This video will showcase how you can use Drupal as your end-to-end shop for taking a Stable Diffusion (text-to-image) model and finetune them with a concept like your own face for instance and reuse that for generation. All done in Drupal. No Python or scripting is needed!
This opens up a whole new world of personalization for you and your company. These models can then be used either to generate via the inference endpoints on Huggingface or to download them to other providers or run it completely locally.
The two services you need are Huggingface (free) for hosting the model and inference and Runpod to host GPU machines with enough juice to finetune.
The price for a SD1.4 model is around $0.5 and for a SD2 $1.
If you will signup for Runpod and like my videos, please use the following link so I can get access to more credits to play around even more.
Links
Drupal Huggingface module: https://www.drupal.org/project/huggingface
Test my generated airdpods model: https://huggingface.co/ivanboring/airpods
Runpod to credit me: https://github.com/ivanboring/drupal-dreambooth-finetune
Docker Hub: https://hub.docker.com/r/ivanboring/drupal-dreambooth-finetune
Repo for Docker: https://github.com/ivanboring/drupal-dreambooth-finetune
Huggingface: https://huggingface.co/