|
Kharmakazy posted:There's a lot of the names there Not all of them, though.
|
# ¿ Jan 6, 2023 04:02 |
|
|
# ¿ May 13, 2024 22:39 |
|
Tree Reformat posted:feels a bit sacrilegious that this thread now probably constitutes the most effort ever put forth in making an actual zybourne clock deliverable, even jokingly Pretty sure that one Valve concept artist put way more time into the thing than anyone before or since. Also the people who made a joke live action trailer for the game a few years after the project crashed and burned.
|
# ¿ Jan 6, 2023 07:19 |
|
Ruffian Price posted:A magic box that will happily invent nonexistent language features whole cloth, because the prime directive is to be helpful and satisfy your query. Verify against a search engine and use the feedback feature if you got a perfect-looking answer that doesn't actually work. Yeah, it has a janky implementation/understanding of some less used languages. It got the syntax all wrong for one I tried, both using some ancient deprecated syntax instead of new and compact code, and completely misusing a different feature. It's clearly just writing any code you ask for in pseudocode and then only turning it into "code" in the actual language when you ask to see it, because it would give me what the output was "supposed" to be when I told it to run a subroutine using a given input, rather than what the code would actually do if it was being interpreted by the AI properly. And I would tell the AI it understood one feature or syntax wrong, and how to fix it, and ask it to apply that fix to X subroutine. But the next time I asked it to write something it would forget one of those fixes, and then the next; it never remembered the proper way to do anything beyond 5 or 10 text exchanges.
|
# ¿ Jan 9, 2023 06:14 |
|
Doctor Zero posted:That result absolutely stunned me. The rest are not quite so perfect, but awesome nonetheless less. Ha, did it give the children long hair because metal?
|
# ¿ Jan 12, 2023 02:04 |
|
pixaal posted:I don't get it how is their shining example not mona lisa or that it steals the style of Van Gogh. Like you could probably convince a jury that something there is wrong. For the former, da Vinci died five centuries ago, and the latter, dude died 133 years ago; how could any jury find legal wrongdoing there? "Style" is not and has never been copyrightable
|
# ¿ Jan 17, 2023 16:39 |
|
Ornamental Dingbat posted:They made a sequel. And an interquel. https://twitter.com/keithscho/status/1613944969479491584
|
# ¿ Jan 18, 2023 10:32 |
|
PoorWeather posted:Anyway, I don't think there's anything wrong with using open source stuff, or just loving around with the technology generally. The people I'm worried about are the ones who seem eager to stan the corporations behind this stuff and their products as if they're synonymous with it. I saw some people on a discord the other day basically worshipping Midjourney as a newborn god and it scared the hell out of me. Post Your Favorite: Derail Valley › PYF ProcGen: drat thats nice I'd worship that
|
# ¿ Jan 19, 2023 08:47 |
|
RPATDO_LAMD posted:the gpt model is pre-trained, it is not learning from your inputs in real time or w/e. after MS's Tay companies aren't dumb enough to do that again Less than that! In my experience it starts forgetting what you've already discussed after around 20 exchanges or so.
|
# ¿ Jan 30, 2023 00:15 |
|
IShallRiseAgain posted:That looks like the old rich guy in the wheelchair in the Hannibal movie Red Dragon. Do you mean the old rich guy in the wheelchair in the Manhunter movie Silence of the Lambs?
|
# ¿ Jan 31, 2023 04:56 |
|
StarkRavingMad posted:I would appreciate any tips on trying to generate pictures that look like a movie still frame or a photograph and less like a drawing. I'm trying some of the obvious things like "photorealistic" and "movie still frame" but it still kind of looks like an artwork. Or does it really just come down to the model you use? No photograph is labeled "photorealistic" in the datasets these things draw from; only drawn/painted/rendered art. Don't use that unless you want clearly not photography. I've had good results entering the names of film cameras, film stock, and especially "cinematography by" whatever cinematographers were active in the era/style/genre you're looking for. ~4 names there is usually good enough.
|
# ¿ Feb 4, 2023 20:11 |
|
KwegiboHB posted:Birthday request: everyone post monster trucks. Thank you! MUTER monster truck rally, nitro infused engine, burning wheel, bisexual lighting, gender reveal smoke
|
# ¿ Feb 4, 2023 21:26 |
|
pixaal posted:Talking about building a large scale game with current tech is silly you have no room for anything but the AI and will require very powerful GPUs the cost of production and how niche a product this will be with most people going "yeah but it looks like poo poo and I need a 4090", this is 5-10 years out at a min, all of these features are things that have to be solved before it's viable and they can be. That's not even DOS RPG. Loaders were like Commodore and Amiga things IIRC.
|
# ¿ Mar 6, 2023 17:17 |
|
HowIsItManifested is pretty great https://clips.twitch.tv/SlickNimbleTeaDoubleRainbow-_8CBDONqYOQtJMw2
|
# ¿ Mar 8, 2023 07:15 |
|
IShallRiseAgain posted:I uh made a body horror LORA, and um well it certainly was effective. Even I was grossed out a bit by it. You can get it here https://civitai.com/models/18399/body-horror
|
# ¿ Mar 11, 2023 23:16 |
|
Molecular photography deconstructed procgen loss.jpg Doctor Zero posted:Wow, that's a great idea! Make stick figure art and use img2img to tell the AI to make them into storyboards.
|
# ¿ Mar 31, 2023 18:01 |
|
KwegiboHB posted:Midjourney Img2Txt nonconformist art brutalize lawfully telling your bros they look submissive and tractable
|
# ¿ Apr 5, 2023 01:50 |
|
deep dish peat moss posted:TIP has been working with a custom text2animation model ITT, reading their posts may give a better understanding of the kind of effort you're looking at - here's the most recent: There's also Joel Haver's method he's been using for a couple years now: https://www.youtube.com/watch?v=tq_KOmXyVDo Basically he rotoscopes keyframes of animation on top of live action, and then uses basically style transfer from the software to apply those hand-drawn frames of art onto the subsequent frames of video. It tends to break when there's too much movement, though, but that makes it perfect for lip-syncing. Combining that with SD or MJ keyframes could yield very interesting (and cost-effective) results. That's a potential way to animate small details, if you can find Andy Serkises rather than just VAs.
|
# ¿ Apr 5, 2023 03:59 |
|
deep dish peat moss posted:Also I haven't drawn much lately because I'm still waiting for a change in medication to even out but here's an example of the kind of thing I've been doing with AI recently: New Voynich manuscript looking good
|
# ¿ Apr 10, 2023 07:16 |
|
Is this and these quote:
|
# ¿ Apr 14, 2023 12:37 |
|
Bucnasti posted:It doesn't understand anything, it associated non-english words with images based on it's training data. Which is why when you feed it prompts in German, it spits out images that look like they're from Germany, because the training data images that were labeled in German were most likely taken in Germany. Also because it's the lingua franca, so it's spoken more widely geographically and in more contexts around the world than German is, generally.
|
# ¿ Apr 21, 2023 07:57 |
|
AARD VARKMAN posted:im game for hero jobs as a theme RIP to a real one
|
# ¿ Apr 22, 2023 18:43 |
|
feedmyleg posted:I've used a combo of getimg.ai+dreambooth and MidJourney in two video projects over the past week and have been totally blown away with how much time they're able to save me and how much more creativity they're able to unlock. Especially when I can use Photoshop to make a mock-up of what I want, then use getimg.ai's text-to-image to hone it into the style I want in 5 seconds. Making a music video where everything was both custom and convincingly watercolor in a very short amount of time was an absolute breeze. You could remake the Take Me On music video in a day if you had the source film to rotoscope, couldn't you
|
# ¿ Apr 23, 2023 04:44 |
|
Roman posted:Making some previs/promo shots for a character. It's rare I get a bunch of stuff this good in one session. Based on Fiona Dourif, with bonus dollar store Elijah Wood at the end. Wow, she looks exactly like her father.
|
# ¿ Apr 23, 2023 16:02 |
|
Brawnfire posted:My prompt here ended up as "cupped hands full of minestrone no bowl" and it only worked once out of dozens of iterations Did you remember to bring your chunky noodle soup?
|
# ¿ Apr 28, 2023 05:53 |
|
Brawnfire posted:
Many hands make light work
|
# ¿ Apr 28, 2023 05:54 |
|
Fuschia tude posted:Many hands make light work Fresh from the garden
|
# ¿ Apr 28, 2023 05:57 |
|
Bucnasti posted:Trying to make some NPC images for Dungeons and Dragons and for some reason, Bing is convinced that dwarf women have big pointy ears, and the more I try to convince it otherwise the bigger it makes them. The more you reference something in a prompt, the more it emphasizes it. Use negative prompting instead to reduce the prominence of something.
|
# ¿ Apr 29, 2023 17:38 |
|
|
# ¿ May 2, 2023 06:26 |
|
pixaal posted:GPT is fine at like an adult swim style for about 3-5 minutes tops then it goes off the rails. I really do think current AI could be curated (this part is important!!) into a viable 2AM sketch show with 5 minute long sketches without more than an improv line read edit. Oh you want the AI to read it too, and decide the emotional tone? Oh boy now you are just being wacky. We might be able to get 15-30 second long consistent sketches. It can do the couch gag equivalent to something else. How Is It Manifested regularly generates 1-2 minute sketches based on a sentence or two of description, with 100% AI generated static images and voices. It adds a whole lot of extra prompting behind the scenes to enforce genre restrictions or even predefined characters, though.
|
# ¿ May 2, 2023 17:38 |
|
Gromit posted:Agreed. I'm not into model trains at all, but I liked some other people's work that had little model houses and plastic people, so wanted to see what AI would do with a whole train set. I'd love to see dioramas of famous historical events, but couldn't think of any in particular that would be fun to see. Lincoln's assassination Caesar's assassination Hannibal crossing the Alps The Fourth Crusade besieging Constantinople
|
# ¿ May 3, 2023 08:15 |
|
Soulhunter posted:be the change you want to see in the world and make a website with gpt Nightcafe does something similar, with daily and weekly challenges where the winners get bonus image generation tokens, as well as ranking the top most popular public images of the last hour, last day, last week, and last month.
|
# ¿ May 23, 2023 03:35 |
|
same
|
# ¿ May 28, 2023 19:21 |
|
I like how it threw some Dali-style melting tableware in there. Just for the hell of it.
|
# ¿ Jun 20, 2023 14:22 |
|
BoldFace posted:Marvel made the intro to their new television show using AI. I get the feeling this sort of thing is soon going to instantly date a work to the mid-2020s, just like really ugly CGI did for the late 90s-early 2000s, or vaporwave to the mid-2010s.
|
# ¿ Jun 21, 2023 13:24 |
|
Roman posted:It's also likely that it was made a while ago with older tech. Progress is measured in months with this stuff. Weeks, it seems like. Meanwhile the lead time on TV production seems barely any shorter than film, these days.
|
# ¿ Jun 22, 2023 04:42 |
|
Crapple! posted:Thanks I'll have to give img2img a shot sometime. I definitely get the panning for gold analogy. The one time I got something like that picture of yours was when I generated this from a chaos 100 prompt I want to see what happens when you keep zooming out
|
# ¿ Aug 8, 2023 00:44 |
|
Mercury_Storm posted:Got some high quality bathroom art now I guess you outpainted the original to get that? unzin posted:2 years ago I was playing with CLIP+VQGAN... can't find one working anymore, but I liked the abstractness of it. Coherent and Artistic modes are still available in Nightcafe. The former is just CLIP, the latter is VQGAN+CLIP.
|
# ¿ Aug 24, 2023 17:15 |
|
Mercury_Storm posted:
Out of all the hobbits that could be, that is Sam least of all.
|
# ¿ Sep 29, 2023 02:20 |
|
First time using Bing for this. Vincent Van Gogh using Nair to remove his ear, Nikon photography DSLR, studio cinema production still. That was taking the prompt a little too literally, so I removed the photography bits:
|
# ¿ Oct 4, 2023 16:17 |
|
|
# ¿ May 13, 2024 22:39 |
|
Debunk This! posted:I'm sure this is pretty boring to most of the thread regulars but I'm having fun trying to create specific fantasy characters and scenes. Anyways heres some Sabriel. Here, have a hawk.
|
# ¿ Oct 8, 2023 02:40 |