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
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
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
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
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
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
Midjourney Tarot
It’s a day of experimenting with prompts and artists names. The plan is to create a deck of Tarot cards, with characters and scenes that share a particular style throughout.
I ask Bing to describe a beautiful tall Queen dressed in white, in detail and Bing kindly does. I change some of the details and add Michelangelo as the artist. The result is very impressive:
I like the second image so I ask for variations of that:
I like the second one again and ask for an upscaled version:
I like these images so much, I find it hard to believe they were created with just a few words from an old man. That is the image of a beautiful woman; asked for and received.
I know by now that Midjourney can produce extraordinary images, but I do not know if it will generate consistently similar styles over time. I try a prompt with a description of the Fool card, giving the same settings as before and specifying Michelangelo. The result is not even close to the prior images:
There’s not much wrong with them but they are too different to be images for the same deck of cards. I have to find out what’s going on here.
I go and study to find out why, and there are so many reasons that I would bore you to tears if I told you. Midjourney is entirely different from the web-based AI’s that I have used up to this point, which work primarily using keywords, as a Search Engine will. Midjourney takes extremely specific instructions.
I Study a bit more and realize that not only are the words important but the order of the words is as important as the words themselves. I put more detail into the description of The Fool, than the Queen and this is why there is the big difference.
I try a new prompt , then more still; changing the order of words and changing the artist names. I get some nice results;
The final image is the closest I’ve got to the Fool facing away from us, which I specified over and over. It’s not perfect but I’ll take what I can get today.
The servers got really slow after this one so I left things there. Progress is slow but Rome wasn’t built in a day.
See you in the next one,
Cheers,
Old Man
Midjourney AI
I am glad that I said the next post would be 3-5 days because it has been a fun filled little while.
There is more to the AI whispering than I first thought. I do not mean it is more difficult, there are just things that need to be considered that could not be anticipated. I will get to them as I update you on my endeavours.
Angela wants a Tarot Deck for her customers, and I said I would design one. As always, I asked the Bing AI how I should go about it and it sent me to Midjourney.com. If you want to sell the images you make, this is the only option; you cannot sell DALL-E images, it is in the terms that you agree to. It is not clear for Stable Diffusion, but I think those images remain Public Domain. Midjourney it is then.
To use Midjourney you need a Discord Server, so I downloaded and installed. I have meant to get Discord for a long time, but I am old and things slip my mind. The trial period only gives you 25 minutes of GPU time and because I did not want to waste any of that time, I decided to research as much as I could beforehand.
Research and type were all I did for most of the day. I have lists of every emotion that exists. I know every type of art style, all the lighting terms, all the renderers, all the aspect ratios and I have seen and studied hundreds of prompts.
Finally ready to try my hand at Midjourney, I asked Bing for a detailed description of a city street. It gave me this: “The kaleidoscope of shimmering lights flicker in the distance as the starry sky sweeps over the city that never sleeps. Hazy clouds envelope the moon so it was in its own realm of perpetual darkness. The wet, desolate streets of the city rested in silence as the starry black sky wept over it.”
I pasted it into Midjourney and it said: Due to extreme demand we can’t provide a free trial right now. Please /subscribe or try again tomorrow.
Marvellous, isn’t it? With some quiet muttering under my breath, I signed out and left it for the day.
Not wanting to face another due to extreme demand message, I bought a subscription to Midjourney the next day. The Bing description of a city street produced a rather good image without any input from me, here it is:
Remembering the Tarot Deck, I asked Bing for a description of the Fool Card, because I like fools. I took part of that description and added some details myself. I won’t give you the prompts for these because they are for someone else but I started by adding the Artist Monet to the description and then, one of my favorite’s, Turner. The results are below.
Monet;
They are quite representative of Monet but a bit boring so I tried Turner, whose landscapes I like very much;
I think that if you want a deck of cards designed, you could do worse than include Turner as an influence but I’m not through with experimenting and I really want to see what including Michelangelo will do. That will be in another blog.
For now I feel like playing around and I expand on the fool reference and go for a Court Jester and this is my favorite image so far;
I’ll be opening an Instagram account soon to post more images like this and I’ll let you know when it’s live.
That’s enough for one post.
See you in the next one,
Old Man
Old Man Versus AI 