How come the faces features and body parts are almost always at the same place on the image ?
I suspect they're used the same seed for every iteration, which is great cause it shows the same context in different styles.
How a Stable Diffusion prompt changes its output for the style of 1500 artists
11–20 of 205 posts
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#12I wonder who is analyzing the weights of the model. At what level is the dimension of "artist name" represented, what is above it and what is below ?
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#13How come the faces features and body parts are almost always at the same place on the image ?
Likely generated from the same random seed.
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#14Interesting that it seems to have no concept of the filmmakers they tried to include here - Tim Burton and Walt Disney didn't produce anything recognizable and look to me like the default stuff you get without providing a style.
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#15Funny that the Bob Ross version just makes them look like Bob Ross. Maybe there are more pictures of Bob Ross in the training set than his actual paintings.
The same thing happens for Vincent van Gogh, and presumably others too.
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#16Interesting that it seems to have no concept of the filmmakers they tried to include here - Tim Burton and Walt Disney didn't produce anything recognizable and look to me like the default stuff you get without providing a style.
We need to solve more captchas
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#17Truly impressive, though it gives me some great fear for all the people whose career is art. This will likely take the pareto to a new height instead of 20/80 maybe even 1/99
Their career isn't art anymore.
Just in case anyone needed to see this spelled out.
The people making fliers have been replaced by AI prompting overnight.
The people doing contemporary fine art with their audience are unaffected.
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#18Funny that the Bob Ross version just makes them look like Bob Ross. Maybe there are more pictures of Bob Ross in the training set than his actual paintings.
The same thing happens for Vincent van Gogh, and presumably others too.
A good measure for whether you're more of a celebrity or an artist is how much of your face a google-image trained AI thinks belongs in your work.
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#19Nice, list could be sorted though
Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists
#20Earlier quoted context omitted.
The same thing happens for Vincent van Gogh, and presumably others too.
A good measure for whether you're more of a celebrity or an artist is how much of your face a google-image trained AI thinks belongs in your work.
Well what if the artist has a popular self portrait?