Patreon
Home / Videos / Almost Double Your Stable Diffusion Speed With TensorRT: The

Almost Double Your Stable Diffusion Speed With TensorRT: The Full 2023 Automatic1111 Guide

Automatic1111 SD Web UI 1-click installer scripts for RunPod or any Linux system, with SDXL, all ControlNet models and TensorRT RTX acceleration.

Published Oct 25, 2023 · 11,069 views · Watch on YouTube

Get the app and files

Automatic1111 RunPod & Linux Installer: SDXL, ControlNet & TensorRT

Automatic1111 RunPod & Linux Installer: SDXL, ControlNet & TensorRT

Automatic1111 SD Web UI 1-click installer scripts for RunPod or any Linux system, with SDXL, all ControlNet models and TensorRT RTX acceleration.

SDXL Speed Comparison: TensorRT vs xFormers and Torch + CUDA Versions

SDXL Speed Comparison: TensorRT vs xFormers and Torch + CUDA Versions

Stable Diffusion XL image generation speed in Automatic1111 on an RTX 3090 TI, comparing Torch, CUDA and xFormers versions with and without TensorRT.

Chapters

  1. 0:00 Introduction to how to utilize RTX Acceleration / TensorRT for 2x inference speed
  2. 2:15 How to do a fresh installation of Automatic1111 SD Web UI
  3. 3:32 How to enable quick SD VAE and SD UNET selections from settings of Automatic1111 SD Web UI
  4. 4:38 How to install TensorRT extension to hugely speed up Stable Diffusion image generation
  5. 6:35 How to start / run Automatic1111 SD Web UI
  6. 7:19 How to install TensorRT extension manually via URL install
  7. 7:58 How to install TensorRT extension via git clone method
  8. 8:57 How to download and upgrade cuDNN files
  9. 11:23 Speed test of SD 1.5 model without TensorRT
  10. 11:56 How to generate a TensorRT for a model
  11. 12:47 Explanation of min, optimal, max settings when generating a TensorRT model
  12. 14:00 Where is ONNX file is exported
  13. 15:48 How to set command line arguments to not get any errors during TensorRT generation
  14. 16:55 How to get maximum performance when generating and using TensorRT
  15. 17:41 How to start using generated TensorRT for almost double speed
  16. 18:08 How to switch to dev branch of Automatic1111 SD Web UI for SDXL TensorRT usage
  17. 20:33 The comparison of image difference between TensoRT on and off
  18. 20:45 Speed test of TensorRT with multiple resolutions
  19. 21:32 Generating a TensorRT for Stable Diffusion XL (SDXL)
  20. 23:24 How to verify you have switched to dev branch of Automatic1111 Web UI to make SDXL TensorRT work
  21. 24:32 Generating images with SDXL TensorRT
  22. 25:00 How to generate TensorRT for your DreamBooth trained model
  23. 25:49 How to install After Detailer (ADetailer) extension and what does it do explanation
  24. 27:23 Starting generation of TensorRT for SDXL
  25. 28:06 Batch size vs batch count difference
  26. 29:00 How to train amazing SDXL DreamBooth model
  27. 29:10 How to get amazing prompt list for DreamBooth models and use them
  28. 30:25 The dataset I used for DreamBooth training myself and why it is deliberately low quality
  29. 30:46 How to generate TensorRT for LoRA models
  30. 33:30 Where and how to see TensorRT profiles you have for each model
  31. 36:57 Generating LoRA TensorRT for SD 1.5 and testing it
  32. 39:54 How to fix TensorRT LoRA not being effective bug

About this video

Stable Diffusion Gets A Major Boost With RTX Acceleration. One of the most common ways to use Stable Diffusion, the popular Generative AI tool that allows users to produce images from simple text descriptions, is through the Stable Diffusion Web UI by Automatic1111. In today’s Game Ready Driver, NVIDIA added TensorRT acceleration for Stable Diffusion Web UI, which boosts GeForce RTX performance by up to 2X. In this tutorial video I will show you everything about this new Speed up via extension installation and TensorRT SD UNET generation.

Automatic Installer Of Tutorial ⤵️

https://www.patreon.com/posts/automatic-for-ui-86307255

Tutorial GitHub Readme File ⤵️

https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/Tutorial-Achieving-Significant-Stable-Diffusion-Speed-Improvement-With-RTX-Acceleration.md

0:00 Introduction to how to utilize RTX Acceleration / TensorRT for 2x inference speed

2:15 How to do a fresh installation of Automatic1111 SD Web UI

3:32 How to enable quick SD VAE and SD UNET selections from settings of Automatic1111 SD Web UI

4:38 How to install TensorRT extension to hugely speed up Stable Diffusion image generation

6:35 How to start / run Automatic1111 SD Web UI

7:19 How to install TensorRT extension manually via URL install

7:58 How to install TensorRT extension via git clone method

8:57 How to download and upgrade cuDNN files

11:23 Speed test of SD 1.5 model without TensorRT

11:56 How to generate a TensorRT for a model

12:47 Explanation of min, optimal, max settings when generating a TensorRT model

14:00 Where is ONNX file is exported

15:48 How to set command line arguments to not get any errors during TensorRT generation

16:55 How to get maximum performance when generating and using TensorRT

17:41 How to start using generated TensorRT for almost double speed

18:08 How to switch to dev branch of Automatic1111 SD Web UI for SDXL TensorRT usage

20:33 The comparison of image difference between TensoRT on and off

20:45 Speed test of TensorRT with multiple resolutions

21:32 Generating a TensorRT for Stable Diffusion XL (SDXL)

23:24 How to verify you have switched to dev branch of Automatic1111 Web UI to make SDXL TensorRT work

24:32 Generating images with SDXL TensorRT

25:00 How to generate TensorRT for your DreamBooth trained model

25:49 How to install After Detailer (ADetailer) extension and what does it do explanation

27:23 Starting generation of TensorRT for SDXL

28:06 Batch size vs batch count difference

29:00 How to train amazing SDXL DreamBooth model

29:10 How to get amazing prompt list for DreamBooth models and use them

30:25 The dataset I used for DreamBooth training myself and why it is deliberately low quality

30:46 How to generate TensorRT for LoRA models

33:30 Where and how to see TensorRT profiles you have for each model

36:57 Generating LoRA TensorRT for SD 1.5 and testing it

39:54 How to fix TensorRT LoRA not being effective bug