You are getting the code that is required to generate the images which you can use with Google Colab (as you can get free GPUs there).
About the models you can use: literally any model (base model, LoRA) can be used, as these are handled automatically (you only need a download link from CivitAI or Huggingface or anywhere else)
Thank you for the input, I'll make sure to change these to make it more clear.
Thank you for the advice. Your write up was valuable to me. I also want to have a lean approach to the problem, I am just overwhelmed with the whole architecture which is needed around something which should be simple (as a pet project).
Thank you for the input, I'll make sure to change these to make it more clear.