[DizzyDoo]

How is this 'Firefly Model' trained and sourced? Will it be on the contents of the stock.adobe.com library?

Clicking through the available pages it seems like a lot of 'coming soon' talk, so there's not really any detail about any of the underlying process.

[timdiggerm]

> The current Firefly generative AI model is trained on a dataset of Adobe Stock, along with openly licensed work and public domain content where copyright has expired.

https://www.adobe.com/sensei/generative-ai/firefly.html#faqs

[m_ke]

I'm sure it's all of their content plus half of the web. The proprietary data they get from Behance, Lightroom, Photoshop and Illustrator (and soon figma) has to be a great advantage for them though.

[mesh]

Does not include Behance data or user data.

https://helpx.adobe.com/manage-account/using/machine-learnin...

"The insights obtained through content analysis will not be used to re-create your content or lead to identifying any personal information."

[rcarmo]

all you've asked is in the FAQ, right at the top.

[olejorgenb]

For what kind of model it is, another poster pointed to https://news.ycombinator.com/item?id=35089661 (a GAN) as a possibility.