Landscapes of Ladakh: AI vs Real

avatar

Landscapes of Ladakh, India: AI vs Real

Recently I have been to Ladakh, India for a relatively long trip over June-July. I shot hundreds of photographs of the incredible landscapes, so I have plenty of personal images of the landscape of Ladakh. Also I visited the spot recently, so I have the memory of the those incredible landscapes burned freshly at the back of my mind.

image.pngladakh_test.png
Bing AI Image GeneratorLooking down/south from Thiksey Monastery, Ladakh

PS. This is on the side, but I must write this for @brucegryllis, or any other new hivers who has similar problems. He asked me about how to display two images side-by-side using markdown. I know there are many ways, but this is the quickest I found. Both images must be of same size. Here they are both 1792 times 1024 pixels. At least I tried to do it, but maybe they are slightly off, but you got the gist of it. Then you insert a 2 by 2 table if you are using peakd. If you are not, just use the markdown code below, and you should have it!

|Image1|Image2|
|-|-|
|caption1|caption2|

Alright, this post is already completely disjointed. My apologies, please bear with me. I have a lot in my mind and trying put this down quickly as kids are trying to make a lava lamp!! Yeah, don't ask! Their Mom is travelling on a business trip!

Back to the images, and I promise I will try and stay on topic.

Intent of this post is to discuss the relatively recent proliferation of AI generatied images based on text prompt. I am writing this for new Splinterlands players who are trying their hands in blogging at hive.

I am not going to get into the moral debate of whether it is good or bad at hive. I will say my opinion on them. In my view the technology is briliant. However, I hate to be a digital artist today, or maybe even a photographer.

Personally I use Bing Image Creator (DALL-E3 Model). I find a simple supportive image for my text content very useful and readily available without having to worry about copyright restrictions of available free images from the internet. I am sure you have noticed, that I do use them in my blog.

I prefer not to use them, where the main content is art or photography. Especially when an user is presenting an AI generated image as manually created art. I think such activity is fradulent. With that said, please look at the two images of Ladakh, India side by side. They are both landscapes.

I have used the following prompt for the image to the left

Ladakh India Landscape Green settlement town in the middle lower right surrounded by barren area

I was trying to get as close to my own image taken from the rooftop of Thiksey Monastry, about 30 min to the south of Leh, Ladakh by car. Mind you, landscapes (photorealistic) are rather difficult to generate by AI. Most of the current publicly available text prompt based AI image generators uses a technique called Diffusion Model. Although the math behind is complicated, but the general idea is simple to understand. Diffusion models work by pairing text description with actual images in a massive database. Typically the model starts with random noise, and matches pixel-by-pixel with the given word prompt based on the database of known images. The model is not copy-pasting random parts of different image objects in a database to generate a new image, but it is subtly shaping random noise to create an image to match a target prompt by trial and error.

If you look at my result, and mind you, I didn't really spend too much time on this; it is probably obvious that which one is AI image, it is rather good. However, I must say, if I am using that landscape as a background of a slide deck regarding, I don't know, say Hydrogeology of Ladakh, the result would be perfectly fine and soothing. Often we use an image to improve the monotony of text, like this writeup right now! I think that AI image will do a good job.

_714d937b-1bf4-4f5c-aef5-e91c9de22288.jpg

This image is generated by a prompt:

Ladakh India Landscape photorealistic

Basically four words, and you have a passable background for your presentation, or a supporting image for your blog, and you don't have to worry about copyright. No wonder, they are everywhere. Just please, do not go overboard with them, and use it as a tool that it is not meant to be used.



0
0
0.000
30 comments
avatar

That markdown trick was well worht the read plus you have some amazing photos from your travels.

0
0
0.000
avatar

Thank you, I am glad that you found it useful.

0
0
0.000
avatar

I have always had difficulty with markdown for some reason it works out ok but other times it does not. I think it has to do with what front end I'm using. Maybe I'm crazy and just can't type the same thing to get it to work...

0
0
0.000
avatar

It’s just matter of getting used to it. I am using it for 6+ years, I am no expert but I know enough to get by. The basic stuff comes naturally after practice.

0
0
0.000
avatar

I have been trying for some years. Someone wrote a good post back in the Steem days on easy to use code and I tend to keep going back to that post for help.

0
0
0.000
avatar

I know a lot of people aren't fans of AI generated art here. Personally, I think it's kind of cool, but I try not to use it too much because I know people don't like it. I think that being able to string the right words together to make a good prompt is art in itself. I guess that's just me though. I think you need to be very upfront about how you created it though and what you used.

0
0
0.000
avatar

It is widely used now, even at hive. Just being upfront about it does the trick.

0
0
0.000
avatar

Like I said, I kind of feel the same as you, but I know there are some who are quite opposed to it. So I try to be careful.

0
0
0.000
avatar

The markdown tip was useful, thank you. There is almost an art in the text input to generate the image it seems.

0
0
0.000
avatar
(Edited)

It is crazy how good the photos are even tho u can tell they do not have a human touch. But still it is impressive how AI is developing, and it is only a matter of time when you can not find the difference of Ai images

How did you like India?

0
0
0.000
avatar

I go to India often, it’s a love-hate relationship. It is probably not a fair question to ask me as I am originally from India.

0
0
0.000
avatar

Understood, im definitely gonna go to india one day in the next few years hopefully.

0
0
0.000
avatar

Currently we are having a love / hate relationship with AI, It works great for images and document summaries, but at the same time it is scary stuff.

Now that we see "strawberry" this is an AI that has been designed to train the next version of chatGPT. Now that is a scary.

PS. I am finding AI very useful especially Gemini on my google phone

0
0
0.000
avatar

In terms of text, basic google search will die slowly. Basic code writing will be next, almost already there.

Images for cover art, semi professional posters and graphic design AI is more than adequate already. I worry about those jobs especially in developing world.

0
0
0.000
avatar

I don't know. I started off loving it - I created an experimental series of cyborgs in the wild west, showing how technology and humans Co exist in uncomfortable ways. But lately, I've come to hate AI images. This one is no exception - it looks unreal, flat, without vitality. Gimme imperfect and moments caught with the human eye any day. I'd rather your worst photo to break up text than an AI one. We survived just fine without it before.

0
0
0.000
avatar

AI struggles a lot with landscapes, does rather well with digital dreamscapes. If you think about it that makes sense. It does well with things that do not exist, does poorly with things that does. However, this is a rapidly advancing branch of technology, soon it will make many things obsolete.

0
0
0.000
avatar
(Edited)

I guess you need to adopt a kind of fatalism in the face of it. Just when I get depressed about it, I go and see a real landscape, which is an absolute antidote to the problem.

I can't help but think of vinyl album covers and the awesome dreamscape art and surrealist landscapes you'd get in the 70s. No matter how realistic AI gets, I'd still prefer a human dreaming a dream of a dream over an AI reflecting the dream of us back at us.

I'm not anti AI as such, just kinda sad we have brought it into being and have it create images we were pretty good at doing ourselves.

0
0
0.000
avatar
(Edited)

"Resistance is futile!"

0
0
0.000
avatar

Ha yep it is!

0
0
0.000
avatar

image.png

I typed:

resistance is futile! from hitchhikers guide to the galaxy

0
0
0.000
avatar

I got the reference - I love your references. I wonder what Adams would have to say about all of this.

0
0
0.000
avatar

Hi, thanks for supporting my post, sometimes I also use AI images but I'm learning to draw, well I draw a little but I need to learn more. My teachers also tell me that sometimes I stray from the topic, I also have a lot of information in my head, I like to study a lot and read. Someday I will travel to India and many more countries, I'm saving for when I'm older. Bye. Thanks

0
0
0.000
avatar

Well I still look your original picture more, especially the sky is much prettier than AI did make it. I think it's bad nowadays that with every picture on the internet I see, (and they start to get so good that you can't see the difference many times) I wonder if this is a real life image I am looking at.
I agree for blogging purposes, except some subjects it's a great aid!
Do you use a paid version for your AI generated images?

0
0
0.000
avatar

Well ladhak is one of the best place to see. The most beautiful place on the north side of India. Btw where are u from ?

0
0
0.000