News for hackers. Stuff that matters.
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by dougmwne on Thursday December 01, 2022 @02:49PM (#33821691)
If the computer was a bicycle for the mind then Stable Diffusion is LSD for the computer.

Who cares how theoretically soulless it is under the matrix transforms, the fact is that this spits out the weird, and us humans chew it up and spit it right back.

I think this is the first new era in Art since postmodernism.

Re:“I've asked Stable Diffusion to generate 250 pages of 198... by bhaney on Thursday December 01, 2022 @02:56PM (#33821804)
So using Stable Diffusion is like giving LSD to your bicycle?
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by alex_young on Thursday December 01, 2022 @03:25PM (#33822206)
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by dpflan on Thursday December 01, 2022 @03:03PM (#33821922)
Seems like a good prompt to try...
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by donkeyd on Thursday December 01, 2022 @04:10PM (#33822802)
I tried, the results were pretty much what you'd expect: https://imgur.com/a/5F4AS2D
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by Yahivin on Thursday December 01, 2022 @03:04PM (#33821931)
Yes.
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by basch on Thursday December 01, 2022 @03:26PM (#33822227)
How long until what is currently photography is either full length video or 3d navigable worlds?

These Star Wars galleries are just phenomenal. I can't imagine it is long until you can apply these as filters to movies, for example taking Rogue One and applying a Fritz Lang or Stanley Kubrick filter.

https://www.facebook.com/groups/395755276049376/?multi_perma...

https://www.facebook.com/groups/395755276049376/?multi_perma...

If I took that galleries above and used it as the input photos, and then used a tool like this, which takes about 5 seconds a frame .. https://gizmodo.com/disney-ai-art-vfx-visual-effects-de-age-...

Or akin to Cars being a remake of Doc Hollywood with anthropomorphized Cars, being able to say something like "I want to see a remake of the 2013 movie Rush, in the world of Zootopia, with 15% styling from Speed Racker, set in the 70's, with flying animals, and the main two rival protagonists being flying squirrels, one of which has a birth defect and a prosthetic wing."

Re:“I've asked Stable Diffusion to generate 250 pages of 198... by WrtCdEvrydy on Thursday December 01, 2022 @03:35PM (#33822344)
> for example taking Rogue One and applying a Fritz Lang or Stanley Kubrick filter.

I mean, what's to stop someone from doing that using a basic ass LUT?

Re:“I've asked Stable Diffusion to generate 250 pages of 198... by basch on Thursday December 01, 2022 @04:30PM (#33823093)
Do you mean just color, or redrawing the costumes and sets and special effects to match aesthetics? In 3D space, and consistently from scene to scene?
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by WrtCdEvrydy on Thursday December 01, 2022 @11:32PM (#33826808)
Aesthetics would be a whole different ball game.
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by basch on Friday December 02, 2022 @10:20AM (#33831629)
If you can get into the facebook links I posted, you can see its a lot more than color grading im talking about.
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by jeremyjh on Thursday December 01, 2022 @03:32PM (#33822309)
Kubrick's version was better than the studio release.
Re:“I've asked Stable Diffusion to generate 250 pages of 198... by GuB-42 on Thursday December 01, 2022 @03:55PM (#33822583)
The think that I find the most LSD-like, both in the visuals it generate and in principle is Google DeepDream.

It works by using an image classifier in reverse. So for example, you have a neural network that identifies bicycles, feed it an image, get the results, and feed them back to the image, boosting the bicycle-like characteristics of the image, repeat the process a number of times. In the end, you get something that looks like the original image, but made of bicycle parts. It is commonly done with faces, it can also be done on intermediate layers, amplifying more abstract details like geometric shapes.

Originally intended as a way to reveal the inner workings of a neural network (for research, debugging, etc...), it has also been used by artists for really trippy visuals.