How Dall-E 2 and Other AI Art Generators Create Images From Text | WSJ
ฝัง
- เผยแพร่เมื่อ 18 ต.ค. 2022
- New text-to-image generators powered by artificial intelligence, including OpenAI Dall-E 2 and Stability AI DreamStudio, let you type in almost any phrase and get an image.
WSJ’s Joanna Stern explains the tech and pits it against a real photographer and a real man in a robot suit.
Tech Things With Joanna Stern
Everything is now a tech thing. In creative and humorous videos, WSJ senior personal tech columnist Joanna Stern explains and reviews the products, services and trends that are changing our world.
More from the Wall Street Journal:
Visit WSJ.com: www.wsj.com
Visit the WSJ Video Center: wsj.com/video
On Facebook: / videos
On Twitter: / wsj
On Snapchat: on.wsj.com/2ratjSM
#AiArt #DallE2 #WSJ
I really like the way this reporter does her videos. Keep it up. WSJ giver her a raise.
💬💬✍️✍️👆
These AI evolve extremely fast. For instance, StableDiffusion is now opensource which means anyone can contribute in order to upgrade it... soon the internet will be flooded with 'fake' images 100% AI generated but the good thing is anyone has now the opportunities to express their ideas beyond our own imagination.
I really enjoy your report and videos. You never disappoint
Well Done! This shoot was A Blast. -Peter
Hey man, just wanna say your site/creations are amazing! Way to go, doing your own thing, going your on way. =) More power to ya my dude.
@@ScumfuckMcDoucheface Thank you for your kind words.
This was a very surface level video and doesn’t do the full capabilities of either Dall-E or stable diffusion Justice. It may take a little bit of adjustment of settings and prompt, but photorealistic images are possible within limits and much more.
Also the ethics of using people’s art styles is also a fascinating topic that deserves to be part of the conversation(Greg Rutkowski)
The artists styles in training are more of a post process comparison to judge quality, trying again when the image doesn't fit enough with the example. I don't think those artists have any valid claim of theft.
The newest version of midjourney makes all these photos look like an early 2000s jpeg. It's insane how fast this is evolving.
Jonna Strrn Does it again 🎉 great reporting
This is quality content. A for effort.
a) not censoring or filtering anything is what makes Stable Diffusion the best in the industry, in part because of b): people should never blindly believe anything they see on the internet in the first place. Right now, I can make more convincing fakes in Photoshop, and nobody asks for Photoshop to be regulated. Image synthesis makes it even easier, sure, but maybe that's the wakeup call people need. Stop blaming the tools, blame the bad actors misusing them, and blame yourself for blindly believing nonsense because of your personal bias.
Chyeah man, scream it out there. =\ feckin' people.
Well said. Classic media throwing fud on everything.
Also weird that they refuse to call it Stable Diffusion or really push it to what it can do. Seems like the report was really shallow in their research.
You can absolutely get SD's prompt output to reach photo realistic.
100%
Exactly this. On top of the theft claims being nonsense, its also not the real issue people need to fear as you can do the same thing with photoshop and stock image sites. The real issue is corporations forcing the use of these tools and then not paying the artist using them, or even trying to do the work themselves cutting out the artist entirely.
I'm sick of arguing with morons on social media about ai stealing their art. Its annoying AF
0:45 0:52 It looks like a Tesla Bot Silver Version
Thumbnail, too
So, it still uses existing images as basis to generate the art. But each of those images are labeled so that the AI can reference what that word is, and analyzes what do these images in a certain word have in common. My question now is, where do they get these images for the AI to reference. Was it sourced fairly?
Good stuff
Fast forward 6 months and the world has completely changed. the way mid journey and stability ai's DreamStudio is moving, the time has come when it will be pretty difficult to figure out which is what - ai or real
What about Midjourney AI
Great video
She's trying to get proof the man was on her pool deck lol
I think a lot of fear artists have comes from the failure of sites like this to explain what algorithms are doing in the initial stages, how they are trained, and what is actually happening in each step to alter the image file. So far I haven't seen a single site explain that stuff as more than "ai is trained on many images" so then artist take that as "its stealing pieces of my art" when it isn't doing that at all. I'm honestly tired of explaining this stuff to angry idiots on social media.
Please explain that part better. Even lawyers and media companies don't seem to understand this aspect of these image generators, further feeding the fear of artists.
Their are models that inspect the image and tells you weither it is CGI or real image
he's not a darlec
but a spacemen
...
How does the AI generator get the 3D model for the scene? It is fed with billions of 2D photos, are they converted to a 3D model or how does it work?
how? by making something that you didn't ask for because the artificial intelligence won't work unless you pay like wsj
Stable diffusion is free to run locally on your PC if you have a good GPU
Computer pictures
or wsj can make more money than both by selling that robot costume
Nobody from WSJ is reading these comments.
1st comment
How about doing some real jounalism and investigateing the ethics of the ai. How the algorithm was trained on scraped images harvested from artstation pintrest etc images that are copyright protected under their respective creators by law. But that the ai buisness walked all over infringing yes stealing. This ai could not exist without the hard work blood sweat and tears and of the artists that proceeded it and is walking on the future of those perpared to put in that same effort to learn the illustation skills handed from artist to artist. The whole thing stinks the project should be scraped and the companies should be forced to start over. And good luck to them then with retrainng of those ai with the billions of images. Images that this time must not copyright infinge, gathered through honest leagal and fair means. Copy right infingment is theft there is no 2 ways about that the ethics on this need its day in court asap before an entire profession is lost to the whims of those who would put no effort in at all. Art is not easy the kind you need to make it to the best studios requires emence skill its time the world recognised tjust how hard and how skilled we are to do that and paid equal to that effort and skill. instead of trying to get artwork for free or pippence. Stop robbing us blind it was hard enough before now we have to deal with false democratisation of our profession. Researching and reporting on that, Such jounalism would be good jounalism instead of what this was.
I agree and well written but that would probably be pretty boring to watch… her report was humorous and informative.
These ai generators steal art from other artists without their permission, mash them together, and create a “new” piece of art.
The bots need to be regulated to protect human artists.
Please make a video about the ethics of ai “art”
which means they are not artists. But that is the world we live in.... fake everything.
Rip artists 💀
Nahhh ☠️☠️☠️