Yoko Li

And to Justine's point, like exactly, like what is the implication for the professional use cases?

Like what, like was the JSON prompting, what can they do more easily now with this capability compared to before?

And then...

I guess one thing we were always wondering is that this release, the open source model is so small.

It's 9.3 billion parameters.

You know, like previously, a SOTA is probably like 80 billion parameters.

It's like 9x of a difference.

And you can't run it on a single GPU instead of having a lot of compute footprint, which really opened up opportunity for people to use it.

So the question is, how did you do it?

I imagine because it's a smaller model, as you mentioned, like it's harder to win on scaling and counting number of chips, but it is possible to win on a specific domain or optimizing for a different, you know, thing in a different domain.

So what was the trade-off for the research team when training this model to decide what to focus on?

For enterprises, as you alluded to, I mean, customization is really top of mind, whether that's a brand kit or it's something that is stylistically just done, but hard to encode that style into just a doc.

So I imagine customization on top of an open source model is just the best way to go.

So the question becomes like, what is the ramp up for the customers or the artists to start, you know, post-training or fine-tuning on top of the ideal brand model?

What do they have to do?

With the JSON prompting and editing and model fine-tuning, the composability aspect of the model is just huge.

There are so many ways you could customize it.

One hot topic in the industry, in the research community, is a genetic loop for creative tools, right?

So it used to be the creativity tools, the consumption layer is always a UI.

As a human, I look at it and then I make modification.