Bites & Bytes Podcast
Unpacking Cybersecurity Ingredients: SBOMs in the Food Industry with Marc Frankel
Marc Frankel
Stable Diffusion is trained on a number of different data sets. One of them is called the LION-5B. Again, the names here don't really matter. But this training data set had 400 million text-to-image pairs. So it had a picture of a cat. When it said the word cat, it had a picture of pencil, so the word pencil.
0
💬
0
Comments
Log in to comment.
There are no comments yet.