vanadium1st

Yeah, it's weird. The music scene is as live as it ever was here, along with all other parts of the normal city life.

It's not really a new situation for us. This war continues for 8 years, and all this time the front was about 200 miles from us. During this new phase of the invasion the frontline got a little closer to Dnipro, but not that much.

Regular life here stopped in winter-spring, when we didn't know which cities will withstand this phase of the invasion. Tragically Kherson, Mariupol and many others are lost as of now. But we in Dnipro were lucky enough and life kind of continues here.

There are changes of course. Practically no artist in Ukraine gets paid now at any level. Every single concert is for charity, gathering funds for arms or refugees. And, as with all other life, there are constant interruptions of air raid sirens.

Other than that, music scene lives as usual. People still go to concerts and artists still perform. Predictably a lot of sad sad songs gets written now, but honestly no one really wants to hear them - everyone here gets enough negativity from everywhere else. The best bet is to stick to the happy and hopeful stuff.

Thank you for your interest. At this moment I am only performing live and am not proud enough of my performance level to record it and share it online

Outside of my regular job, I am an indie folk music artist, trying to rise in the local music scene here in Dnipro, Ukraine. Even though learning to be a musician from scratch in my 20s was a hard process that took years and years, by far the hardest part of it was trying to establish a passive income, so I could have enough free time for practicing, performing and writing music.

A lot of my talented peers are so much better then me in all of the music and performing stuff, but can't find enough time for it between regular boring work. Woody Allen said that 80% of success is just showing up, and it seems true. But now I see how a lot of talented people simply can't afford to show up. They are missing open mics and performing opportunities because they can't skip another shift as a barista, they can't find time for rehearsal because of soul killing the low paying bank job. I keep thinking about all the beautiful songs that are left to be unwritten.

I guess the life of artists was always like that - either you are struggling, or you have a source of passive income that carries you through the development years. And I do think that this moment in history is as full of opportunity as it ever was. Still, it was a surprising discovery for me. I really thought that at least at the starting level it would be mostly about who plays their chords better, and it surprisingly isn't.

Stable Diffusion is mind-blowingly good at some things. If you are looking for modern artistic illustrations (like the stuff that you would find on the front page of Artstation) - it's state of the art, better in my opinion then Dalle-2 and Midjourney.

But, the interesting thing is that while it is so good in producing detailed artworks and matching the styles of popular artists, it's surprisingly weak at other things, like interpreting complex original prompts. We've all seen the meme pictures made in Craiyon (previously Dalle-mini) of photoshop-collage-like visual jokes. Stable Diffusion with all its sophistication is much worse at those and is struggling to interpret a lot of prompts that the free and public Craiyon is great with. The compositions are worse, it misses a lot of requested objects or even misses the idea entirely.

Also as good as it is at complex artistic illustrations, it is as bad at minimalistic and simple ones, like logos and icons. I am a logo designer and I am already using AI a lot to produce sketches and ideas for commercial logos, and right now the free and publicly available Craiyon is head and shoulders better at that then Stable Diffusion.

Maybe in the future we will have a universal winner AI that is the best at any style of pictures that you can imagine. But right now we have an interesting competition when different AI have surprising strengths and weaknesses and there's a lot of reason in trying them all.

I believe that it already did, honestly. The output and range of Dalle-2 and Stable Diffusion is unmatched by any human artist. I am not only talking about quantity and range - the best illustrations generated by Stable Diffusion are honestly unbelievable and could totally get on the front pages on artstation on their own. The digital paintings, the 3d renders, landscapes, portraits, concept arts, character designs - I've seen too many world class examples of those generated by AI. The best human artists can usually be world-class at a single style or a genre, while Stable Diffusion is world class at hundreds of them. There's of course no way to judge art objectively. And there are at the moment a lot of gaps that AI is not the best at. Still, if there was a single human artist that could do the things that stable diffusion can do - he would be the best artist that ever lived, no doubt.

I am a working digital artist, my personal feed is filled with takes like this. I understand the crisis that artists go through currently and I understand their emotions. I've personally made peace with it already, but it will take time for everyone and there will be a lot of concern, rage and bargaining in the process.

All of us artists woke up in the world where the thing we were learning to produce all of our lives became 100x cheaper. I've been kinda waiting for this to happen for truck drivers or translators and was honestly surprised that it got to the artists first. But, there's nothing to do now.

There will be a lot of takes trying different ways to deny this reality. Like if we agree that this thing is immoral or anti-cultural it will go away and our potential customers will forget about it. I think that it's a waste of time The industry is not completely gone, but it will go though a massive transformation. The basic hierarchy of artists will probably stay the same - people who were good in the pre-ai era will still be good working with the ai. If you've learned your basic skills right - they will still work.

I've personally already changed my workflow to use ai art for the sketches, ideas and references. And then polish them to commercial level using my old experience and skills. It's funny how this thing is so new, but I've gotten so used to it that it's already hard for me to come back to my old set of tools. And I do recommend all other artists to do the same and to try to find their place in the new reality - it really seems like there's no other way.

I've tried out a couple of prompts from the post in Stable Diffusion and as expected the results were much weaker. It has drawn some alpacas and basketballs with little relation between the objects.

I've been playing with Stable Diffusion a lot, and in my experience its results are much weaker then what's shown in this post. The artistic pictures that it generates are beautiful, often more beautiful then Dalle-2 ones. But it has a real problem understanding the basic concepts of anything that is not the simplest task like "draw a character in this or that style". And explaining the situations in detail doesn't help - the AI just stumbles upon basic requests.

Seems like Stable Diffusion has a much more shallow understanding of what it draws and can only produce good result for things very similar to the images it learned from. For example, it could generate really good dutch still life paintings for me - with fruits, bottles and all the regular expected objects for this genre of painting. But when I've asked it to add some unusual objects to the painting (like a Nintendo switch, or a laptop) - it couldn't grasp this concept and just added more warbled fruit. Even though the system definitely knows how a Switch looks like.

The results in the post are much more impressive. I doubt that Dalle-2 saw a lot of similar images in training, but in all of the styles and examples it definitely understood how a llama would interact with a basketball, what are their relative sizes and stuff like that. On surface results from different engines might look similar, but to me this is an enormous difference in quality and sophistication.