Automatic1111 Stable Diffusion DreamBooth Guide: Optimal Classification Images Count Comparison Test
Sign up RunPod: https://bit.ly/RunPodIO. Our Discord : https://discord.gg/HbqgGaZVmr. New best training settings for DreamBooth training in Automatic1111 Web UI. 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 🥰 https://www.patreon.com/SECourses
Published Feb 25, 2023 · 28,525 views · Watch on YouTube
Chapters
- 0:00 Introduction to Best Settings of DreamBooth training experiment
- 0:56 How to close initially started Web UI instance on RunPod Stable Diffusion template
- 2:20 Which RunPod machine you should pick for DreamBooth training and why
- 2:48 The used versions in this experiment such as Automatic1111 version, xformers version, DreamBooth version
- 4:20 Best DreamBooth settings for 0 classification images
- 4:45 How to continue DreamBooth training from a certain checkpoint
- 5:12 Used command line arguments for best DreamBooth training
- 5:20 Used extensions list for best DreamBooth training
- 5:45 Starting to set parameters for 0 classification images - equal to fine tuning
- 6:45 Used training dataset and what dataset features you need
- 7:45 Setting concepts tab of DreamBooth training
- 8:00 When you should use FileWords and why you should use for fine tuning and how to do fine tuning
- 10:15 Best training setup parameters for DreamBooth training when using classification images
- 11:28 How to calculate number of steps for each epoch
- 13:17 All trainings are completed
- 13:49 Comparison of sample and sanity sample images generated during training
- 13:55 Analysis of 0x classification samples
- 14:41 Analysis of 1x classification samples
- 15:14 Analysis of 2x classification samples
- 15:36 Analysis of 5x classification samples
- 16:12 Analysis of 10x classification samples
- 16:34 Analysis of 25x classification samples
- 16:45 Analysis of 50x classification samples
- 17:28 Analysis of 100x classification samples
- 17:49 Analysis of 100x classification samples
- 18:09 Comparing each checkpoint in all of the trained models
- 18:46 How to use x/y/z plot to check different training checkpoints
- 19:51 All grids are generated and how did i download them
- 20:40 Analysis of 0x classification x/y/z grid images
- 21:58 Analysis of 1x classification x/y/z grid images
- 23:10 Analysis of 2x classification x/y/z grid images
- 24:03 Analysis of 5x classification x/y/z grid images
- 25:00 Analysis of 10x classification x/y/z grid images
- 25:36 Analysis of 25x classification x/y/z grid images
- 26:15 Analysis of 50x classification x/y/z grid images
- 27:27 Analysis of 100x classification x/y/z grid images
- 28:02 Analysis of 100x classification x/y/z grid images
- 29:00 Summary of the experiment
- 29:40 Very important speech part
About this video
Sign up RunPod: https://bit.ly/RunPodIO. Our Discord : https://discord.gg/HbqgGaZVmr. New best training settings for DreamBooth training in Automatic1111 Web UI. 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 🥰 https://www.patreon.com/SECourses
Playlist of #StableDiffusion Tutorials, #Automatic1111 and Google Colab Guides, #DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img:
https://www.youtube.com/playlist?list=PL_pbwdIyffsmclLl0O144nQRnezKlNdx3
Easiest Way to Install & Run Stable Diffusion Web UI on PC by Using Open Source Automatic Installer:
How to use Stable Diffusion V2.1 and Different Models in the Web UI - SD 1.5 vs 2.1 vs Anything V3:
Zero To Hero Stable Diffusion DreamBooth Tutorial By Using Automatic1111 Web UI - Ultra Detailed:
Sketches into Epic Art with 1 Click: A Guide to Stable Diffusion ControlNet in Automatic1111 Web UI:
Ultimate RunPod Tutorial For Stable Diffusion - Automatic1111 - Data Transfers, Extensions, CivitAI:
8 GB LoRA Training - Fix CUDA & xformers For DreamBooth and Textual Inversion in Automatic1111 SD UI:
2400 Photo Of Man classification images:
https://drive.google.com/file/d/1qBf8VyUbmPNalKqm076yOsQjE8BrcG7R/view
0:00 Introduction to Best Settings of DreamBooth training experiment
0:56 How to close initially started Web UI instance on RunPod Stable Diffusion template
2:20 Which RunPod machine you should pick for DreamBooth training and why
2:48 The used versions in this experiment such as Automatic1111 version, xformers version, DreamBooth version
4:20 Best DreamBooth settings for 0 classification images
4:45 How to continue DreamBooth training from a certain checkpoint
5:12 Used command line arguments for best DreamBooth training
5:20 Used extensions list for best DreamBooth training
5:45 Starting to set parameters for 0 classification images - equal to fine tuning
6:45 Used training dataset and what dataset features you need
7:45 Setting concepts tab of DreamBooth training
8:00 When you should use FileWords and why you should use for fine tuning and how to do fine tuning
10:15 Best training setup parameters for DreamBooth training when using classification images
11:28 How to calculate number of steps for each epoch
13:17 All trainings are completed
13:49 Comparison of sample and sanity sample images generated during training
13:55 Analysis of 0x classification samples
14:41 Analysis of 1x classification samples
15:14 Analysis of 2x classification samples
15:36 Analysis of 5x classification samples
16:12 Analysis of 10x classification samples
16:34 Analysis of 25x classification samples
16:45 Analysis of 50x classification samples