yardenst

We generated hundreds of images using a subset of Parti Prompt and manually rated them. Our results show that for most challenges SD3 Large outperforms Medium in all challenges, but most significantly in Style, Perspective and Imagination where SD3 Large is a clear winner.

We demo with people without copyrights and have strict terms of use

>Though it’s obvious that the customer does not have these permissions in probably 95% of cases, maybe 100%. Because if both people agree, then you might as well just take a photo of them together. No need for AI then.

That's not true if they cannot meet in person.

The legal aspects here are very interesting but I think they miss the point. This tech can be used to create photos with celebrities, but not only.

We do use regional prompting but not only

By customer I mean our own customer (a business) and not the end user

This is something our customers need to deal with

As a young startup, this is something we are also trying to figure out. Currently, it's evident that this technology generates the most value in the B2C sector. However we also observe a robust B2B demand for other AI models (e-commerce)

Now we are focusing on serving other businesses, if you have a good consumer app idea please let's talk over email we would love to collaborate.

Stable Diffusion's eco system is pretty wild!

Sorry, we try to move fast, we’ll fix it in our next release

For this reason we’re currently screening all new customers and monitoring the usage

Great point, when using the API the photos used to train and generate photos are provided by the customer, and they must have the correct permissions to use them

It is not something we allow now for various reasons in the demo website, but please contact me at [email protected] and we will make what you need.

Using the API it's possible to choose any 2 persons.