Stable Diffusion, NovelAI, Machine Learning Art - AI art generation discussion and image dump

[Menachem Sneedson]

I, for one, welcome the age of post-evidence.

 

[Thumb Butler]

This is fun.

Chantal is an obese grinning diabetic bald canadian woman with bad skin living in kuwait



who will win the election?

 

[Black Spruce]

OpenAI introduced SORA (Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.) today on their Twitter thread - archive. You can visit it here.

How long until the government is generating videos of people they don't like diddlin' kids and arresting them for it?

 

[Hyperbolic Steroids]

If I want niggers, Bing, I'll ask for niggers, don't just go throwing niggers at me all willy-nilly.
View attachment 5726200

You did put "American" in the prompt.

 

[888Flux]

OpenAI introduced SORA (Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.) today on their Twitter thread - archive. You can visit it here.

that is genuinely disturbing. it's not that the videos are flawless, but they would be able to fool 90% of normalfags.

This technology should not exist and I'm starting to believe this is not something that humanity created themselves. GPT-2 was released only 5 years ago and just 5 years ago the most state of the art image recognition model was something like YOLOV4. i don't think that adds up at all, no matter how many financial resources and researchers that OpenAI (which was much smaller back then) had at their disposal.

Where do they source the data from

 

[Dick Mason]

OpenAI introduced SORA (Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.) today on their Twitter thread - archive. You can visit it here.
View attachment 5725089
Here is an example. The prompt is: "Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes."

View attachment 5725088

This kills the Hollywood. I hope reasonably passable open source alternatives can sprout up in the next couple of years. Unshackled from censorship, this will lead to creative renaissance of sorts.

The big downside: porn. The horrors we're going to see are going to make the already hyper-destructive addictive porn seem innocuous.

https://www.hollywoodreporter.com/business/business-news/openai-introduces-ai-video-tools-encroaches-hollywood-1235826527/

OpenAI Marches on Hollywood With Video Creation Tool​

The technology has the potential to displace huge swaths of labor as the entertainment industry grapples with AI.

The Hollywood Reporter says many in the industry are very scared.[1]
“I’ve heard a lot of people say they’re leaving film,” he says. “I’ve been thinking of where I can pivot to if I can’t make a living out of this anymore.” - a concept artist responsible for the look of the Hunger Games and some other films.
"A study surveying 300 leaders across Hollywood, issued in January, reported that three-fourths of respondents indicated that AI tools supported the elimination, reduction or consolidation of jobs at their companies. Over the next three years, it estimates that nearly 204,000 positions will be adversely affected."
"Commercial production may be among the main casualties of AI video tools as quality is considered less important than in film and TV production."

Hollywood is over by 2030 no matter what. Whether you're an actor actor or voice actor or writer or anything else, your best-by date has been set in stone.

https://news.ycombinator.com/item?id=39386156

A lot of coping over at Hacker News. "b-but look at how imperfect it is! its useless!" As if it's not going to dramatically improve with a lightning-fast quickness.


This isn't art. Its information, potentially powerfully affecting information streams, just like any other. Look at the crap quality of the average Youtube content creator. They can amass huge audiences, wealth, and power despite being mediocre. Creations from AI-generated video will rapidly become popular and profitable, despite their flaws, and in some cases because of the whimsy or creepiness their flaws imbue them with. Humans are trivially easy to manipulate with multimedia information streams. These will have no problem whatsoever gaining a major foothold in any area where it can be shoehorned into.

https://twitter.com/DrJimFan/status/1758210245799920123

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths.

I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be!

Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee."

- The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space.
- The 3D objects are consistently animated as they sail and avoid each other's paths.
- Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations.
- Photorealism, almost like rendering with raytracing.
- The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe.
- The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect.

Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.

 

[Terrifik]

that is genuinely disturbing. it's not that the videos are flawless, but they would be able to fool 90% of normalfags.

This technology should not exist and I'm starting to believe this is not something that humanity created themselves. GPT-2 was released only 5 years ago and just 5 years ago the most state of the art image recognition model was something like YOLOV4. i don't think that adds up at all, no matter how many financial resources and researchers that OpenAI (which was much smaller back then) had at their disposal.

Where do they source the data from

Great steps in human progress are made by things that don’t work the way philosophy thought they should. If things always worked the way they should, you could write the history of the world from now on. But they don’t, and it is those deviations from the normal that make human progress. - Charles F. Kettering

Wheel of progress

https://twitter.com/tomwarren/status/1758204817074245895

.......
the meme for context

https://twitter.com/AimagineNFT/status/1758209568549798223

 

[Historical Strelkov]

Just wait until the prompt part isnt text based anymore and it becomes the selling point for neuralink.

 

[888Flux]

Elon great progress is made when your hands off.

More like this technology was handed off to select few people who are controlled and in the gri,d. It's always existed, but they are using it now to disrupt language.

The end goal of these people is to completely deracinate humanity. This means removing all form of identity from an individual, race, religion, and culture and converting them to a seamless unit. When symbols can be generated synthetically without the direction of human consciousness it loses all meaning. It's the molestation of the way we communicate with eachother. Which is the goal, total utilitarianism

 

[Neurotypical Mantis]

OpenAI introduced SORA (Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.) today on their Twitter thread - archive. You can visit it here.
View attachment 5725089
Here is an example. The prompt is: "Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes."

View attachment 5725088

those people are really tall

 

[Terrifik]

More like this technology was handed off to select few people who are controlled and in the gri,d. It's always existed, but they are using it now to disrupt language.

The end goal of these people is to completely deracinate humanity. This means removing all form of identity from an individual, race, religion, and culture and converting them to a seamless unit. When symbols can be generated synthetically without the direction of human consciousness it loses all meaning. It's the molestation of the way we communicate with eachother. Which is the goal, total utilitarianism

He did try to warn people about Ai.
Also, Expect Ai laws to be pushed in the USA in about a couple of months & month or less for the UK.

https://www.nytimes.com/2023/03/29/technology/ai-artificial-intelligence-musk-risks.html

March 29, 2023
阅读简体中文版閱讀繁體中文版
More than 1,000 technology leaders and researchers, including Elon Musk, have urged artificial intelligence labs to pause development of the most advanced systems, warning in an open letter that A.I. tools present “profound risks to society and humanity.”

A.I. developers are “locked in an out-of-control race to develop and deploy ever more powerful digital minds that no one — not even their creators — can understand, predict or reliably control,” according to the letter, which the nonprofit Future of Life Institute released on Wednesday.

Others who signed the letter include Steve Wozniak, a co-founder of Apple; Andrew Yang, an entrepreneur and a 2020 presidential candidate; and Rachel Bronson, the president of the Bulletin of the Atomic Scientists, which sets the Doomsday Clock.

“These things are shaping our world,” said Gary Marcus, an entrepreneur and academic who has long complained of flaws in A.I. systems, in an interview. “We have a perfect storm of corporate irresponsibility, widespread adoption, lack of regulation and a huge number of unknowns.”

A.I. powers chatbots like ChatGPT, Microsoft’s Bing and Google’s Bard, which can perform humanlike conversations, create essays on an endless variety of topics and perform more complex tasks, like writing computer code.

“Humanity can enjoy a flourishing future with A.I.,” the letter said. “Having succeeded in creating powerful A.I. systems, we can now enjoy an ‘A.I. summer’ in which we reap the rewards, engineer these systems for the clear benefit of all and give society a chance to adapt.”

 

[cantankerous jackalope]

If you've ever had a lifelong dream to be a famous artist/writer/filmmaker the door on achieving this is rapidly closing.​

​

This technology is progressing at such a rapid rate that soon everyone will be able to create their own music, movies, etc. We'll see a massive shift towards personalized content unique to each viewer. The opportunity for someone who isn't already established as an artist to create a new story/film/drawing and get the gratification of it being seen and appreciated by thousands of people is rapidly, rapidly closing. Obviously nothing precludes someone from making art for arts sake, but there is a certain kind of fulfillment and satisfaction of having your work become popular and appreciated by thousands of others across the world - and that opportunity will be effectively gone soon.


I truly don't think we're ready how AI is going to fundamentally destroy the dreams of millions of creative people. On one hand, it's tragic, but the on the other there was an insane amount of gatekeeping/raping in Hollywood that you had to play ball with your politics, actions, buttholes, etc. maybe it is for the best.

 

[Edict of Expulsion]

Just after the writers strike, too.

I wonder what the Big Buck Bunny will be of AI generated showcase movie

A jewtuber could do something where 100 ish creators all make a 60 second clip and then combine it into one feature length film.
The audio is the tough part, for now.
Decent music.

People actually just aren’t subscribing to disney or other globohomo services but getting their hours filled with tiktok, xitter, fortnite. Kind of a leg up.

The analogy goes (((Hollywood))) is cable TV, AI generated entertainment is alt media

I’m excited for remixes of Europa the last battle for tiktok.

 

[cantankerous jackalope]

Just after the writers strike, too.

I wonder what the Big Buck Bunny will be of AI generated showcase movie

A jewtuber could do something where 100 ish creators all make a 60 second clip and then combine it into one feature length film.
The audio is the tough part, for now.
Decent music.

People actually just aren’t subscribing to disney or other globohomo services but getting their hours filled with tiktok, xitter, fortnite. Kind of a leg up.

The analogy goes (((Hollywood))) is cable TV, AI generated entertainment is alt media

I’m excited for remixes of Europa the last battle for tiktok.

I mean if you can get over the existential angst that this induces we're about to enter a golden age of custom entertainment. Theoretically one could generate Zone of the Enders 3 or create more episodes of Cowboy Bebop where Spike didn't die. Or create a custom movie for Dragon Ball Z that takes place during the Cell Games where Cell and Goku have to team up to fight Broly or some shit.

 

[Miller]

If I want niggers, Bing, I'll ask for niggers, don't just go throwing niggers at me all willy-nilly.
View attachment 5726200

The Bing model is so smooth-brained that it shits out stuff to promote melanated history month.

How long until the government is generating videos of people they don't like diddlin' kids and arresting them for it?

It will happen soon, since they also make the rules

X (formerly Twitter)

As usual, the same people and corporations will have access to it while the pleb will only be able to use the most lobotomized models like BingAI.

You did put "American" in the prompt.
View attachment 5726385

Jesus Christ, Denton.

 

[General Emílio Médici]

My honest reaction

 

[BirdUp]

calm down

 

[TheGuntinator]

Either that or there is going to be embedded cryptographic fingerprints put on to every single camera and they'll have to upload unedited data to a tightly controlled server or something. That or maybe they'll make all the AI shit embed something so it can be detected. I do recall there was a thing with upscaling the images during the Rittenhouse trial so I really think if it's pervasive they'd have to put out a standard on it.

When a model is created that lacks these fingerprints, (likely for the government) won't you have people coming up to you saying it can't be faked because it doesnt have the AI fingerprint? Like it'll stop random people from causing trouble with AI, but if the government wanted to say... publish a video of Tommy Robinson stabbing a muslim who doesnt exist so they can give him life how would someone tell? You'd point out its fake and a dozen people will tell you it doesnt have the fingerprint so it cant be, even though the fingerprint was an artificial addition, and not something within the metadata as a process of AI creation, and can therefore just be disabled. We already had this with the Kentucky Fried babies in Israel and the "Is it AI" sites giving contradictory results.

 

[WelfareNiggerQueen]

My honest reaction

View attachment 5727345

 

[General Emílio Médici]

but why a cowgirl