|
Welcome to the AI-art thread. AI art, and AI in general, is literally going to change the world. The way it works is a "prompt" is written, and the AI model interprets the "prompt," and creates an image. This technology is going to put power into the hands of idiots like me, and also into the hands of idiots in executive board rooms. It's going to change the way we work, the way we create, the way we go to school, everything. It's highly exploitable. It's also super fun. If you're curious about the tools, then this is the thread for you. Maybe I'll flesh out this post with a bit more detail, maybe I won't, who knows? But here's some neato information for you to begin the exploitation of this fun little field. Web-Based: Craiyon (free) This is probably the most popular AI image generator out there. It's free, it's easy to use, and it creates whacky results. This is "a cat dressed up like Chairman Mao giving a speech at the Pentagon." (mine)  Dall-E 2 (Free to try once you're in the beta, then not free) Dall-E 2 is proprietary bullshit that costs actual real dollars in the form of credits, but it does produce neat results. It's based on OpenAI, which isn't "open" at all. If you've seen an article on the internet about the magic of AI generated images, it was probably focused on Dall-E 2. This is "A photorealistic render of a cute fuzzy orange monster sitting at a desk in a depressing cubicle doing boring accounting work, path tracing, volumetric lighting, moody." (mine)  Discord-Based: Midjourney (Free to try, then not free) Midjourney is open to the public. It's free at first, but once you run out of free, it costs money. It's closed-source with no plans to make it open-sourced. It will soon have a web-based version. It's probably the biggest and most popular of the AI-generated image makers, even bigger than Dall-E in some ways. The results that it produces are clearly weighted to not produce "bad" results. People like using Midjourney because it requires less prompt engineering knowledge. This is "Industrialpunk Fembot Natalie Kardashian with gears in her head" character portrait art by Ivan Azaizovsky, cgsociety" (not mine). You can easily find more examples of Midjourney on Google, or just go join their discord.  Stable Diffusion (Free, Stable Diffusion is the new kid on the block. Currently, you can run Stable Diffusion locally on your own GPU, or you can run it on their website. The website functionality is currently in a closed beta, but I think it'll open up soon. It does cost credits/money... but you can run it locally, for free, if you prefer. All of these examples are mine:  "Amazing photorealistic digital concept art of a guardian robot in a futuristic city, by James Clyne and Joseph Cross. Cinematic. LED lighting. A bright billowing explosion in the distance. Wide angle. Clean lines. Balanced composition."  Local (note: Anything local requires a GPU with CUDA cores (sorry AMD), and at least 8gb of VRAM. 12gb is better. 24gb is more ideal) Disco Diffusion This is my personal favorite. The results are always a little surprising, it takes some finesse to get coherency, and it's never boring. It's also the slowest and the biggest pain in the rear end to get working. Google Colab Version A GitHub repository/Python/Anaconda/you're a developer version Or a version that can run on a platform called Visions of Chaos, and the instructions on how to make it work are here. Visions of Chaos is an extremely powerful suite of software. It's free. It's amazing. The developer is super cool. The VoC Discord is awesome. If you're going to run Disco locally, this is the way to do it. All of these examples are mine:  code: Stable Diffusion Stable diffusion is a free open source competitor to both Midjourney and DALL-2/OpenAI. It can be run locally, or it can be run via a web interface that, as of this writing, is still in limited beta access. It can produce images quickly and with a high degree of fidelity. Visions of Chaos can also be used to run Stable Diffusion, which is how I've been doing it and it's freaking great. This is the guide to getting the machine learning stuff up and running. Be prepared to fill up around 300gb of storage. I recommend putting it on a fast drive. Stable Diffusion-UI is another front-end that allows you to easily install and run Stable Diffusion locally on your computer. It has a localhost-based WebUI. Looks pretty cool, though I haven't personally tried it yet. Sneeze Party fucked around with this message at 15:30 on Sep 12, 2022 |
#
?
Aug 18, 2022 15:08
|
|
|
|
| # ? Apr 25, 2024 02:43 |
|
|
This space reserved, probably pointlessly. Or not so pointlessly. Here are some resources. Lexica is basically a search engine for Stable Diffusion prompts. You want to make something trippy but you're short on time and/or you don't care about being original? Check this out. CLIP Artists is a gigantic list of 600+ artists. It's a good place to start for artist style modifiers. "A painting of a cat in the style of Andreas Rocha" for example. CLIP Prompt Engineering is a neat guide on the way that various styles and modifiers interact with one another. Very succinct information with visual examples. A Traveler's Guide to the Latent Space is a Disco Diffusion-oriented guide. It's a fantastic read written by a guy who knows a lot about Disco. He's been using it since before most of us knew it existed. It explains every variable. Clip Front is a search engine, of sorts, that will query the Laion5B dataset for whatever you want. For example, not sure if the AI knows who your favorite artist is? Plug their name into this search engine and find out for sure. Sometimes you have to put "by Artistname" for it to recognize what you're talking about. It's a neat tool. Sneeze Party fucked around with this message at 14:56 on Sep 11, 2022 |
|
#
?
Aug 18, 2022 15:08
|
|
|
AI art models already do really impressive poo poo and they're only going to get better.
|
|
#
?
Aug 19, 2022 08:01
|
|
|
You're absolutely right. It's going to get easier and easier to make things look better and better, and more how you want them to look. This is one from last night, with Disco Diffusion. 
Sneeze Party fucked around with this message at 14:21 on Aug 19, 2022 |
|
#
?
Aug 19, 2022 14:04
|
|
|
https://stability.ai/blog/stable-diffusion-public-release Here we go.
|
|
#
?
Aug 22, 2022 19:51
|
|
|
Updated the OP to reflect Stable Diffusion's release. I'm not a huge fan of it so far. I mean, it's neat, and it's fast, and you can get some clean looking results. But most of what I'm seeing out of it looks sort of generic.
|
|
#
?
Aug 23, 2022 16:14
|
|
|
https://colab.research.google.com/drive/1yLplnDxUhfOSatH46jg1r-Cb2KK4Z4BW 4chan got a leak of Stable Diffusion version 1.3 the weekend before 1.4 came out. If you pay the  for google collaborate pro, this link will let you run a hosted version of that. If you have hacking skills you can put 1.4 on your Google Drive and replace the model with the current one.
Dehry fucked around with this message at 03:16 on Aug 25, 2022 |
|
#
?
Aug 25, 2022 03:14
|
|
|
The Dream by Wombo app is in the middle of implementing Stable Diffusion today according to their Discord and it is already a HUGE improvement over whatever they had before. People have the right number of limbs and everything!
|
|
#
?
Aug 25, 2022 14:09
|
|
|
You can also run Stable Diffusion from within Visions of Chaos, which has been working really well for me. This is from a run I did last night. It's so fast on my GPU -- like a minute per render, or less.  Along with the rest of them: 
|
|
#
?
Aug 25, 2022 17:31
|
|
|
I have created art
|
|
#
?
Sep 1, 2022 02:08
|
|
|
I discovered Midjourney today and holy poo poo was I ever underestimating what this AI image generation crap can do   
|
|
#
?
Sep 1, 2022 02:20
|
|
|
gently caress it I’m posting some more because the thread is slow and my wife is already so sick of hearing about this  
|
|
#
?
Sep 2, 2022 04:28
|
|
|
madmatt112 posted:gently caress it I’m posting some more because the thread is slow and my wife is already so sick of hearing about this I'll listen to ya, buddy! I'm in the same boat.
|
|
#
?
Sep 2, 2022 08:35
|
|
|
HanzoSchmanzo posted:I'll listen to ya, buddy! I'm in the same boat. Hell yeah! I realized the link to Midjourney’s discord is absent in the OP, so there it is for anyone else. Discord is the only (I think) way to interact with the MJ service, but their website is cool and good - especially the live catalogue where users’ generations are listed. It’s pretty slick. Here’s my profile. The website does require a Discord login to see the catalogue/feed side of things, unfortunately no anonymous/unauth browsing but Discord is pretty anonymous if you want it to be. The MJ discord has a ton of channels - many are for generation, some are show and tell, obviously some general discussion/FAQ type stuff, but one of the most interesting is #prompt-craft wherein people discuss and explore how to, well, craft prompts. This whole model of “feed AI words, get image output” starts to get kinda freaky for me. Prompt crafting, whether you’re aware that’s what you’re doing or not, is in that uncanny valley between “regular computer-touching to make it do what I want” and “seance with an alien intelligence to understand how it interprets language by reverse engineering what it paints on the wall after I tell it something”. I’m really interested in what Disco Diffusion can do, but sadly haven’t had the time to get over the learning curve nor have had the patience to wait for its iterations - especially when MJ often takes literal seconds to output. madmatt112 fucked around with this message at 14:07 on Sep 2, 2022 |
|
#
?
Sep 2, 2022 14:00
|
|
|
madmatt112 posted:Hell yeah! I realized the link to Midjourney’s discord is absent in the OP, so there it is for anyone else. Discord is the only (I think) way to interact with the MJ service, but their website is cool and good - especially the live catalogue where users’ generations are listed. It’s pretty slick. Here’s my profile. The website does require a Discord login to see the catalogue/feed side of things, unfortunately no anonymous/unauth browsing but Discord is pretty anonymous if you want it to be. Haha. You do sound pretty excited. I'm an artist by trade, so equal parts excited and also terrified over here. If you want help with figuring out Disco, let me know. It's my favorite generator so far, but the results are a lot more evocative, instead of specific.
|
|
#
?
Sep 4, 2022 08:19
|
|
|
quote:I’m really interested in what Disco Diffusion can do, but sadly haven’t had the time to get over the learning curve nor have had the patience to wait for its iterations - especially when MJ often takes literal seconds to output. Disco Diffusion does take a long time, like 10 or 15 minutes per render for most people, but the results tend to be a lot more unique and surprising than the other platforms. If you want to check it out, the easiest way is through Visions of Chaos. You can also use Stable Diffusion from within Visions of Chaos. SD is kind of like Midjourney in that it's fast and the outputs are really neat. Be aware that the total install size for Visions of Chaos is like 200 or 300 gigs. You're getting *a lot of stuff* to mess around with in it. Midjourney does some fuckery on the backend to make nearly every output look mind blowing, but the result is that Midjourney output tends to have a very Midjourney look-and-feel. Regardless, it's a totally mind-blowing technology. In Stable Diffusion and Disco Diffusion, you maintain more direct control over your output. Also, I'm updating the second post with some useful websites and resources.
|
|
#
?
Sep 6, 2022 14:14
|
|
|
Sneeze Party posted:Disco Diffusion does take a long time, like 10 or 15 minutes per render for most people, but the results tend to be a lot more unique and surprising than the other platforms. I gotta get more solid state storage e: and a bigger GPU apparently lol madmatt112 fucked around with this message at 17:26 on Sep 7, 2022 |
|
#
?
Sep 7, 2022 02:44
|
|
|
madmatt112 posted:I gotta get more solid state storage That being said, always get a bigger GPU 
|
|
#
?
Sep 8, 2022 14:30
|
|
|
Sneeze Party posted:Stable Diffusion has forks now, which are available in Visions of Chaos, that'll run on 4-6gb of RAM. So any 8gb card will handily run it, and run it pretty darn well. I have a 6GB nvidia gtx 1660 super. It’s incredible for gaming and whatnot, but it’d be the absolute bare minimum for ML workloads it seems. Probably still worth a try! I wrote a small blog about my few days’ adventures in this space if anyone wants to see it. Don’t know what the forum policy on linking to a personal WP site is.
|
|
#
?
Sep 10, 2022 03:17
|
|
|
madmatt112 posted:I have a 6GB nvidia gtx 1660 super. It’s incredible for gaming and whatnot, but it’d be the absolute bare minimum for ML workloads it seems. Probably still worth a try! Assuming you mean a wordpress blog, of course! I don't see a reason to not link it unless it contains something hateful or unsavory. And since I'm here--do you want a thread tag other than shitpost? Great thread!
|
|
#
?
Sep 10, 2022 06:58
|
|
|
madmatt112 posted:I have a 6GB nvidia gtx 1660 super. It’s incredible for gaming and whatnot, but it’d be the absolute bare minimum for ML workloads it seems. Probably still worth a try! The link on your profile page is broken; you might want to fix that, too!
|
|
#
?
Sep 10, 2022 11:44
|
|
|
Sitting Here posted:Assuming you mean a wordpress blog, of course! I don't see a reason to not link it unless it contains something hateful or unsavory. And since I'm here--do you want a thread tag other than shitpost?
|
|
#
?
Sep 10, 2022 14:26
|
|
|
Sitting Here posted:Assuming you mean a wordpress blog, of course! I don't see a reason to not link it unless it contains something hateful or unsavory. And since I'm here--do you want a thread tag other than shitpost? https://matthew-field.ca/2022/09/07/making-a-i-art/ Ah, yes, my profile links to my old site. Thanks.
|
|
#
?
Sep 10, 2022 15:09
|
|
|
I've been getting into this in a big way. Something about it finally clicked now that I can run SD locally and iterate faster than the online tools. May have gone and bought a new 3080 today because of it, lol.. I'm posting most of my stuff on instagram as @ickn_ai if you want to check it out. The best thing I've found is to guide the general composition with input images, and then building on those. I took a photo of one of these weird rear end tabasco peppers I grew this summer and fed it into SD, and asked for it to be a scientific textbook illustration.. and the way it does letters is just incredible. I can't wait to use this as a tool to develop ideas and starting points for artwork that I would finish out and detail myself.
|
|
#
?
Sep 11, 2022 02:35
|
|
|
Here are a few more from my pepper explorations. I'm working out some ideas for labels for my home made hot sauces.
|
|
#
?
Sep 11, 2022 02:44
|
|
|
Those are seriously awesome. I've seen some other cool "schematic" styled generations, too. How are you running SD? Just through conda/or whatever, or Visions of Chaos? Also, I updated the second post with some neat resources for anyone who is interested.
|
|
#
?
Sep 11, 2022 14:57
|
|
|
I'm using stable-diffusion-ui - https://github.com/cmdr2/stable-diffusion-ui#installation. It's a nice self-contained package that downloads everything automagically and then runs a web ui on localhost to interact with it, and is pretty quick to spin up the generator. I have VoC installed and started to poke around a bit after the lengthy (but well documented!) setup process for ML, I have found it to be much slower to load and initiate the SD model than stable-diffusion-ui. That unfortunately adds a lot of friction to my own process for refining ideas. I'll probably mess with VoC more later when I'm looking to do larger high res pieces and have mostly worked out the prompts and composition at smaller scales with the faster tools. For now, 4x GFPGAN upscaling get me plenty of detail for squirting out stuff that is just going to be seen on instagram, or fed into Illustrator to be converted to vector.
|
|
#
?
Sep 11, 2022 21:37
|
|
|
ickna posted:I'm using stable-diffusion-ui - https://github.com/cmdr2/stable-diffusion-ui#installation. It's a nice self-contained package that downloads everything automagically and then runs a web ui on localhost to interact with it, and is pretty quick to spin up the generator.
|
|
#
?
Sep 12, 2022 15:30
|
|
|
Oh thank gently caress! Thank you for creating this, Sneeze Party. I wanted an AI thread, but I didn't want to have to create it. I've been messing with Midjourney for a couple of weeks and it's pretty drat close to what I've wanted for ... forever, really. Good imagination +  learning art = AI ART MOTHAFUCKA!Glad to have other goons with me falling down the rabbit hole - like a lot of you my wife just tunes out when I start blathering about the 500 versions of a D&D character I made. I am getting in this heavily - I have a ton of ideas for uses for this (which I'll be doing well if I even use ONE). I didn't know you can run this stuff local. I have a super beefy MacBook Pro 16" M2 - would it be better to build a dedicated windows (  ) machine for this?here's my profile: https://www.midjourney.com/app/users/355140082325389312/ Lately I've been messing with the "puppet" method found here, trying to get a consistent character in different environments. I've had mixed success. https://docs.google.com/document/u/...aign=midjourney Making Goth Wood Elves:     I managed to somehow make a whole series of cosplay pics:          Character studies:          Tried to do some Ripley inspired things and it got really fixated on "orange"   Obligatory HR Giger rip-offs  
Doctor Zero fucked around with this message at 21:25 on Sep 12, 2022 |
|
#
?
Sep 12, 2022 20:39
|
|
|
I had no idea AI image generation had come this far. Amazing stuff. Those Disco Diffusion naval/space action scenes are extremely my poo poo. How does this work in terms of copyright? I got the impression from the Stable Diffusion site that it's "free cor non-commercial and commercial use," meaning you own the image you generate? If someone else uses the exact same keywords, will they get the exact same image, or is there some sort of infinite seed/iteration mathemagic going on in the background? How much time would it take studying this stuff to make something like the abovementioned spacey scenes if there's a particular scenario in mind? It'd make a hell of a book cover.
|
|
#
?
Sep 12, 2022 20:57
|
|
|
Duuk posted:I had no idea AI image generation had come this far. Amazing stuff. Copyright/Commercial use - It depends on the service. Midjourney allows commercial use of images depending on subscription. Free/Trial subs can use commercially with CC attribution. Anything else can be freely used for commercial use, although if you make more than $1 mil a year you are supposed to subscribe to the corporate tier. My understanding is most (if not all) services allow commercial use. Note that under current Copyright law, art has to be created by a human to be able to be Copyright protected. I'm sure that will be changing at some point in the future (when big companies like Disney start using it). How much time? It's like any other skill, but it's easy to use, difficult to master. You could do something like that picture within minutes. It's when you start wanting specific things (a red dreadnaught with 16 phaser banks firing on a Danubian star cruiser that looks like a giant Henry Kissinger) that it starts to turn into an 'art rather than a science' so to speak. You can use anyone's prompts and you will NOT get the same results. Midjourney does use a seed, but even with re-using that, it seems each work is unique, even if it's in small ways. Further, there are a shitton of parameters you can add to change things like focal length, lighting, time spent pondering the work, how much the AI can be creative, etc. etc. E: by the way, this is what that dreadnaught prompt gives me in Midjourney. 
Doctor Zero fucked around with this message at 21:22 on Sep 12, 2022 |
|
#
?
Sep 12, 2022 21:17
|
|
|
Duuk posted:I had no idea AI image generation had come this far. Amazing stuff. quote:How does this work in terms of copyright? I got the impression from the Stable Diffusion site that it's "free cor non-commercial and commercial use," meaning you own the image you generate? quote:If someone else uses the exact same keywords, will they get the exact same image, or is there some sort of infinite seed/iteration mathemagic going on in the background? With Stable Diffusion, you just need to have the same resolution/prompt/model/seed. quote:How much time would it take studying this stuff to make something like the abovementioned spacey scenes if there's a particular scenario in mind? It'd make a hell of a book cover. Stable Diffusion makes it a lot easier to get *good* stuff, but it still takes some knowledge to get *wow* stuff. Midjourney makes almost everything look somewhat dope, but it can't be run locally and it's not open source so it can go right on and gently caress off. No offense to the Midjourney poster above. That's good stuff. Sneeze Party fucked around with this message at 21:21 on Sep 12, 2022 |
|
#
?
Sep 12, 2022 21:19
|
|
|
Somebody good with time budgeting please help me my work time is starving Also had a Goblin muse today.         
|
|
#
?
Sep 13, 2022 02:31
|
|
|
   
|
|
#
?
Sep 13, 2022 02:34
|
|
|
I asked Midjourney to make Shrek as photographed by Annie Leibovitz. It wasn’t pretty.
|
|
#
?
Sep 13, 2022 02:38
|
|
|
I like these videos that use the new fill-in-the-blank feature to generate infinite zooming videos like this: https://www.youtube.com/watch?v=xvZel00y7kQ Reminds me of an old scrolling-zoom tiles.ice.org quilt from the early-mid 2000s.
|
|
#
?
Sep 13, 2022 08:27
|
|
|
Sneeze Party posted:No offense to the Midjourney poster above. That's good stuff. Thanks! None taken! Now that I know I can run stuff like this locally, you can be sure I am going to try. I saw on the Stable Diffusion site that they are working on a Mac M1/M2 client, so that will be perfect. I've been wondering what Midjourney would do if you fed it famous quotes. Here are some. I've seen things you people wouldn't believe... Attack ships on fire off the shoulder of Orion... I watched C-beams glitter in the dark near the Tannhäuser Gate. All those moments will be lost in time, like tears in rain... Time to die.  Gozer the Traveller, he will come in one of the pre-chosen forms. During the rectification of the Vuldronaii, the Traveller came as a large and moving Torb! Then, during the third reconciliation of the last of the Meketrex Supplicants they chose a new form for him... that of a Giant Sloar! Many Shubs and Zulls knew what it was to be roasted in the depths of the Sloar that day I can tell you.  I am groot.  I have had it with these motherfreakin' snakes on this motherfreakin' plane! (It wouldn't take 'gently caress' so I had to improvise)  What the mother father cocker spaniel is going on here? (this is the only Sam Jackson line I could think of that doesn't have swears  ) Honey? Where's my super suit? (okay, I lied - that too)  Just keep swimming.  With great power comes great responsibility.  You will ride eternal, shiny and chrome.   THERE ARE FOUR LIGHTS! (I like how one of them has five)  Not the bees!  What is this? A center for ants?  You shall not pass!  Why so serious? (Mj definitely knows about Batman) 
|
|
#
?
Sep 13, 2022 15:19
|
|
|
Doctor Zero posted:Oh thank gently caress! Thank you for creating this, Sneeze Party. I wanted an AI thread, but I didn't want to have to create it. Some information on getting SD up and running on an M1 Mac. Not sure how helpful it'll be but feel free to post your results. https://news.ycombinator.com/item?id=32678664
|
|
#
?
Sep 14, 2022 01:39
|
|
|
sad AMD noises
|
|
#
?
Sep 14, 2022 01:54
|
|
|
|
| # ? Apr 25, 2024 02:43 |
|
|
People who make ai images please post links to your albums or something so I can see what other goons are sorceling up.
|
|
#
?
Sep 14, 2022 05:36
|
|