Brandon Rowlett

That's great to hear! We've implemented gatys on C++ windows caffe but are now looking to get the speed and texture size up, so this looks promising if we can...

Ah, okay, that's good to know. I'll play around with it some more. I'm aware of the checkerboard link, so I'll take a look at that after we've played around...

When you are training it lists the number of parameters its training with.

It would just be nice to update to pytorch 2.0 generally, as the base pytorch instructions don't even have 1.13 (I'm sure we can easily find it), and if we...

I've followed the above steps, and this code: ``` from deepfloyd_if.modules import IFStageI, IFStageII, StableStageIII from deepfloyd_if.modules.t5 import T5Embedder device = 'cuda:0' if_I = IFStageI('IF-I-XL-v1.0', device=device) if_II = IFStageII('IF-II-L-v1.0', device=device)...

update to this - I pulled 21GB of wikipedia text (articles only), then used wikiextractor to extract the articles into a clean text format (modifying it a bit to clean...

Text that it chokes on is this: "0 and 1. Direct3D will then use the elements from the different input slots to assemble the vertices. This can be used as...

Making MacYang555 modification does circumvent the recursion loop as well. I think there needs to be some safeguards that automatically handle that though.

Please update if you find a way to improve inference speed. Quality is great, but speed is definitely a problem

What timing...I just read about Toolformer yesterday: https://arxiv.org/pdf/2302.04761.pdf What is really interesting is figure 4. It shows that somewhere between 750M-1B parameters is when it appears models become smart enough...