How To Install DreamBooth & Automatic1111 On RunPod & Latest Libraries - 2x Speed Up - cudDNN - CUDA

I have shown how to install latest version of Automatic1111 Web UI for Stable Diffusion and DreamBooth extension of Auto1111 on RunPod in this video. Moreover, I show how to upgrade to latest Cuda, Torch and cuDNN DLL files. With these upgrades the image generation speed literally doubles.

GitHub Readme File ⤵️

Download Auto Install Scripts ⤵️

Our Discord server ⤵️

If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 ⤵️

Technology & Science: News, Tips, Tutorials, Tricks, Best Applications, Guides, Reviews ⤵️

Playlist of StableDiffusion Tutorials, Automatic1111 and Google Colab Guides, DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img ⤵️

0:00 Introduction to installation of DreamBooth on RunPod
0:28 How to register RunPod and login and select which Pod for DreamBooth training
0:45 How to deploy a RunPod and customize deployment
0:55 Which template to select for Automatic1111 & DreamBooth on RunPod
2:30 How to open JupyterLab interface on RunPod
2:40 How to install with automatic install scripts
3:05 Manual installation starts
3:37 First part of auto install completed - start second and final part
4:01 Continuing manual installation
4:18 How to install latest version of xFormers for Stable Diffusion
4:55 Automatic installation completed and ready to use
5:18 Continuing manual installation
6:22 How to start Automatic1111 Web UI
6:40 How to connect web ui interface on RunPod
6:50 How to set default VAE for best VAE to get better image quality
7:24 Image generation speed test on RunPod Stable Diffusion Automatic1111
8:15 How to upgrade to the latest version of xFormers
8:36 How to start again after restart of your Pod
9:30 Huge speed drop after restarting pod
9:49 The reason of huge it/s speed drop after restarting RunPod
11:29 With which command double the speed after restarting your Pod
12:12 Side by side speed comparison of default cuDNN vs my latest cuDNN
12:46 Batch size 8 speed test results

Installing Latest Automatic1111 Web UI, DreamBooth Extension, CUDA, and cuDNN DLL Libraries on RunPod | Detailed Tutorial

Welcome to this detailed video tutorial where I will guide you through the process of installing the latest Automatic1111 Web UI, DreamBooth extension, CUDA, and cuDNN DLL libraries on RunPod. If you're lacking a powerful GPU, RunPod is the ideal solution for utilizing Stable Diffusion with Automatic1111 Web UI. To facilitate your learning, I have prepared an amazing GitHub readme file that contains all the necessary commands which I will demonstrate step-by-step.

We will start by initiating our RunPod, and you can register or login using the provided link. Once logged in, navigate to the community cloud and select the desired deployment. While the RTX 3090 is my preferred GPU for DreamBooth training due to its exceptional speed and performance, for this tutorial, we will utilize the RTX 4090. Customize the deployment by adjusting the volume disk to approximately 110 gigabytes and select the "Stable Diffusion web automatic" template.

Please note that the version may vary when you watch this tutorial, but always opt for the "web automatic" version. Proceed with the deployment by clicking "Continue" and then "Deploy". This will initiate the manual installation process. Additionally, we will start another instance for automatic installation as I have prepared an automatic installation script. Follow the same steps for deployment, and name this instance "auto install".

[SECourses]

If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 ⤵

Technology & Science: News, Tips, Tutorials, Tricks, Best Applications, Guides, Reviews ⤵

Playlist of StableDiffusion Tutorials, Automatic1111 and Google Colab Guides, DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img ⤵

[Ekkivok]

FIRST ! thanks to answered my request <3 You're the best !

[FilmStir]

I don't understand why it takes so many steps? Why isn't Automatic1111 just in Runpod as standard?

[Lacher-Prise]

WoW !! what a master class !! thank you very much !! GG congratulations 🎉
Team Shibuntu

[Noname-muhm]

Thank You Very Much For this tutorial and the amount of work you put in all your videos. I'm going to follow your guide and comment to confirm if everything went smoothly :)

[SerhatGKE]

Öncelikle bu öğretici video için teşekkürler. Bu tarz içerikler ingilizce olarak çok sayıda mevcut ama türkçe kaynak yok denecek kadar az. Ben bir türk genci olarak yapay zekaya çok hevesliyim ama yabanci dilimin olmamasından kaynaklı bu konuda çok hızlı ilerleyemiyorum. Keşke sizin gibi içerik üreticileri bu tarz videoları türkçe olarak üretse de biz gençlerin de işi kolaylaşsa biraz daha.

[omriAI]

I don't understand why you didn't choose the fast stable diffusion template. It is much easier and faster. What are the advantages of this installation?

[funnyknowledge]

Hey:) what’s the difference between this video and the one you posted last night? Regardless thank you for your time and effort 🙌

[mldeeplearningdatascience]

Sir, i trained my realistic model as you explained in the end of photo studio video. After tha ti'm trying to use automatic111, it is stuck on loading. I have restarted the pod multiples times. I also added --no-gradio-queue in the argument as i saw it online but still its not working. Any solution sir? So that i can create the x/y/ z plot with my models.

[digital]

Thanks for this tutorial. Can you do a video on how to install and run temporalkit correctly on runpod?

[thinhnguyensb]

i replaced xformers (0.0.21.dev549) with argument --opt-sdp-attention the result is 5% faster. Also for windows when I disable disabling Hardware GPU scheduling, performance increases by 10%

[diegopons]

Hey! Is Dreambooth extension working better than kohya now!? 😊

[mldeeplearningdatascience]

Thank you Sir for this great tutorial! Sir, everytime i do the entire process and restart the pod after manual installation, my Jupyterlab doesn't work. It's always "Bad gateway Error code 502". Everything worked fine the first time but after doing all the steps it happens.

[JadhuGhr-lzen]

Right now I unable to download file from run pid please help me

[AaliDGr]

Is it free same like kabble offers ?? or something like it??

[MC-ujby]

at the age of AI, we still have to hassle with so much installation proceedures