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).
Do people realize that, these interview question collection do not help? I think there is 2 things to address here:
- Interviewers will know "what is known" by every candidate (with the help of these pages) and harder questions will be asked
- If these questions are asked at >junior levels, then RUN! the work will not satisfy you. The interview should be fun, and show the creativity of the candidate. These ones could be answered by anyone who read it a few times. I would not like to work with somebody who only know the answers to these questions and not more
Everyone repeat after me: "we need a baseline model".
You should always try some "dumb" models first. You'd be surprised how hard is to beat (of course depends on your KPIs) a historical average model with a more sophisticated method.
Thank you for the input, I'll make sure to change these to make it more clear.