following red error message in the console. When installing a1111 from scratch it also gives an error when installing onnxruntime and all the dependencies, stating something about cuda 12 and incompatibilty with onnxruntime? I guess this leads the error below? Can you check? 2024-05-20 11:29:59,858 - ControlNet - INFO - Preview Resolution = 512 2024-05-20 11:29:59,858 - ControlNet - INFO - ip-adapter-auto => ip-adapter_face_id_plus 2024-05-20 11:29:59.9806034 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "g:\installer_auto1111\stable-diffusion-webui\venv\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: G:\installer_auto1111\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads\insightface\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0 2024-05-20 11:30:00.5415761 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "g:\installer_auto1111\stable-diffusion-webui\venv\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: G:\installer_auto1111\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads\insightface\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0 2024-05-20 11:30:00.6250399 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "g:\installer_auto1111\stable-diffusion-webui\venv\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: G:\installer_auto1111\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads\insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0 2024-05-20 11:30:00.7516377 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "g:\installer_auto1111\stable-diffusion-webui\venv\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: G:\installer_auto1111\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads\insightface\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0 2024-05-20 11:30:00.9349707 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "g:\installer_auto1111\stable-diffusion-webui\venv\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Furkan Gözükara
>>138487425

if you get error during installation that means your C++ tools is not properly installed : https://youtu.be/-NjNy7afOQ0 also make sure that default python is 3.10.11 i installed several times yesterday perfectly working no errors

KwotheEragon

Thx so much, i just found your amazing youtube video. I am so hapapy there is more, more on patreon. All your work and tutorilas that is masterpiece of AI. I think there is nothing commpared to your youtobe and your patreon. Thx

KwotheEragon

:-) I was fist happy but now i am not happy anymore. I found out that this new installer doenst work with dreambooth. It would have save me a lot of time, if there had been a notice about this.

Furkan Gözükara
>>141386318

for dreambooth you need to have a specific version here : https://www.patreon.com/posts/auto-installer-84773926

jonathan sanchez

Are the .yaml files no longer necessary? are they obsolete? Your ControlNet model download script does not download them. thank you for your work, honestly it's one of the best you can find on the internet.