query

[AMITESHPATEL]

I hope this message finds you well. I recently came across your repository for Stable Diffusion in PyTorch and I must say, your effort in making the codebase minimal, and easy to read is commendable. I am new to generative models and your implementation has piqued my interest.
I was wondering if you could provide some insights into the training process of your Stable Diffusion model. Specifically, I am curious about the following:

1. Training Data: Could you please let me know on which dataset you trained your model? Understanding the dataset used would help me get a better understanding of the capabilities and limitations of the model.

2. Training Time: I'm also interested to know how much time it took for your model to train. This information will help me gauge the computational requirements and plan accordingly for any experiments or projects involving Stable Diffusion.

Moreover, I would like to know more about your approach to writing this code. Did you primarily refer to research papers, or did you take inspiration from other implementations? For instance, you mentioned using Andrej Karpathy's miniGPT. Could you share your thought process behind choosing this reference or any other methods you considered during your implementation?
I greatly appreciate your assistance and expertise in this matter. Thank you for your time and for sharing your work with the community. I look forward to your response.