Thank you:)

Thank you so much:)

Thank you so much @nikv and @curangel :)

Definitely. More the better:)

Looking forward to your results too:)

Hi @dbddv01! I duplicated most of the images by flipping them horizontally, so I had a total of 132 images. Regarding the selection criteria, it depends on what you want to do from the model you create.

Thank you so much:). Like I have said before, you were an inspiration!

Hi @eve66 . Thank you so much:). You don’t need a modern computer to do all this. Any device which can run a modern browser and a Google Colab subscription is sufficient. Just follow Kaliyuga's tutorial...

These images are getting better and better!

Thank you so much:)

Thank you:)

Check this out :)

Hey, thank you so much:) AI is a great tool for people who are not so artistic too(in the traditional sense), like me:)

It can already happen... Kaliyuga's pixel art diffusion can be used to generate backgrounds or even art and assets for pixel art games. She is also working on a sprite sheet diffusion model, so we can

Thank you:). She is doing much more... She is more like an AI scientist!

Thank you so much @jotakrevs and @curangel :)

Thank you @bhattg and @indiaunited :)

I would like to add one thing. If your dataset consists of images in 256x256 or 512x512 format only, when you try to generate an image higher than this resolution, there are tiling issues. I ran into this

Only one question, when do we stop training?

Nice results, and thanks for the mention:)