Stable Diffusion 3 - An Amazing AI For Free!

❤️ Check out Weights & Biases and sign up for a free demo here: wandb.me/papers
📝 The paper "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis" is available here:
stability.ai/news/stable-diff...
Waitlist: stability.ai/stablediffusion3
📝 My paper on simulations that look almost like reality is available for free here:
rdcu.be/cWPfD
Or this is the orig. Nature Physics link with clickable citations:
www.nature.com/articles/s4156...
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Alex Balfanz, Alex Haro, B Shang, Benji Rabhan, Bret Brizzee, Gaston Ingaramo, Gordon Child, Jace O'Brien, John Le, Kyle Davis, Lukas Biewald, Martin, Michael Albrecht, Michael Tedder, Owen Skarpness, Richard Putra Iskandar, Richard Sundvall, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Tybie Fitzhugh, Ueli Gallizzi.
If you wish to appear here or pick up other perks, click here: / twominutepapers
Thumbnail background design: Felícia Zsolnai-Fehér - felicia.hu
Károly Zsolnai-Fehér's research works: cg.tuwien.ac.at/~zsolnai/
Twitter: / twominutepapers

[@jonathanmoore4837]

Thanks Dr 🎉 what a time to be alive 🎉

[@christopherneufelt8971]

Yep. We will have Degrees and will have nothing... p.s. Someone who programmed ANN in VHDL long time ago (I was young, I didn't know!)

[@KimForsberg]

I just love how "ok, this old technique from a few months ago" and then "here is the new revolutionary technique". The rate of evolution of machine learning is just insane.

[@1lllllllll1]

This is why experts keep warning that AI has enormous potential to slip into uncontrolled chaos. Because algorithms can evolve exponentially in terms of complexity, there is a real possibility of this complexity to become overwhelming to society. At that point, it will need to be so highly regulated that it becomes almost useless. That’s the reason why so much warning. Experts don’t want this to happen. Sadly, politicians aren’t paying attention and industry is left to self regulate. You can see this best right now at google’s Gemini LLM. It is exceptionally restrictive at the expense of being competitive with Microsoft’s Bing.

[@Robin_Goodfellow]

Stable Diffusion out here doing what OpenAI was supposed to do

[@glenyoung1809]

Which is why they need the support of the open-source community. The alternative is that we are locked into a Microsoft-OpenAI walled garden which will control what you get and how much you must pay for it, plus the added cost of total access to your data and the results of your queries.

[@philsomething8313]

how can we donate?

[@Auziuwu]

Facts

[@AngryApple]

​@@philsomething8313 subscribe to them to get early access and commercial access to new models

[@0AThijs]

They even inherited their censoring!

[@vi6ddarkking]

We were already able to do extremely detailed and exact images with ControlNet and Loras. I am absolutely salivating at what we'll be able to do once we can finetune SD3.

[@TheSmurfboard]

As an SDXL user I’m giving this new version three thumbs up !

[@NLite486]

i signed up for the waitlist, can't wait to see what bullshittery I get to generate

[@kotekutalia]

What a great time to be alive!

[@eestaashottentotti2242]

🐂💩

[@paolettinic]

1:49 trypophobia triggered so badly I threw the papers

[@TheReaI0ne]

I came to make the same comment. Bro needs to put a warning next time 😮😂

[@morgan3692]

SD is open source and have no any kind of censorship.

[@CNC-Time-Lapse]

I can't wait for this one... Such a massive improvement over SD2 in so many ways. The community is going to make some crazy good models with these too.

[@larion2336]

I just hope the new model is not too censored. Sometimes it feels like the more advanced any of these become, the less fun we're allowed to have with them. That has been the theme with big LLM's at least.

[@kernsanders3973]

They confirmed it will "SFW" unfortunately. So it will be up to the community to put the N in the NSFW

[@lijo1830]

stable diffusion is a blessing.

[@vidyagaems4063]

Understanding images and understanding meaning are creeping closer to each other. One day, we'll have a unified AI, capable of generating complex images with non-obvious description, like "Einstein writing his name and most famous equation". Two papers after that, it will write a paper itself.

[@hombacom]

The problem is that there isn't one truth or one answer to every problem. Humans design with a purpose but AI emulate us without understanding fully. We disagree about things. Change our minds with time and trends. AI + human > AI.

[@Pyriold]

@@hombacom There is nothing magical about human cognition. AI in time will be able to surpass us everywhere, since humans are hardware limited.

[@KibitoAkuya]

Given how most people misunderstand why Einstein got a Nobel prize, I wonder if AIs answer that one correctly (given that they use databases built off of the internet)

[@scooterboom4157]

I love youre videos man! hope you keep reminding me that the time I'm alive in is incredible!

[@HistoryIsAbsurd]

wow just insane! Thanks

[@willd4686]

The open models are where its at!

[@blackyoutuber9.11]

nice doctor rudy will be happy

[@Blubb5000]

Wizardry!!! YES!

[@peffken8834]

Thx! Really astonishing results. But what is kaleidoscopic at the bird? Perhaps I'm not confirm with the definition...

[@nikhilsultania170]

Incredible Video. Do you also make longer videos where you explain these novel techniques in more details?

[@dkianz]

What a time to do designs!

[@sinkler123]

As a fan of the channel, I am making an NPC researcher in my D&D campaign, based on your charming personality. :) Can you please share what laws 2 & 4 are? These quotes are priceless. 🙏

[@zdanee]

I still love how at every introduction your accent at your name completely changes back to Hungarian :) No AI voice generating model will ever be able to generate it quite like that!

[@Ken1171Designs]

I can already do so much in SD-1.5 with a mere 1B model, while SDXL is 3.5B, and SD-3 gets so much more capable with 8B. I know a LOT of work was put into the algorithm's optimizations, but AI seems like a field where size does matter. I can only imagine what SD would eventually be able to do with a 13B model. What a time to be alive! 😁

[@fnorgen]

I find capability tends to scale somewhat logarithmically with model size, so brute force scale is not terribly efficient on it's own. Still very impactful off course, but there's a reason why models size tends to grow explosively, making everything awfully heavy to run. I'm going to seriously miss the old days of casually cranking out 9+ images for a quick test run every time I tweaked the prompt in SD1.5. That little baby is comically lightweight by modern standards.

[@Ken1171Designs]

​@@fnorgen Yup, and that's why I am still using mostly SD v1.5. I can still render 8 images at once in SDXL, but it's not as fast. SDXL also doesn't like long prompts when I want to be very specific. From one of the examples in this video, I saw a very long prompt and the results matched quite well, which gives me hope. 🙂

[@AngryApple]

the big jump from SD1.5/2 to SDXL was that you could use more natural language to describe your image. SD3 seems to improve on that alot

[@Ken1171Designs]

@@AngryApple I hope so! That would reduce the trial & error, and make the tool more productive. ^____^

[@marcfruchtman9473]

Thanks for the review. Yea, Text in the image generation software has been "underwhelming"... to say the least. This is a huge improvement.

[@encyclopath]

I hope there will be the option to use the legacy text generation when they finally perfect it. it’s so endearing.

[@miriamkapeller6754]

I mean, you will have the option to disable T5 and CLIP-G/14, leaving you with just CLIP-L/14 like SD1.5, but even then it will still have far better text generation due to the higher model capacity.

[@encyclopath]

@@miriamkapeller6754 i’m already nostalgic for it!

[@latt.qcd9221]

This looks like a jump over 1.5 that will actually be worth the upgrade.

[@fideys]

Hell, it‘s even a jump from XL!

[@EvanBoyar]

Interesting that the paper includes the avocado students in front of the chalkboard because that has an error in the text. There are seven "r"s on the chalkboard while the prompt only calls for six. I wonder if it still struggles with repeated letters.

[@ZphyZphyer]

It's a long repeated letter, to be honest a small error

[@yuryeuceda8590]

Last week i dream about a place like a castle and when I wake up I was thinking how the brain can create this kind of scenes hyper realistic and taken from nowhere. I was thinking if we can access the brain in such a way we can generate this scenes from our brain and put them on video it could be amazing creativity

[@MCA0090]

There was a research where they put some people to watch videos and then close their eyes and reimagined those videos again on their minds while an AI was reading their brain activity, they trained the AI on that data and it was able to rebuild the "videos" the people where thinking on... the videos the AI generated weren't perfect, but they do looked like the videos those volunteers have watched before.

[@yuryeuceda8590]

@@MCA0090 Wow that was amazing

[@aderitosilvachannel]

I'm eager to see how SD3 deals with hands and teeth. That seems to have been the curse of AI generated images for a while.

[@banzai316]

Awesome! We may be able to show live simulations when we land on Mars

[@8bitsAaron]

Please tell me what are the other two laws (2nd and 4th), i'm dying to know! Love your videos!

[@ironman8257]

Man.... WTF.. So cool!

[@BungusThe3th]

Artstation featured. Realistic. 4k. Artist name. Tall, red hair, cleft chin, porcelain skin, rosy nose, curly hair, exaggerated eye makeup, exaggerated lipstick. Fluted pants , overalls, fashion artist pattern, white gloves , flower lapel. Comically large shoes. Driving miniature car.

[@agracier8656]

Is the voice a reincarnation of Peter Lorre?

[@DaniPooo]

looking forward to when I can finally train some SD 3.0 models

[@mosiach369]

Can you use an image of someone and create art with the person integrated into the art?

[@kanetsb]

Mathematics is scary. I mean this defines human creativity as a function. Sure it's got billions of parameters but still - it's just a function.

[@michaelleue7594]

Well, not really. There's a good piece of info in the video at 5:24 to show that. See how the lines minimize and then start to go back up? You can think of that point as the point where the AI fails to model human creativity anymore, sorta. Humans are capable of observing that they're getting close to a ground truth and that their model of the situation needs additional scope or refinement to improve. Every single AI will in every situation develop its model, get to that minimized point, and then keep on going with the same assumptions even after the model fails. It's called the bias-variance tradeoff. Nobody can fix it except with human intervention. If you let a machine run on its own, it will always, no matter what, reach the point where additional effort makes things worse. Human creativity is exactly the thing that we can apply to avoid that situation. A better claim would be that the function demonstrates that a lot of what we thought was creativity was really just artists yanking on established norms or being random. But real creativity is still out there as an ingredient in real art and still wins every time.

[@Flackon]

Perhaps the entire universe is just a fractal function with astronomically large amounts of inputs over time!

[@smorty3573]

WARNING for people with fear of holes: Skip the time between 1:48 and 2:00

[@selohcin]

Go to therapy, people. You are not in a state of good mental health.

[@sergetheijspartner2005]

Do you also do the voice of Ren Hoek in the cartoons?

[@galvinvoltag]

Mischief! Dark magic! Witchcraft! I love all these arts without artists! I hope our witches will achieve even more unbelievable papers about their dark magic techniques.

[@vidyagaems4063]

It's not without artists. It just requires less manual skills.

[@miriamkapeller6754]

@@vidyagaems4063 I mean, if you want to call yourself an artist if you're typing in a few words until it looks right, then you can do that, just don't expect anyone to take you seriously...

[@vidyagaems4063]

​@@miriamkapeller6754 You would call a mindless drone that can only reproduce reality an artist. I would call it a "camera", because actual art requires creativity - something you lack.

[@miriamkapeller6754]

​@@vidyagaems4063 There's not a single word in your post that makes sense. Try again tomorrow when you're sober....

[@Flackon]

@@miriamkapeller6754people who understand creativity and art will take them seriously. Who cares about the people who have yet to catch up?

[@afaha2214]

This is just magic. imagine somebody from 1998 watching this video they will be convinced we have flying cars by now

[@Recuper8]

Can it do human hands correctly???

[@alexandrustefanmiron7723]

Hold on to your papers!

[@ProcXelA]

How to use it?

[@TheCynicalNihilist]

Cant wait to use it with automatic1111. Will be testing with a 4090 as soon as its available.

[@jonorgames6596]

when?

[@nullifier_]

​@@jonorgames6596 when it's available can't you read?

[@Gaukh]

Now Claude 3 :o

[@afterglow1478]

The I can't bear it pictures made me crack up

[@Jewelsonn]

I get better results with Imagine v5.2 model for text with higher details just like this... I don't know what else they could improve with quality except for the compression and accuracy. As higher detail models lack prompt accuracy that 1.5 had.

[@Star_Dynamo]

This is so scary, but so exciting!

[@ironman8257]

What's scary about it? I seen only net positive

[@callibor3119]

Is it open-source?

[@Albtraum_TDDC]

I wonder how many people asked AI to write a better ending season for Game of Thrones, so far.

[@DeusExNihilo]

I tried with ChatGPT to no avail

[@RodrigoOM]

what is the fourth law of papers?!

[@gfdggdfgdgf]

I wonder if this will be better than the many tweaked 1.5 models, any official releases after 1.5 were marginally better at best. (But easier to prompt)

[@miriamkapeller6754]

You can look at the paper and the showcases. SD3 is in a completely different league in both quality and prompt understanding, there's barely any point in even trying to compare the two.

[@kophaihoang]

1:50 😭😭😭

[@timeTegus]

😍🤣😅

[@Dial8Transmition]

Wasn't stable diffusion already out and free? Is this just a new version or something?

[@nemonomen3340]

New version, yes. Very much improved as well.

[@fideys]

Yeah, that‘s why there‘s a 3 in the name

[@Free2PlayLessPays]

im still not seeing "1 click download here to install locally and train your own models with gui"

[@ringkunmori]

I talk to some people and they sometimes think that all AI tools are paid through a subscription as if it's like Netflix. It's amazing how out of touch some people are.

It's not being out of touch 😂 AI is evolving super fast and unless you are terminally online following all the shit that's happening, you just don't know

[@nemonomen3340]

Stable diffusion has been freely available for over a year. You don’t need to be terminally online to discover this. The only people who don’t know are people who don’t care to know.

[@rando6836]

We’re headed in that direction with Stability and others now refusing to allow free commercial use in their “open source” releases.

[@ryzikx]

some are. they use SD on the backend. hell midjourney is a subscription

[@Schmidtelpunkt]

That is the plan long term. After all, somebody has to make money with it. Else there is no point in doing it.

[@siquod]

"sample efficient" means something different, though

[@sharif47]

6:05 what was the prompt here? Krabby Patty secret formula?

[@apples2892]

This guy has a great voice. He sounds like Maurice Chavez from Grand Theft Auto.

[@dna2dna275]

Dude, not cool. My wife literally left me 3 weeks ago to explore Hungary with some “friends” on a short trip. I thought it’s no big deal. But later on I found out that it was just a lie. She actually ended up going to Hungary alone with the sole purpose of getting to meet and get to know Karoly. I found this out from a letter she left me right before she left about how Karoly is the “love of her life” and how she wants to start a future with him. Fast forward to today and she has pictures of them two together on her social media and she has completely forgotten about me. I’ve never been more devastated in my life. If I would have never watched two minute papers in the first place I could have avoided this entire mess.

[@jknvorneb]

@@dna2dna275 what?

[@dna2dna275]

@@jknvorneb My wife left me for Karoly Zhona Faher. that’s “What”. My life has been ruined because this guy’s videos about AI and machine learning somehow seduced my wife.

[@jknvorneb]

@@dna2dna275 how did it seduce your wife

[@O1NKery]

imagine the borno

[@isatche]

Sooo... Do we know when? :)

[@fideys]

Yesterday

[@braydenshorey8188]

So it will be soon free.

[@Alex29196]

24 gb minimum vram

[@fpvx3922]

" A lot of you will be able to run this from their laptop", lol sure :D

[@gawkthimm6030]

I want open source AI, where we all have access to the source code and can alter it, I want true "free to use" AI that can be changed into anything.

[@ryzikx]

stability open sources everything, youre complaining in the wrong place

[@gawkthimm6030]

so where can I find this open source Ai you mention?

[@fluffywhitebudgie6376]

Literally google it

[@miriamkapeller6754]

@@gawkthimm6030 What are you asking for exactly? SD1.5, SDXL and Stable Cascade are all freely available, research paper, code and model weights. Same for all other models they put out.

[@gustavodutra3633]

There's this thing called "Google", I don't know if you use it. And yeah, Stable Diffusion is completely open-source.​@@gawkthimm6030

[@norbertnagy4468]

I have an 8gb RTX 3070 i hope i can run some version of this locally, but i keep my hopes in check xD

[@miriamkapeller6754]

You can... they already announced the smallest version will have 800M parameters, so you can run that and probably the next largest one. too Not the 8B model, of course.

[@Comenta-san]

what a time to be a Two Minute Papers subscriber

[@robertkeddie]

Never mind spelling - can Stable Diffusion 3 count? I tried to get Microsoft Image Creator to make me a picture of three squirrels cavorting in the snow - it gave me eight. And squirrels having a snowball fight was against usage regulations. 😒

[@nemonomen3340]

Not sure if it can count, but it’s supposedly far better at accurately generating complex descriptions such a “A blue monkey doing a handstand on top of a red pig next to a miniature rhino.” I would imagine the improved comprehension affects counting to some degree.

[@Schmidtelpunkt]

"squirrels in snow" must be an euphemism for a sex practice. Or paraphrases one. Or paraphrases one which is already paraphrased and with enough attempts end up showing exactly what perverts want it to show.

[@Dimencia]

See his previous video about this same model, but basically yes, it's a little better at it

[@fideys]

Image creater has the goofiest censorship. I can‘t seem to generate anything remotely fun.

[@realmetatron]

Please make a short video where you slowly explain how to say your name

[@c0d3_m0nk3y]

You won't believe it, but there is one actually. Search for "TU Wien Rendering #1 - Introduction". Right at the beginning he teaches his students how to pronounce his name.

[@luiginotcool]

Watch his ray tracing course on his channel, lecture 1 he explains how :p

[@fideys]

Just say Dr. Károly Zsolnai-Fehér it‘s that easy

[@BigPapaMitchell]

I'm so excited for artists and human expression to be replaced by AI slop

[@dolcruz6838]

Man i live AI

[@YYYValentine]

I am curious when will become all people in the world obsolete

[@patrickhector]

only if you define a human's worth by what they can produce

[@YYYValentine]

@@patrickhector Good point. I am not define like that, but not I am who decide

[@patrickhector]

@@YYYValentine you underestimate the importance of self-worth

[@NotYoutube-cp3qg]

Only youtubers can't be obsolete because people never gonna stop watching videos doesn't matter what the world is going through

[@vongregor1]

It just gives people who are creative a massive tool to create whatever they imagine. The computer won't sit there and decide what to make.

[@Ardwick-Crome]

Not a fan of SD. Tried several of the prompts from the paper in MJ v6.0 and they are superior to SD 3 in every way. As long as you remember to adjust the --S value and use RAW.

[@fpvx3922]

Just requires 24 GB VRAM

[@panpiper]

I'd like to see an image generator successfully render a knight wearing chainmail wielding a sword and shield. Every attempt I have seen is a dismal failure.

[@Pyriold]

Just tried that on the free bing create and the result was flawless.

[@TheBitProgress]

42

[@teamvigod]

WHAT A TIME TO BE ALIVE!!!

[@dawid_dahl]

WARNING: Trypophobia alert at 01:50

[@mr.mirror1213]

Is there a free website which gives us the compute

[@technolus5742]

There is stable horde.

[@technolus5742]

After watching the video: many people will be able to just run it on a laptop, and soon in phones.

[@gamblerofrats]

Replicate might add it but it's not available yet

[@Parasmunt]

AI how it is 'AI give me a stupid dog picture' AI how i wanted it to be 'AI here is all the data we know on lung cancer, give me a cure' 10 hours later 'here are several treatments you never thought of'.

[@theetaylorschmidt]

Does SD3 need to be as hyper photo realistic as Midjourney to be considered better? Discuss below

[@ryzikx]

no it needs to follow prompts more accurately

[@theetaylorschmidt]

@ryzikx would this include "apple on the left side of screen" or do you mean easier to prompt with natural language

[@rajanverma211]

I don't think it's free. Model is not available for download.

[@Pixeljelly_only]

A kiejtésből egyből tudtam, hogy magyar

[@marcuswilkinson2021]

Trypophobia warning: 1:46

[@vchalmel]

Why on earth do they still make discord mandatory ?

[@zdanee]

They don't. That is for Midjourney, this is for Stable Diffusion.

[@vchalmel]

@@zdanee Dude the link provided to subscribe for the waitlist literally has Discord Id as a mandatory field.

[@MikkiPike]

if Gemini Advanced ever got merged with something like this, I'm sure we'd be well beyond AGI in a matter of weeks if not days.😊

[@jeffg4686]

@3:21 - you don't have to sell it that much 😂😂😂 This day and age is just craziness. I went into 3d a while back and it's now gone. A dead field almost.

[@c0d3_m0nk3y]

What are you talking about? There haven't been so many exciting new techniques in 3d in a long time. There is Nanite, Lumen, upsampling, frame generation, path tracing, realtime denoising and now all the AI stuff on top.

[@jeffg4686]

@@c0d3_m0nk3y- 3d has been evolving quickly, no doubt. Especially the webgpu stuff, and all the augmented reality and all that. Super fast evolution. AI outpaced it...

[@dshcfh]

@@c0d3_m0nk3y Why would anyone learn how to design a 3D model now that AI has killed the need for it? This is going to be every art field. Pretty bleak.

[@c0d3_m0nk3y]

@@dshcfh Oh, you mean from an art perspective? I thought @jeffg4686 was talking about engineering...

[@porudoryu]

Not long ago, I get annoyed at AI images for taking away the livelihood of most of my friends and fam who work as graphic artists and related industries. Then, I look at it in a different angle... hey, these research about artificially generated images will definitely help humanity. The same way as the Holodeck in Star Trek. I think in the near future, this will be our new form of entertainment and can can also be used for research purposes.

[@phutureproof]

Can can like the dance?, a novel form of entertainment these days

[@krautdragon6406]

Good luck waiting for someone to built your utopia. You might be sacrificed next for someone else's personal idea of their utopia - without you in it. :/

[@BigPapaMitchell]

how does replacing artists with ai help humanity

[@BlackTakGolD]

Nice, the topic aside, it's good to be flexible to evidence and not just have a one way of thinking about something, everything is nuanced and having a one track mind is just a coping method to a complex world rather than an accurate way of assessing situations (Ironically we seek generality in these systems, but we struggle to have it.) AI is clearly a helpful tool, more accessible than any other, and will help many people, and already people with injuries/disabilities or lack of time or simply not wanting to spend effort on something that doesn't need it depending on their use case, do use some sort of AI every day. There are many risks to consider with almost anything too, and we should always critique new technologies even more so, but as the technology has developed thus far, the benefit certainly outweighs the downsides for many; in every area I can look, AI is providing value, such as in the gaming world with upscaling technologies (2x FPS with basically no downsides is no joke), or art and architecture being given a much faster creativity process, or coding being infinitely more accessible and convenient because of AI (No one is willing to help me well with my messy Python code on stack overflow like a tiny LLM is lol), OCR, translation in general, protein folding too? And this is just off the top of my head. Still, this is an ever projecting field, and even if we have positive results right now, we should definitely be careful of conclusions such as "overwhelmingly effective artificial systems that are not aligned with human values," that is if we care about still existing in the way we do then.

[@encyclopath]

The holodeck helped humanity? Have you seen Star Trek?

[@Shefetoful]

poggers

[@juezna]

tripophobia trigger warning

[@danser_theplayer01]

So is it or will it be? Make up your mind.

[@helphelphelphelpmehelphelphelp]

This is interesting, but how will this affect the ai girlfriend market?

[@bazookaman1353]

One step closer to AI+FDVR virtual girls.

[@BlackoutGootraxian]

better pfps/avatars for them in general

[@vidyagaems4063]

You'll be able to have many waifus at once.

[@TheBennyFisch]

I wouldn't call a non public waitlist "free"

[@fideys]

It‘ll be free when it‘s fully released

[@pfifo_fast]

my bar is set pretty high, ive found more flaws in sdxl than this channel has papers. Out of this new iteration, I expect photo realistic hands and feet each and EVERY single time, and I also expect a wide variety of faces to be generated, not the same 3 faces over and over and overrrrrr again. In my experience, none of the diffusion models out there are worth a crap, the whole idea should be scrapped and we should start from scratch with some other technique that is actually capable of generating good images.

[@fideys]

Go find a new technique and come back to us

[@Flackon]

Why would you expect that? Btw, I've been able to generate good images from SD models relatively straightforwardly. Perhaps you need to develop your skills with the available tools?

[@justuseodysee7348]

SDXL is nearly useless due to inability to train new models on 24GB GPUs. Hopefully this will be better

[@miriamkapeller6754]

How do you figure that a 8B parameter model would be easier to train than a 3.2B parameter model?

[@fideys]

@@miriamkapeller6754SD 3 is just built different

[@oscarltbro6808]

Una ves que OPEN AI sacó su inteligencia SORA, ya cualquier avance en otra cosa se ve insignificante, mejor que se ahorren sus avances hasta que sean mejores que sora 😅

[@jopansmark]

It's so over for Midjourney and OpenAI.

[@santitabnavascues8673]

AI is collapsing on itself

[@0sliter0]

waitlist = not free... at this point this is just newsletter promotion

[@ProcXelA]

Yea, right. It's just a spam.

[@miriamkapeller6754]

...? The model is in preview. It will be released for all, probably in a few weeks.

[@fideys]

@@miriamkapeller6754how do people not get what a waitlist is?

[@0sliter0]

@@miriamkapeller6754 yeah in those weeks a better model would already appear... why bother learning this if you can't use it... why gatekeep?

[@Flackon]

waitlist only means there is a list to wait on. It has nothing to do with its status as a free release

[@rando6836]

“Free”, but not for commercial use because Stability sold out. So not “completely open” like you said.