Creating a Customised Stable Diffusion with LoRA

Oded Golden (~oded)


0

Votes

Description:

Retraining stable diffusion from scratch is not feasible for me and you. However, in this talk I will show you how to “hack” the retraining with no budget nor special resources, using a LoRA model.

Large generative models such as stable diffusion take enormous resources to train, making retraining and fine tuning them less and less feasible. Fortunately, a technique called LoRA allows us to bypass this obstacle by training with 10,000 times less parameters, and thus creating a light-weight model dedicated to our use case.

In this talk I will walk you through how to retrain with LoRA so you can have your own dedicated Stable Diffusion model for generating anything from racoon memes to boba tea commercials. Using LoRA is free, does not require a deep understanding in ML or expensive GPUs, and I will show how to run it for free using Google’s Colab.

Speaker Info:

Oded Golden is a senior machine learning engineer with more than 10 years of engineering experience bringing products to live. He has a M.Sc. degree in computer science, specialising in deep learning.

Speaker Links:

https://www.linkedin.com/in/oded-golden/

Section: Data Science, AI & ML
Type: Talks
Target Audience: Intermediate
Last Updated: