imagen-pytorch VS metaseq

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

This is a super important issue that affects the pace and breadth of iteration of AI almost as much as the raw hardware improvements do. The blog is fun but somewhat shallow and not technical or very surprising if you’ve worked with clusters of GPUs in any capacity over the years. (I liked the perspective of a former googler, but I’m not sure why past colleagues would recommend Jax over pytorch for LLMs outside of Google.) I hope this newco eventually releases a more technical report about their training adventures, like the PDF file here: https://github.com/facebookresearch/metaseq/tree/main/projec...

The number of people who can actually pre-train a true LLM is very small.

It remains a major feat with many tweaks and tricks. Case in point: the 114 pages of OPT175B logbook [1]

[1] https://github.com/facebookresearch/metaseq/blob/main/projec...

Reliability at scale: take a look at the OPT training log book for their 175B model run. It needed a lot of babysitting. In my experience, that scale of TPU training run requires a restart about once every 1-2 weeks—and they provide the middleware to monitor the health of the cluster and pick up on hardware failures.

I really appreciated this log of Facebook training a large language model of how troublesome AI development can be: https://github.com/facebookresearch/metaseq/tree/main/projects/OPT/chronicles

Stable Diffusion will run on any decent gaming GPU or a modern MacBook, meanwhile LLMs comparable to GPT-3/ChatGPT have had pretty insane memory requirements - e.g., <https://github.com/facebookresearch/metaseq/issues/146>

It seems so, check this log book from Meta: https://github.com/facebookresearch/metaseq/blob/main/projec...