Back
News
March 6th, 2023
minute read

DreamBooth on Runpod: How to Train for Great Results

Zhen Lu
Zhen Lu

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5
Heading 6

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

Block quote

Ordered list

  1. Item 1
  2. Item 2
  3. Item 3

Unordered list

  • Item A
  • Item B
  • Item C

Text link

Bold text

Emphasis

Superscript

Subscript

Ever wanted to start generating your own unique creations using your own custom dreambooth model, but didn't have any idea where to start or what settings to choose? Well, one of our users decided to put together this epically comprehensive guide by running a ton of tests on Runpod! I'm hoping it will give you a good starting point, and maybe solve some of the common problems when getting started with dreambooth training. Enjoy!

Update: Here's how to fix some of the issues when running with the latest versions of dreambooth/automatic1111

Original Video:

Warning: it contains a TON of content

Here's the TOC

0:00 Introduction

0:49 Setup and Install

7:15 Starting experiments

15:49 How to add more disk space to your existing Runpod

17:08 xformers related bug error

18:20 How to resume a failed training

18:49 All tests have been completed time to check their training samples

25:36 Finding a good seed to compare all checkpoints within each trained model

48:30 How to download all decided best checkpoints via runpodctl

49:09 How to use web terminal when jupyter connection is not available

49:56 Where to put downloaded safetensors model files  

51:05 Final Comparison

1:00:20 Conclusion

Newly  Features

We've cooked up a bunch of improvements designed to reduce friction and make the.

Create ->
Newly  Features

We've cooked up a bunch of improvements designed to reduce friction and make the.

Create ->
Newly  Features

We've cooked up a bunch of improvements designed to reduce friction and make the.

Create ->
Newly  Features

We've cooked up a bunch of improvements designed to reduce friction and make the.

Create ->
We're officially SOC 2 Type II Compliant
You've unlocked a referral bonus! Sign up today and you'll get a random credit bonus between $5 and $500
You've unlocked a referral bonus!
Claim Your Bonus
Claim Bonus
Blog

DreamBooth on Runpod: How to Train for Great Results

DreamBooth can generate amazing, highly personalized images—but only if you train it well. In this post, Zhen walks through best practices for getting the most out of DreamBooth on Runpod. Learn what datasets to use, when to use regularization, how many steps are ideal, and which hyperparameters to tweak.

Author
Zhen Lu
Date
March 6, 2023
Table of contents
Share
DreamBooth on Runpod: How to Train for Great Results

Ever wanted to start generating your own unique creations using your own custom dreambooth model, but didn't have any idea where to start or what settings to choose? Well, one of our users decided to put together this epically comprehensive guide by running a ton of tests on Runpod! I'm hoping it will give you a good starting point, and maybe solve some of the common problems when getting started with dreambooth training. Enjoy!

Update: Here's how to fix some of the issues when running with the latest versions of dreambooth/automatic1111

Original Video:

Warning: it contains a TON of content

Here's the TOC

0:00 Introduction

0:49 Setup and Install

7:15 Starting experiments

15:49 How to add more disk space to your existing Runpod

17:08 xformers related bug error

18:20 How to resume a failed training

18:49 All tests have been completed time to check their training samples

25:36 Finding a good seed to compare all checkpoints within each trained model

48:30 How to download all decided best checkpoints via runpodctl

49:09 How to use web terminal when jupyter connection is not available

49:56 Where to put downloaded safetensors model files  

51:05 Final Comparison

1:00:20 Conclusion

Build what’s next.

The most cost-effective platform for building, training, and scaling machine learning models—ready when you are.

You’ve unlocked a
referral bonus!

Sign up today and you’ll get a random credit bonus between $5 and $500 when you spend your first $10 on Runpod.