Hey @ilaksh Let's talk over email. We have a lot of different options and details re the API that we're still considering and trying to improve with our partners
We're trying to streamline the process and explain it. Running the infra for this is hard. We are running on expensive A100 machines which are not easily available and not part of Google Colab infra.
There are lots of hyper-parameters one could toy with, and we're trying to hide those and give optimal results automatically.
Obviously this could all just be the start of it, and we might continue to develop on different directions where we see it's most fun :)
We're relying on Google's Dreambooth paper which differently from Text-Inversion, it does full model fine-tuning. This should help achieve higher fidelity results if you're trying to replicate the distinct features of your subject
Indeed we're working on that and explaining the technology behind is one of the things we're working on. Currently we're training a Stable Diffusion image-generation model, to the custom images that the user provide so that he can generate images of his specific subject consistently. This relies on a paper by Google called Dreambooth. So thank you mainly to Nathaniel Ruiz
Hi all, great to see someone posted our service :) We started working on this 3 weeks ago and are having real fun with the response. People are creating amazing stuff, and doing great experiments.