#how to detect ai

[amalasdraws]

https://www.tumblr.com/bigmammallama5/732632789726478336?source=share do you have any tips on how to detect ai and deepfakes?

Good question and I'm gonna be honest, it's not always easy and it will only get harder and harder. I'm just an artist who has spent their personal time to dive into this topic and study images. I'm still learning and there is a lot I don't know. But let me show what I know. This will be long, but I will make a summary at the end! So far, even with ai having become better and better there are still almost always some things wrong with an image, and they all have a very specific look to them. So let me try to show you some and point out some of them.

As we all know, a biggest struggle ai had were hands. And even though here and there we still see messed up hands, I say "had", because the hands is actual a good example on how ai is improving and will only get better. Still, looking at pictures that show more hands is always worth it, because somewhere in the back there will be most likely at least one messed up hand.

Another issue a lot of ai still has is hair though!

It's very obvious still in many ai "drawings" and in those otherwise well rendered portraits. Hair starts to blend with the ears a lot, or with the clothes.

There is also often this very odd look between something too sharp and way too blurry

There is often a very specific texture to the hair. I actually do not know the artistic or specific name for it. I can only describe it as this weird sharp feeling that makes it look oddly pixely, and then you have areas where it's very blurry. And the kind of loops and almost flame like looking hair we see in the last pic out of the three here is also something very common with ai.

As an artist I know we make mistakes too! The way I draw hair is flawed too! But it's not only that it's flawed here, but it's following always the same pattern and falls into the same issues over and over again, no matter who is "creating" the image. Those flame like loops are a common one, next to the odd blends and weird sharp and blurry textures.

But ai is getting better, and we not only have "art" and something that tries to be a drawing/painting, but photos too.

A lot of those "photos" have a very specific texture and look to them! Again, it's not always the mistakes, but the very specific optic too. A lot of the images are oddly smooth, too rendered, with always blurry backgrounds. And when you look closer at the background you will see the mistakes! The crowd behind Jesus is a hot mess once you look closer. Bob Marley's hair has the same issue than I described before. Lincoln is surrounded by people with messed up hands and don't even get me started on the faces behind Caesar.

So a lot of ai images look alright on a first and quick glance, but as more time you spend with them, as more mistakes you will notice. The wehre is Waldo of ai horror.

And those "photos" shared here are still very obvious. Not just the mistakes and messed up details but the very specific aesthetic too.

Those images get better and better and as less details you have, as less mistakes you have!

With photos like this it becomes harder and harder. There are not many details and no hands. Not many mistakes can be made. Also the very obvious plastic looking smoothness isn't so much here anymore. It kinda still is...but differently. And always the blurry background!! Sometimes the hair is still a giveaway. Collars and clothe straps are also often still a giveaway upon close look. As is jewelry. Earrings will be different and necklaces often don't go all the way around, just end, or blend with the hair or clothes.

Often details on jewelry is also blurry and not shown properly. This is a trick with many details. With jewelry, batches, hair, ears, text. So it's often blurred out and not shown properly because ai doesn't know what to really show here.

It's often really just the small details and when we scroll down quickly we will miss them. Like the wedding ring on the middle finger, the pens on top of a closed pocket, the batches that are always blurry, messed up faces that blend with a blurry background.

And sometimes it's so subtle that I could only really tell that right is the ai image in comparison to the real photo on the left. The real photo shows hands clearly and even when things are blurred out it doesn't feel that it's done to hide things. The ai image on the right hides the hands. There is also a very dead look in the eyes :D

And here I could only tell because the text in the back doesn't make sense. Even blurred out we should be able to make out something here

And after seeing a lot of ai images I recognize the kind of blurred out bg in combination with a very smooth and well rendered foreground/characters.

And here the only giveaway is a closer look at the backgrounds as well

To summarize it:

Ai and fake news rely on a fast living world. We are being bombarded with tons of information and messages daily and we scroll past quickly. But the best tool, for now, in detecting ai is taking our time! Those images get better and better but so far there are still always some things off!! Especially in the background!

Hair. Often weirdly smoothed out and oddly sharp at the same time

Hair often blends with the ears or the clothes

Details are blurred out.

Jewelry doesn't match (example earrings). Details on metal often blurred out and never shown. Necklaces blend with hair or the clothes, and don't go around the neck.

Background is always blurred out.

In this blurred mess there are often hidden very messed up faces and/or hands.

A very specific smooth and yet too sharp/too rendered aesthetic combines with an always blurry bg.

Text, especialyl in the background, is not legible and doesn't make sense.

Backgrounds are often (so far) the dead giveaway. Somewhere in the back things become muddled and messed up. This shows also very well in ai decor/architecture. There will be odd lines that don't align or align too well. Curtain poles that end in the furniture, a plant that is behind a lamp suddenly having leaves in front of the lamp. As longer you look as more you will notice.

Conclusion:

Take your time with images! Sit with them! Especially when it's framed as important and political news. Is it ai and propaganda, or did it really happen? Don't fall for the quick buzz and outrage! Some things are obvious right away but with others you have to take your time. And it's time you have! If you are still unsure if a pic is real or not, do some research on top. Image reverse search. Can you find it anywhere else? Are other news outlets sharing it? Does the image/message make sense? For example there is now a deepfake of Bella Hadid voicing support for Israel. Ask yourself, does this make sense? If it feels out of line compared to previous behavior, do some research! Media literacy is not just as being able to recognize a fake or real right away, but being able to do research. To question things! Don't just take every post online for face value. Even when shared by a mutual you trust. They might have been tricked!

There are so many information online and it's great to have access to so information, but it's also difficult to wade through all of it. Media and truth are a weapon and it's being twisted and bend used to manipulate. Always has! But ai and so many people being able to post and share things, it becomes bigger and bigger and more dangerous. So don't just take everything that is handed to you and share it further no questions asked. Media literacy and being able to think for ourselves and do the research is important!! And as research becomes harder and harder, as sources are being messed up with ai and other fake news, it's even more important to sit with the images and study them. See the flaws, the mistakes. Compare it to other news and images.

This got long, and I started to ramble at the end. Sorry But I hope this helped

[onsukun]

just a girl

[halflifebutawesome]

I am a good person. I am a powerful person, I don't believe in evil. I think that evil is an idea created by others to avoid dealing with their own nature. I understand my own nature, good and evil have nothing to do with it.

[kugisakiss]

watched m26 hehe, sorry for the word vomit

if anyone was wondering how i was counting how many movies they appeared in, i made a little timeline when i was trying to figure it out for myself ↓

all dcmk movies are released on golden week which is in april. shout out to the detectiveconanworld wiki i couldn't have done it without you x

the real enemy is conan because he's got a perfect 100% movie spotlight

[akiizayoi4869]

One of my favorite things to think about when it comes to Shiho and Agasa's relationship is how Agasa finds this little girl wearing a giant lab coat passed out in the rain, he takes her into his house so she can warm up and get a change of clothes, and while this is all happening she tells him who she is. A former member of the organization that gave Shinichi the drug that shrank him, and that she's the creator of said drug, and how she also took the drug to kill herself, but it shrunk her instead. Agasa hears all of this and is like "Oh, well that's interesting. Anyway I'm going to adopt you, you're officially my daughter now." Without asking her any questions or judging her for her past, and Shiho's reaction was probably like "wtf???"

[clownakai]

Akdkfkskfkkscnjssk she called him bleached😭😭😭😭 godbless Shiho never change

[haylessa]

she didn't even try lmao

[interdimensionalpancakes]

file 383 | random coai moments i love (1/?)

[phreaticlayer]

they should be at the club

[sfaira]

Six years late, but apparently that is what was needed so I could not fail miserably at trying to draw everyone's favourite Detroit machine I am obsessed, spent his week reading fanfics and watching various clips but still, as I'm a person of one fanart per character I think you shouldn't expect more Connor xD A shame really, cause it seems I'm just starting to learn how to draw him but I don't want to get my own hopes up. Anyways, I'm free now, I contributed to the fandom after all these years.

[glitzglamgunpowder-if]

Do you have a physical description for the ROs?

Hello anon!! I'll probably add additional details later, but I used some pictures to try and convey the overall vision I have for everyone (these aren't their canon FCs or anything I couldn't find a one-to-one ratio for all of them based on their given descriptions). I don't have official visuals with them just yet because I want to avoid making AI portraits, and I haven't found a Picrew with the more gritty/realistic style I want also I can't draw but hopefully someday I can commission artists to help out!

ALSO, I'm aware some of these hairstyles are not historically accurate. I also know that beauty standards have changed over the years so what was attractive then isn't necessarily attractive now. Since this takes place in an alternate universe, my explanation is going to be that the "traditional hairstyles" of the time are for more formal/official settings, but they have their own preferences for how they like to wear their hair in their free time (like a stylized modern interpretation similar to what Bridgerton does).

Alistair/Alice Delacroix - THE RIVAL

French/Irish; Average Height (Alistair is 5'10 and Alice is 5'5); Somewhat Muscular; Ivory Skin Tone; Shoulder-Length Wavy Blonde Hair; Blue Green Eyes; One-Sided Dimple on Right; Sharp Jawline; Scar over Left Eyebrow

Samuel/Samantha "Sam" Kaminski - THE BOSS

Jewish and Black; Tall (Samuel is 6' and Samantha is 5'7); Muscular; Deep Brown Skin Tone; Textured Black Hair; Deep Brown Eyes though there have been rumors they glow red at night; Sharp Eyebrows; Adorn Themselves with a lot of Accessories/Jewelry

Hendrik/Helena Rietveld - THE BODYGUARD

Guyanese; Above Average Height (Hendrik is 5'9 and Helena is 5'6); Muscular and Toned Body; Sunkissed Skin Tone; Curly Dark Brown Hair; Amber Eyes; Traditional Tattoo that Travels from One Arm All the Way to Back

Jesse Lê - THE FRIEND DETECTIVE

Vietnamese; Above Average Height (5'8); Fit Body; Light Tan Skin Tone; Slightly Wavy Long Black Hair Typically Tied Back; Dark Eyes (Practically Black); Wears an Eyepatch over Right Eye

[purenguyening]

There something that really gets to me about this moment in this particular Conan case. Ai, who is normally written off as cold and calculating, uses her knowledge to comfort and reassure Maria about her Osaka dialect. Especially, when prior cases up to this point, the whole family of Kansai dialects, but especially Osaka's variant is played off as "improper" Japanese for a quick joke.

This delights me so much as both an Ai fan and as a linguist who loves and adores all regional variants from the bottom of my heart.

[startswith0]

Conan : *is late

Haibara : a murder happened, innit

Shinichi is not going to be the dad that left to buy milk. He's gonna be the dad that left to solve murders

[lucreciaart]

Sisters 🌅

[cfserkgk]

I can't seem to draw nowadays so here's some low quality screenshot redraws of male Haibara (whom I think about more than I should).

Also anybody agrees with me that early Haibara was so so so cool, like the hospital scene with the roses? We need more Haibara love.

[bastionbibi]

She ALWAYS hides behind him it's pretty fucking cute imo. And Shinichi's already used to it, just expecting her to hide and shields her no question asks.

I know that it's pretty much a given, he's the only one she can trust, but that wasn't always the case, right? I love how it's an established dynamic between them now.

Especially in the later chapters, when she kept getting haunted and he just JUMPS IN, feeling just as protective, seeing that she was almost killed a couple of times already and despite not saying it, wouldn't that give any man some level of anxiety??

Shiho just expects Shinichi to be the literal shield between her against the world. But isn't it ironic that at the same time, if her shield is threatened, she's even willing to give her life to protect him?

Two sides of the same coin.