Top - OpenAI GLIDE (filtered), Bottom - LaionideV2

Watermarks

There are watermarks in some outputs. You can try to prompt engineer this away, but it isn’t always possible. royalty free seems to work well.

Direct comparison with OpenAI GLIDE

You can see a comparison over the same captions in this weights & biases report

Data filtering

Data was removed from training given any of the following: - Value of ‘NSFW’ or ‘LIKELY’ in the nsfw column from LAION’s metadata - Images which originally had an aspect ratio greater than 1.3 (or) less than 0.8 - The original width or original height is less than 256 pixels. - Captions were checked against a list of slurs. If a slur is in the caption, it is removed. I won’t be publishing the slurs.

Shout out to stability.ai for donating the compute to laion needed for this to be possible.