|
TIP posted:it appears a second gender has struck the building It's twins! Oh, miscarriage. poo poo.
|
# ? Jun 8, 2022 22:02 |
|
|
# ? May 29, 2024 18:59 |
|
not what i asked for, but also, exactly what i asked for edit: seriously, bro
|
# ? Jun 8, 2022 22:13 |
|
Honestly thinking of using the first or middle one as an av: Hellblade: Senua's Snackrifice
|
# ? Jun 8, 2022 22:31 |
|
Renaissance apocalypse angel oil painting
|
# ? Jun 8, 2022 22:33 |
|
One thing I'm really impressed with is that even Dall-E Mini is great at "knowing" reflections. This is "flooded picadilly circus": On the other hand, it has issues with other things. This is "a blue red panda" - it is a bit sad? Maybe that's how it interpreted "blue" And then I tried a "a small blue panda" - and just got red pandas again.
|
# ? Jun 8, 2022 23:19 |
|
I notice some phrases are very "strong" and tend to overhwhelm almost anything you pair them with. e.g. I tried a bunch of things with Beksinski and almost anything comes out just looking like a legit Beksinski painting, the Kermit one was one of the only ones I got anything weird out of where it actually seemed to pay attention to the rest of the query. another extremely strong phrase is "Mr. Bean".
|
# ? Jun 8, 2022 23:25 |
|
Entropic posted:another extremely strong phrase is "Mr. Bean". claymation mister bean
|
# ? Jun 8, 2022 23:31 |
|
"Four-panel comic strip about a lazy orange cat that likes lasagna"
|
# ? Jun 8, 2022 23:48 |
|
post played with Dall-E mini a while looking for insights into how it builds things up into a picture earlier in the thread someone posted a tweet where some guy says AI generated art is the fleshlight of creativity, I copied his whole tweet into mini dall-e and got this: every time I generated it I got a very similar set of photos with a couple Starry Starry Nights then I saw someone else in the thread used just "AI generated art is the fleshlight of creativity" without the rest and got nearly identical results, including the Starry Starry Nights this led me down a rabbit hole of trying to figure what part of that phrase was triggering it to recreate Starry Starry Night so regularly so I tried each important word individually and determined that it seemed to be combining colors and shapes from AI, art, and creativity to arrive at Starry Starry Night put them all together and and interestingly enough the input "starry starry night" does not work I also tried adding back in the less important words like of, the, and is and it was interesting the way that they could change the outcome, driving it towards or away from Starry Starry Night "art is the creativity of AI" seemed to produce Starry Starry Night the most out of any entry using words from the quote, but I think I also figured out the absolute shortest input to reliably get Starry Starry Night the fact that "AI art creativity" so reliably produces a specific painting makes me nervous at the thought of trying to use any of these systems commercially we're gonna need a second AI to judge the outputs against the training materials to make sure we're not duplicating copyrighted designs
|
# ? Jun 8, 2022 23:56 |
|
because I'm a sensible adult I'm now trying to make it make porn, which is pretty hard - maybe some filtering in how it interprets words https://imgur.com/a/9sCMs7T https://imgur.com/a/QtZbz8r - some of these are NSFW, I guess
|
# ? Jun 9, 2022 00:09 |
|
https://twitter.com/paynomindsf/status/1534320090308440064
|
# ? Jun 9, 2022 00:09 |
|
https://twitter.com/HotPinkJustice/status/1534675317570289665?t=j3-uE2nBcO79ErtvqfA6nA&s=19
|
# ? Jun 9, 2022 00:18 |
|
ymgve posted:because I'm a sensible adult I'm now trying to make it make porn, which is pretty hard - maybe some filtering in how it interprets words
|
# ? Jun 9, 2022 00:23 |
|
TIP posted:the fact that "AI art creativity" so reliably produces a specific painting makes me nervous at the thought of trying to use any of these systems commercially Running the prompt "Art is the creativity of AI" through DALLE-2 produces much different results, and a bunch of logo styled designs. It does not seem to be stuck within that same "Starry Night" rut as your mini results, at least:
|
# ? Jun 9, 2022 00:42 |
|
|
# ? Jun 9, 2022 00:44 |
|
Hot Pink Justice posted:Running the prompt "Art is the creativity of AI" through DALLE-2 produces much different results, and a bunch of logo styled designs. It does not seem to be stuck within that same "Starry Night" rut as your mini results, at least: neat to see what it does with the input but I wouldn't expect to get the same thing out of any other model I just find it interesting that it's possible to generate a pretty close recreation of a painting without using any words from the title or the name of the painter it makes me wonder how often these AIs are creating close approximations of art that I'm unfamiliar with
|
# ? Jun 9, 2022 00:48 |
|
george costanza as a cyberpunk bounty hunter
|
# ? Jun 9, 2022 01:29 |
|
Starry night is there because of the million articles from a couple years ago talking about AI style filters based on starry night, which included the full painting for comparison
|
# ? Jun 9, 2022 01:33 |
|
i imagine something similar for things like "comic sans" where the result is entirely about the skeleton without a hint of font
|
# ? Jun 9, 2022 01:35 |
|
not good at context had to test the online version to see if it was better tuned than the one I run locally, but it's really hard to make it actually make something that's not just an image of the full planet
|
# ? Jun 9, 2022 01:38 |
|
Tunicate posted:Starry night is there because of the million articles from a couple years ago talking about AI style filters based on starry night, which included the full painting for comparison yeah there's a lot of phrases that trigger far too specific things on Mini, it seems
|
# ? Jun 9, 2022 01:39 |
|
If I’m impatient and willing to pay, what’s the best option right now, Midjourney? They have a $10/month option I might try although I would prefer it wasn’t recurring.
|
# ? Jun 9, 2022 02:07 |
|
|
# ? Jun 9, 2022 02:12 |
|
working through this thread backwards and i think this needs more love
|
# ? Jun 9, 2022 02:14 |
|
somehow getting it almost exactly right but completely backwards but probably better than what I was going for
|
# ? Jun 9, 2022 02:32 |
|
Dall-E Mini completely forgets some parts of the input if it feels like it It managed "blue apple" on its own, but only gave normal apples for "magenta apple" - I feel like it's a lot more focused when it had something close to it in the original training data (lots of google image hits for blue apples, but not that many for magenta) Also compare and contrast "very shiny glass rabbit" (lots of google image hits, so it probably exists a few times in the training data) vs "very shiny glass capybara" Reformulating the query made it a bit better though - "capybara figure made of glass" gave these, and there is like one glass figurine on google images and it doesn't look like these at all Bonus: "underwater phantom of the opera"
|
# ? Jun 9, 2022 02:41 |
|
Carl Sagan as Elon Musk Elon Musk homeless Barack and Biden as Mao Zedong Barack and Biden as Kim II-sung Bernie Sanders as Lenin Mao Zedong blazing it Bernie Sanders as an 80s glam rock god ymgve posted:not good at context MidJourney is a ton better than dall-e mini, though I like that dall-e mini seems to handle certain things better anyway plus as far as I can tell, no text restrictions. I can't do anything with "Al Gore" because "gore" is filtered >:| sunrise on mars
|
# ? Jun 9, 2022 02:52 |
|
edit: LOL a goon a few pages back had the same idea and got different pictures, amazing
|
# ? Jun 9, 2022 02:59 |
|
This is my first prompt that has anything approaching what I imagined it would produce:
|
# ? Jun 9, 2022 03:17 |
|
KakerMix posted:MidJourney is a ton better than dall-e mini, though I like that dall-e mini seems to handle certain things better anyway plus as far as I can tell, no text restrictions. I can't do anything with "Al Gore" because "gore" is filtered >:| Yeah, but dall-e mini is free and open, which is a big plus, also no censoring I managed to make some porn-like images, but it struggles with the concept of verbs so I haven't managed to make any images with "action" happening (yes I know there is porn on the internet shut up) Also tried really hard to make any gore photos after you mentioned the censoring, but (thankfully) it seems the training data hasn't had much of that. I managed to make some dead pigs, but they were all fully intact and just lying down, with some slightly bloody spots on the skin. I did manage to make it cough up these brilliant pieces though: "human, damien hirst installation"
|
# ? Jun 9, 2022 03:18 |
|
The future is...public transport!
|
# ? Jun 9, 2022 03:18 |
|
Entropic posted:somehow getting it almost exactly right but completely backwards but probably better than what I was going for George Krangstanza
|
# ? Jun 9, 2022 03:18 |
|
|
# ? Jun 9, 2022 03:25 |
|
When the AI misunderstands brilliantly "tower of babel, professional camera"
|
# ? Jun 9, 2022 03:39 |
|
|
# ? Jun 9, 2022 03:46 |
|
|
# ? Jun 9, 2022 03:55 |
|
i asked it for "elon musk homeless and begging for money" and it just gave me regular pictures of elon musk maybe it knows something we don't
|
# ? Jun 9, 2022 03:59 |
|
https://twitter.com/pixelatedboat/status/1534733940476346368?s=20&t=uxrr-1eMoXYxoNb-qey1bg
|
# ? Jun 9, 2022 04:09 |
|
I have a new favourite thing (most of these are variants of "octahedron of [material] on [place]", most often a coffee table) edit: now we're getting more bold ymgve fucked around with this message at 04:37 on Jun 9, 2022 |
# ? Jun 9, 2022 04:17 |
|
|
# ? May 29, 2024 18:59 |
|
I mean... sortof
|
# ? Jun 9, 2022 04:21 |