The focus of your link appears to be papers and research. I would imagine somebody with less time for these developments is looking for more practical "here's how you can use this cool new AI" style articles instead.
Deforum stuff is cool, but also a bit of a flash in the pan because of the disconnected nature of the generated frames.
Pure video generation is getting better, but like all generative AI it lacks imagination and cannot really create new things, making it less qualified for truly mindblowing psychedelic visuals in its current state.
Best thing about milkdrop was that you could use a microphone. We brought a projector and screen to a music festival (HSMF) in '04 and had a jam circle in our camp where the visualizations would respond to the music we were making. Definitely a hit way back when before that sort of stuff became boring.
On Android the free ProjectM app hasn't been updated since 2022. Does anyone know how to install Milkdrop 3 on Kodi for Raspberry Pi or in F-Droid? Kodi is also on Android.
Looks interesting, but inviting users to try your service, letting them put in effort (in this case typing a prompt) and THEN forcing them to login is considered a black pattern in my book.
I understand some form of rate limiting is necessary, but this bait and switch setup always feels like a kick to the face.
Yeah, it says it will create an SVG in seconds, but seconds later, there is no SVG. Did not occur to me that I had to log in, but probably won’t as I cannot be bothered to follow black patterns…
It's kind of annoying that some of the best models out there have a tendency to produce very not safe for work results.
Look mom, I can make some cool astrology images for you! Whoops, that's boobs. That too. And this one. Ehh, hold up, I need to add a pile of negative prompts first...
Sketching nude humans is a huge part of how human painters learn. Because surprisingly clothed humans are just nude humans with some fabric over them, and the fabric can make it harder to tell what's going on.
Even if we assumed equal amounts of effort, it wouldn't be surprising if a large corpus of nude images in the training data improved model results.
But maybe we should have better negative prompt presets for different levels of decency
In the near future, we will have less art made by professionals and more art made by hobby artists (with or without AI support).
It will be a tough time for professional artists, but personally I don't believe we will "lose the human spark" in this transition.
If all AI art is soulless, new artists will rise that can put the missing part back in.
How many amazing potential creations have been lost because their creators did not have the time or money to make them? I'm looking forward to see what these people will create in the coming decade!
I think without financial support you're not going to get very good art. Some of the greatest artists of the renaissance were only able to spend all day painting because they had patrons. My city has lots of public art because the government spends money on it.
I believe there's a substantive difference between digital art tools like photoshop or illustrator and LLMs. LLMs do not create "art", they create images. Previously, you had to PAY an artist to create art. Now, you pay for an API to create an image loosely based on the specifications you give it. As a result, there is less art in the world.
Art models, to me, are very powerful paintbrushes. The technical skill of the artist is less important, but their ability to create art that makes people FEEL is more important than ever.
Which one makes things become bigger? I learned that one first and then later figured out the one that makes the mixed image smaller (cross eyed I think?). Now I cannot do the big one anymore.
