ssebowa VS imagen-pytorch

If google doesnt, someone like lucidrains probably would implement it, just like he did for imagen and muse.

lucidrains/imagen-pytorch: Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch (github.com)

Hi Can someone guide me a little, as to how i can use LAION dataset to train my imagen model? like how i can download the data, and in which format it should be fed to https://github.com/lucidrains/imagen-pytorch code?

If we were to put money into training something, I'd hope we use a better model, like Imagen.

I've been messing around with this open-source implementation. You can get a pretty good idea of the model size by just copying the parameters from the paper.

I'm waiting on this implementation/training of imagen: https://github.com/lucidrains/imagen-pytorch

I'm honestly surprised that they trained a StyleGAN. Recently, the Imagen architecture has been show to be both easier in structure, easier to train, and even faster to produce good results. Combined with the "Elucidating" paper by NVIDIA's Tero Karras you can train a 256px Imagen to tolerable quality within an hour on a RTX 3090.

Here's a PyTorch implementation by the LAION people:

https://github.com/lucidrains/imagen-pytorch

And here's 2 images I sampled after training it for some hours, like 2 hours base model + 4 hours upscaler:

https://imgur.com/a/46EZsJo