Home > Apps > Apps How To

How to Train Stable Diffusion with Your Images?

A Comprehensive Guide to Training Stable Diffusion with Your Images
Last Updated on August 11, 2023
How to Train Stable Diffusion with Your Images
PC Guide is reader-supported. When you buy through links on our site, we may earn an affiliate commission. Read More
You can trust PC Guide: Our team of experts use a combination of independent consumer research, in-depth testing where appropriate - which will be flagged as such, and market analysis when recommending products, software and services. Find out how we test here.

Using an AI art generator such as the Stable Diffusion is enjoyable and entertaining work and helpful in professional life. But did you know you could also use them to create unique images at your own trained Stable Diffusion? 

Let’s find out how. 

How to Train Stable Diffusion with Your Images?

To accomplish that, you would only need DreamBooth, and next follow the easy steps below:

  • Arrange for a faster, more stable GPU and VRAM, and click the “RUN” button to proceed.
  • Have DreamBooth ready and run it by clicking the play button.
  • Once you click the play button, log into the Hugging Face account. Log into it or create a free account if you don’t have one.
  • Once you navigate the settings page, click the “Access Tokens” and “Create New” buttons. It will generate a new access token, and you can rename it.
  • Next, click on the runtime and install the Xformers by clicking the play button.
  • Connect your Google Drive and set the new name as “Class Name.”
  • Next, you will be required to upload some reference images. We recommend using 6–20 images; you can view them there.
  • Next, you will use DreamBooth to train the AI model for all the uploaded reference images.
  • Once completed, convert your AI model into a ckpt format.
  • In the next two runtime processes below the interference category. You now have to prepare the freshly trained model of the textual prompts for the image generations. Once done, press the play button for every runtime to finish in a few minutes.
  • Lastly, type the textual prompts to generate the AI-trained images.

What is Image-To-Image or Img2Img Stable Diffusion?

The latest Stable Diffusion pipeline is the latest approach to generating images. It uses a deep generative model to generate images based on text prompts or an image.


Stable Diffusion is available for various uses in different models and ways. However, the main purpose is the same, which is to generate images.

Therefore, you can use the training model to train Stable Diffusion for your personalized image content. It is easy and does not require much time either.

Kevin is the Editor of PC Guide. He has a broad interest and enthusiasm for consumer electronics, PCs and all things consumer tech - and more than 15 years experience in tech journalism.