Addition

Share this post

AI-Self Portraits

addition.substack.com

Discover more from Addition

Insights and experiments at the intersection of Generative AI and marketing.
Over 2,000 subscribers
Continue reading
Sign in

AI-Self Portraits

Training Stable Diffusion On Myself

Paul Aaron
Nov 23, 2022
2
Share this post

AI-Self Portraits

addition.substack.com
Share

A couple of weeks ago, someone asked me for a headshot for a speaking engagement. I didn't have one – at least not one that was recent – so I considered my options. Could I use AI to generate my new headshot? 

AI image generation models like DALLE-2 and Stable Diffusion have consumed an incredible amount of images from the web. But unless you're internet famous, these AI models will struggle to generate accurate pictures of you.

To get around this, researchers have learned how to train image models on new visual concepts. This technique is generally referred to as "Dream Booth." It was first published in a research paper from Google in August and has since been replicated by open-source developers using Stable Diffusion.  

Training the Model

To get started we provide the model with a few dozen images of me, which we teach it to associate with a random keyword.

Examples of training images used to train Stable Diffusion.

Image Generation

Once trained, the model can generate new images of me whenever we prompt it with my unique keyword. I can combine this keyword with a wide range of prompts enabling me to explore various styles.

Here's me as an astronaut. 
Here's a douchey business shot.
This one's more my speed.

Future Use Cases

Beyond solving my headshot problem, a wide range of commercial use cases will benefit from this technology as it continues to improve. For example:

  • Automotive companies that spend millions on 3D Renders may find more flexibility and creative possibilities training AI models to understand their new lineup of cars. 

  • Advertisers could generate personalized ads that show me products in the situations most likely to appeal to me.

  • Future versions of this technology could be used to generate photo-realistic avatars of me within virtual environments like gaming and VR.

As always, reply to this email if you have any comments or questions.


Are you AI Curious?

  • Visit our website to learn about the work we do

  • Read about us in the Wall Street Journal

  • Follow us on Twitter

2
Share this post

AI-Self Portraits

addition.substack.com
Share
Comments
Top
New
Community

No posts

Ready for more?

© 2023 Addition Technologies, Inc
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing