Category: AI Whisperer

AI Whispering 9

May 18th, 2023

Midjourney

I thought I’d try for something completely new today so I asked Midjourney for an image of Cerberus, the three headed hound of hell, ascending from the pit, it gave me this:

That wasn’t quite what I was looking for but I persevered and eventually got a hell hound:

I am though, currently obsessed with angels and fairies and without even thinking, I was making more images of them. I have tried to get good images of male angels for weeks now but every attempt has brought awesome angels with awful faces. Today I got one that I really like, it took a long time and many attempts:

I like to think that the Archangel Michael looks something like this. I also asked for female, obviously, and got these:

Both of whom I hope to meet in Heaven.

I feel this post wouldn’t be complete without some fairies, so:

I also spent some time making magical backgrounds for blending with characters that I particularly like, that’s why the backgrounds for some of the angels and fairies look similar. They were made with this prompt: Waterfalls coming from the clouds, cloud people, fairies, dwarves and dragons, play together in a magical fairytale land –v 5.1 :

And just for the sake of variation, here’s something to give you nightmares:

Sweet dreams, see you in the next one.

Cheers,

Old Man
AI Whispering 8

May 17th, 2023

Fairies

Today I signed into the Midjourney server earlier to try and get more images rendered before it gets busy, which is about noon.

I thought I ought to try a different subject as most of my images are of Angels or Fairies and people might start wondering if I have a thing for them. I thought that Demons might be of interest and asked the Bing AI if it would describe one for me. I asked specifically for a description of a demon standing over a woman who was sleeping.

Bing replied that it would be inappropriate and harmful to describe such a thing. I didn’t want to argue with Bing as it’s given me no nonsense until now so I asked for a description of a Genie instead.

I have spent the day wondering whether Bing might actually know what a Demon looks like and doesn’t want to scare me, or perhaps it’s programmed to respond to things like demons in the way it did.

I typed the description of a Genie into Midjourney and because it included “dark skin” and “clouds of smoke” the image I got was of a Rastafarian with extra long Dreadlocks smoking from a bong.

I went back to Fairies and tried varying prompts. My first was this:

Djinn, dryads, changelings, cloud people, fairies and dwarves, in a magical fairytale land with hearts and flowers and rainbows and I got cool stuff:

The last one would need editing if I wanted to use it as the woman bottom centre, and bottom right corner have three legs and most of the faces are hideous but apart from that, it’s good.

Then I asked for –v5.1 which is the latest version and got better stuff:

Then I asked for hyper realistic with –v5.1:

In case that’s just not enough Fairies for you, here’s a couple more:

That ought to be enough for anyone. See you in the next one.

Cheers,

Old Man
AI

May 16th, 2023

Midjourney continued

Today is another day of experimenting with blending. I’m not really sure what I’m trying to find, whether it’s a certain style or a perfect image, but I spent a lot of time prompting and blending.

I have a few images, mostly abstract and surreal, because that’s the style I like. They don’t make a lot of sense as a set of images but they are pleasing to my eye so I’ll post them.

I don’t know what this might be but it’s interesting;

Death is a woman:

A Forest Fairytale:

Judgement day:

And a couple of warriors:

The server was busy this afternoon and I had long waits for some of the images so that’s it for today. See you in the next one.

Cheers,

Old Man
AI Whispering 8

May 15th, 2023

Midjourney AI

I’ve been at the AI Whispering for a fortnight now and it isn’t what I expected it to be. The first few days I spent experimenting with prompts and artists names, and lighting and styles. There is much to be learnt from this, but this way doesn’t really involve the user. It is just the same as asking an artist to create a work of art based on your description. I prefer to be involved a bit more.

I spent the greater part of this last week learning how the AI blends different aspects of different images, and though it’s not always predictable, you can get a feel for the likely outcome for a blend of two or three images.

I like looking at beautiful women, so I’ve made a lot of images of them. In the first instance, the image will be nice, but ordinary, like the image below for instance:

I then blended it with an image of clouds to get this:

While I really like the above image, it’s lacking in detail and the colors are flat and empty. I wanted something full of life so I used a prompt to generate the next image, so I could blend them:

I know this seems over the top, and at first I would have thought so too but the results are lovely:

I also tried blending it with some Dali type art I found online and got this:

and some surrealist art for this:

I am enjoying the blending, mostly because it gives me something more to do than type words. I have been working on images for the Tarot deck too, though a particular style isn’t yet settled. Here are a couple of preliminary ideas for the Magician and Death cards:

This last one is based on the Hanging Man but it’s just a start:

I am enjoying the Midjourney AI as much today as at the start. The more time I put in, the better my results are. See you in the next one.

Cheers,

Old Man
AI

May 12th, 2023

Midjourney

I spent a lot of time on Midjourney today to get some animal – human hybrid images. Some of them are funny, some are pretty and some are a pretty dark.

The first is a Cheetah Woman;

Tiger Woman

Lioness Lady

Then a Raven Girl

This was a lion too

This was a lion and then a rabbit

You can see the images taking a darker tone as we progress, then things get pretty nightmarish

And on that note, I’ll wish you sweet dreams. See you in the next one.

Cheers,

Old Man
AI

May 11th, 2023

Midjourney, again

Another day on the Midjourney Server, was fun as always. Today though, I got my first job cancelled. I was attempting to blend an image that I had just made with an image from my PC. After a few minutes waiting for it , I went to my messages and found it was stopped because the image filter had flagged it.

There was a warning that trying to circumvent the community guidelines filter could see me unable to use the service. It linked to the image that I had posted, it was one that Midjourney itself had produced a minute or two earlier.

I won’t post it here, because if one filter has flagged it, another may also flag it and I don’t want that. It was not obscene but I can understand why a filter might think so. It was a variation of this image:

I’ll be more careful in the future, I’d rather not get a reputation for flagged images.

There was also another first for me; I had produced a series of images and variations of the same. I had a couple of jobs running at the same time and so just downloaded the upscaled images as I saw them, while scrolling through the server.

One of the images I downloaded was not an image I had selected for upscaling and it didn’t have my name on it. It was one of my images, but someone else had chosen to upscale it. I didn’t know this was possible, so it’s something to be aware of if you’re using Midjourney.

I’m finding that some images will have a watermark or some text where someone might put their signature. I prefer to not have that so I had a chance to use the healing brush in Affinity Photo 2. It does a great job and works exactly the same way as Photoshop, here’s an example, the text is in the bottom left:

removed:

Apart from that, it was just more learning about styles and how images blend. I got quite a few awesome images and I’ll post some here:

Hope you like them, see you in the next one.

Cheers,

Old Man
AI

May 10th, 2023

General AI stuff

This is a blog about AI in general, rather than learning to Whisper to it.

I was listening to Aespa’s new song Welcome to MY world (Feat. nævis) last night. aespa 에스파 ‘Welcome To MY World (Feat. nævis)’ MV – YouTube

I really like it and could write a bit about the other groups I like but the point is that nævis is an AI. I compose music but, although my music might be good, it will almost certainly never be heard by many people. I think our time as composers and singers and songwriters is about up.

AI Music Generator – SOUNDRAW This can compose any music and for around $17 US a month you can sell what it gives you.

There are now whole girl groups in Korea generated by AI. Mave is only one: MAVE: Members Profile (Updated!) (kprofiles.com)

I started thinking about the price of Photoshop after yesterdays blog, wondering why their prices have increased so much over such a short period and I can only conclude that fewer people are using it. For my needs, I could just use Gimp, which is free, I just don’t need all the specialized tools that Photoshop provides.

I think this is the case for a lot of users. If you wanted to create images in the past, of any sort, Photoshop was a must have tool but now, I can just go to Midjourney and ask for whatever image I want. Describe an angel and I get:

An angel, describe a female Angel and get a female angel:

If I want angels and fairies in different styles, I get them:

A couple of years ago, if I had generated angels in software like 3DS, I would still need Photoshop and layer upon layer, trying to make the image beautiful. Now I can just ask for it to be beautiful and it is.

All I need Photoshop for really is for cropping and adjustment layers for hue and brightness changes, so that images match one another if in a sequence. I think Photoshops days are numbered too.

If Midjourney can make images, soon there’ll be an AI making feature films.

I think that very soon all our jobs will be done by AI. There was an article a while ago about ChatGPT passing the Bar exam in the US. It wasn’t trained to pass it, it passed without any preparation. Lawyers will soon be obsolete and if it can pass the Bar exam, I don’t think accounting exams will test it.

We are entering a new age, one where our skills can’t compete with AI, it might be wonderful but what do people do if they have no job to go to? How will they find purpose in life?

Maybe we don’t need a purpose, maybe all we need is a lot of the time at the beach, with robots waiting on us, while we listen to AI generated music.

We’re almost there.

See you in the next one,

Cheers,

Old Man
Ai Whispering 7

May 9th, 2023

Styles, blends and sizes

Today I have mostly been having fun with blending images to see the outcome but I also had to look at image editing software.

I like Photoshop and I would like to use it but at over £20 per month it costs more than it’s worth for me. The next best according to the search results is Affinity Photo 2. I haven’t used it but it costs £70 all in. No recurring monthly payments, pay once and keep.

That’s a bit more realistic, so I download the 30 day trial. The interface is very similar, the tools look similar and the layers panel looks similar.

It’s Photoshop without the Adobe branding.

It doesn’t take any time to get used to the interface, it’s exactly the same as I’m used to. I play around with it for a while and crop a few images, change the hue and export, there’s no difference. I like it and I think I’ll keep it.

I am still finding the right style with the Tarot Deck and I really should continue with that but I feel like a change so I blend some of the images I’ve already made with others that I have on my drive. I really like the outcome with several of them and I’ll post them here;

The first two are my favourite, the images Midjourney can create is still astonishing to me.

I have opened an Instagram account and it’s here: Old Man (@oldmanversusai) on Instagram

I’ll link it on the site soon and for now it’s just got a few photo’s, some of which I’ve posted here but I will be uploading separate images there in the future.

That’s all for now, see you in the next one.

Cheers,

Old Man
AI Whispering 6

May 7th, 2023

End of the first week

The first week was mostly experimenting with prompts and using the same words in a different order. I tried using different artists as a reference and several different art styles.

Things do not always go as planned and getting a scene exactly the way I want it, is sometimes beyond me. I expect this to change over time.

I have spent a lot of time watching videos and reading about other people’s experience of writing prompts. Much of that was pointless because things are changing so very quickly. What worked well in version 4 will not produce anything similar in version 5.

Midjourney is at V5.1 now and the prompts need to be written in a different way. Another thing is that most people do not want to make images that look the way I want them to look. I spend time looking at the images and reading the prompts that are being created on the server while I am waiting for mine to render. The majority are happy to accept any image that a basic prompt produces.

Some folk are using Midjourney for book covers. The prompts are simple and look like this: A book cover for many beautiful children’s stories. That is all they write, and they get some lovely images.

There are requests for images that will clearly be used as an advert, some for shoes, others for credit cards. They are simple prompts and the results are good, but they will never be great.

There are also some very detailed prompts and some awesome images. Some of these images are created using specific words or terms and I tried them myself to see the results. One of them is divine light this lights the object, or person in a unique way and I used it for the image of a golden cup (chalice) which I may use for the Ace of Cups.

I also used it for a dragon image, which I made just to amuse myself;

What I have mainly been doing is trying to produce a set of images in the same style, which will go together in a deck of Tarot cards, and I feel that I am doing quite well at this.

I am using a prompt with the same characteristics to create all the images and then, I blend each of them with an image that has the style I want them all to have.

My first week of learning to AI Whisper ends with this set of images:

The Emperor:

Becomes this, when blended;

The Empress

Becomes this:

The Magician;

Becomes:

The Lovers:

Become:

The High Priestess:

Becomes:

As with the learning of all new skills, perseverance is key. As the late, great, sainted mother used to say; nothing worth having comes easy. Or something like that.

That’s all for now, see you in the next one.

Cheers,

Old Man
AI Whispering 5

May 5th, 2023

Midjourney Gothic Punk

Yesterday was a long day of experimenting and I only received a couple of good images for my time. I learned from it though, so it was not a waste.

Today, rather than trying different artists, I try different art styles. You may find the images produced today, very similar to those I’ve posted before. This is because I’m using the same description in the prompts and using variations for lighting or renderer or just removing the artist name.

I ask for the image of the Queen, which would be the Empress Card, but in the style of Gothic Punk and I receive these:

I like the fourth image so I expand on that:

I like the second and vary it again:

Then I try Cyber Punk:

Then I mix Gothic and Cyber Punk and get these:

I like all the styles but as I’ve mentioned before, the same style must run throughout the whole deck, otherwise it will simply be a collection of really nice images, with nothing in common.

I was thinking about how I might accomplish this overnight and I concluded that I should blend each image with an image that has characteristics that I would like included.

I won’t upload the image as it’s for an ongoing project but I will say that it has intricate patterns in it and that’s how I’m getting the details that I get on the next set of images:

I like these a great deal and so I go through the same process with the Emperor card:

I have more images for other cards that I won’t post today because this blog already has a lot and I don’t want to bore you. I will post the final two for today below;

I like this style and Angela does too, so I think I’ll be moving forward with it.

I used the same description for the Magician card but, although it looks good, I want to try some variations. I also had a go with the Ace of Swords and I’ll post those or their variants over the weekend.

That’s a lot of images so I’ll leave it here for now.

See you in the next one.

Cheers,

Old Man