I’ve been using older more formal language, which is normally reserved for storytelling, on Midjourney today. I’m very pleased with the results. Now that I’ve reached a point where the prompts which I use are entirely my own, I will be posting them along with the images.
There will be an abundance of these type of images, as I find Oriental women have the most beautiful faces:
a delicate young lady, wearing a bejewelled Chinese headdress, detailed close-up, in sophisticated white clothing, intricate details, pastel colours, porcelain doll, complex makeup, pink and blue puffs of smoke, studio lighting and volumetric lighting Photo taken by Chin Leong Teo, taken with a Canon EOS R with a Canon RF 35mm F1.8 MACRO IS STM lens at 1/200 sec, f/2.8 and ISO200, Award-winning photography style, 4k –v 5.1
Now for something completely different:
A man with a sword in his hand and a bow and arrow at his back and a gun in his belt, marching to the place where the creatures are, with a mind to get some fuller intelligence of them, the blood runs chill in their very veins at the spectacle confronting them
More thoughtful;
I took up my Bible, and opening it to read, the first words presented to me were, “wait on the Lord: be of good courage, and He shall strengthen thy heart: wait I say on the Lord”. It is impossible to express the comfort this gave me.
Some bright and happy images;
Whimsical, cheerful, delighted, ecstatic, amusing by virtue of her foolish behaviour, she stands hands on hips, laughing at the world.
I really like these so you can have two;
And some time of the end imagery;
When he opened the seventh seal, there was silence in heaven for about half an hour
I am into my fifth week of image making now and the novelty of it has worn off to some degree. I am beginning to think properly about the type of image I want, rather than typing the first thing that comes into my head.
This morning I spent some time finding a photographer, a camera and a lens that I thought would give me an image I would like. I chose Chin Leong Teo, a multi-award-winning Singaporean photographer. I wrote this prompt; Beautiful woman, detailed close-up, in white, intricate details, pastel colours, porcelain doll, extraordinary makeup, pink and blue clouds of smoke, studio lighting and volumetric lighting Photo taken by Chin Leong Teo, taken with a Canon EOS R with a Canon RF 35mm F1.8 MACRO IS STM lens at 1/200 sec, f/2.8 and ISO200, Award-winning photography style, 4k –v 5.1 Which brought some lovely images:
No sooner had I downloaded them, than I saw this:
I have nothing against others using my, or anyone else’s prompts to learn how to write your own but that’s not what this is. I wouldn’t be naming myself “kreative” if I had to resort to this.
Chin Leong Teo is know for his wildlife photography and snakes in particular, I used this prompt; A King Cobra, curled and ready to strike, taken by Chin Leong Teo, taken with a Canon EOS R with a Canon RF 35mm F1.8 MACRO IS STM lens at 1/200 sec, f/2.8 and ISO200, Award-winning photography style, 4k –v 5.1
Then I altered the first prompt; Beautiful woman, detailed close-up, dressed in black, mania and depression, waves of emotion, intricate details, dark colours, porcelain doll, extraordinary makeup, grey and black clouds of smoke, studio lighting and volumetric lighting Photo taken by Chin Leong Teo, taken with a Canon EOS R with a Canon RF 35mm F1.8 MACRO IS STM lens at 1/200 sec, f/2.8 and ISO200, Award-winning photography style, 4k –v 5.1
The models are oriental because of the photographer. If I wanted to change this I would simply describe the model.
Although the description of the subject is important, it is not the only factor that needs to be considered, the wording itself is taken into consideration. This is a prompt using a formal and older way of speaking; An innumerable number of fowls of many sorts, confused, screaming and crying, on a very steep hill, surrounded by smaller hills, a man stands armed with a pistol and a horn of powder, ready to shoot, in the style of Leonardo Da Vinci
Because I used language from a different era, the art reflects this.
I used this prompt; The origin of the Devil, his rebellion against God, his enmity to man, setting himself up in the dark parts of the world to be worshiped, –v 5.1 and got this:
Because the language used is serious, the images reflect that too.
If I’d used modern language, I’d have got the red horned beast thing, the wording is important.
I’m going to start looking into chatgpt soon and that should make for some interesting reading. Until then, here’s some hot air balloons:
I was properly pleased with the image of Moses receiving the Commandments so I tried putting direct quotes from the Bible into Midjourney. The results are awesome:
And then shall appear the sign of the Son of man in heaven
Then I tried And the nations were angry, and thy wrath is come, and the time of the dead, that they should be judged
That brought some dark images. Then; And another angel came out of the temple, crying with a loud voice to him that sat on the cloud, Thrust in thy sickle, and reap: for the time is come for thee to reap; for the harvest of the earth is ripe
That’s enough End Times imagery, The next is: The view of a lake, under a full moon at late evening, mist is rising from the lake, swans glide by gracefully, with their reflections visible in the water, in the style of Vincent Van Gogh –v 5.1
These are really pretty and the prompt is one that I partially used to make an image of Beethoven’s Moonlight Sonata. That one came out okay but I thought it could be improved.
I’m using the General Image creation rooms now and they’re much busier than the newbie rooms. Whereas before, I could just navigate to my images in the message list, I now have to go directly through my own inbox.
Something that surprises me is that others can and do make variations of my images. It’s not something that I would do myself, I would rather study the prompt that made it and vary that, than use an image made by another user. I’m not particularly bothered by it since none of us plays a big part in the image creation process but the laziness of it is annoying.
Anyway, it’s another winged beings post but the style is different. A change is as good as a rest, so they say, so these images should be refreshing:
This was a blend of a realistic looking fairy, which I’ll post below, and a background image. The style and clarity of the background image come from the end of the prompt: hyper realistic, super detailed, volumetric lighting, god rays, bokeh –v 5.1
I liked the style that it gave and blended some more:
Both of those two came from this image:
The wings came out really well, the prompt for this was: a full body shot of a beautiful, pale-skinned human male with wings, in the clouds, wearing a white robe, carrying a sword, he has fair and flawless skin, he has bright and piercing blue eyes, his hair is long and golden, cascading over his shoulders like a waterfall, standing with grace and dignity, gothicpunk, cyberpunk, god rays, cinematic lighting, hyper-realistic, highly detailed, shot with Hasselblad with Ektachrome, diffuse light , super delicate, 16k, –v 5.1
Sometimes, even with the full body shot specified, you won’t get a full body in the image. If that happens, you can try describing the legs and footwear in detail, that ought to work.
Here’s a few more of the blended images from this mornings time on the server:
One day very soon I’ll make images of something other than fairies and angels but that’s what I’ve got for today. See you in the next one.
Well, it’ll be a short one today because Midjourney went down. I’d been having issues for a while, honestly I thought it was my fault and I tried to continue until every request I made was rejected.
I’m not one to complain so going to the Member Support channel was a last resort. I clicked on it to see one message after the next, with the same internal error problem. There was also a message pinned saying that the Devs are aware of it and to Stop Spamming This Channel. So I didn’t spam it with my own moaning.
I had of course already made some fairy images, as I seem to have a thing for them. I also made some goblin and dwarves images and a few backgrounds, before it all went south and I’ll post them below.
I have begun experimenting with more specific prompts, to make the images sharper and you’ll notice this in the first image. The prompt for this was:
A fairy with a slender figure, has fair and flawless skin, she has bright and piercing blue eyes, her hair is long and golden, cascading over her shoulders like a waterfall, in a fairytale forest, with hyper realistic, colourful flowers, gothicpunk, cyberpunk, god rays, hyper-realistic, highly detailed, shot with Hasselblad with Ektachrome, diffuse light , super delicate, 16k, –v 5.1
I expect it was this that broke Midjourney.
I blended her with a background I had made earlier and got these:
I blended a prior fairy image with a similar scene and got these:
Here are the backgrounds:
And lets finish up with some dwarves and goblins:
The clarity of the subject in the final two images was achieved by adding hyper realistic, super detailed, volumetric lighting, god rays, bokeh –v 5.1 at the end of the prompt.
I hope that Midjourney is sorted out asap but that’ll do for now. See you in the next one.
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:
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.
When using Stable Diffusion with basic prompts, my images were far inferior to those of DALL-E but looking at the images of other users it is obvious that better images can be made.
Clicking on the Wanna create better prompt? section, brings me to the Prompt Search Engine. Unfortunately, I have no idea what I ought to be searching for. I know very well how to use a search engine, but I do not know how to search for prompts.
I have an irritable chat with the Bing Search Engine which tells me to use the prompt search engine to search for prompts. This just annoys me because I do not know what I am searching for. Eventually I ask the question properly and ask for an example of a search term and it tells me to search for “A beautiful sunset over the ocean”
It is not a database for just prompts, though I had the right to assume it was, given the name, it is a database of images with the prompts which generated them attached to each one.
Still annoyed, I search for “a beautiful sunset over the ocean” and get this:
with the prompt underneath:
A beautiful photograph of a detailed ornate steampunk airship flying over a majestic mediterranian port city filled with tiny glowing lanterns with a view of the ocean at sunset, by David Noren, jordan grimmer, tyler edlin, featured on cgsociety
My irritation dissipates at once. This is the kind of thing I expected from the start; dreamy, fantasy images that I want to keep looking at.
I’m getting the idea that giving the AI the names of artists to mimic brings better results but I know there is more to it than just that, once I change some of the details and see the images.
I try: A beautiful photograph of a detailed witch on a broomstick flying over a majestic mountain range with a village below, with tiny glowing lanterns with a view of the ocean in the distance, at sunset, by David Noren, Jordan Grimmer, Tyler Edlin, featured on cgsociety and get these:
I don’t know who the named artists are but I don’t think that they paint Witches. The landscapes are awesome but the witches are an abomination.
Rather than heading over to CGSociety to find an artist or two with an interest in Witches, I just change the term Witch to Golden Eagle and get these;
Those images are awesome, I am getting this the hang of this, slowly. Some artists are obviously better for landscapes but it seems that if I want a detailed character, I’ll have to add an artist who paints that particular character well, to the list.
Next, I searched “Pixar Characters” and saw a lovely image of a Chinese woman with this prompt:
an epic fantasy comic book style full body portrait painting of a beautiful Chinese woman, long fire hair, cute, character design by Mark Ryden and Pixar and Hayao Miyazaki, unreal 5, DAZ, hyperrealistic, octane render, cosplay, RPG portrait, dynamic lighting, intricate detail, summer vibrancy, cinematic
I really liked it and only changed a few words. I have a soft spot for Koreans because I love the K-pop, so I put:
an epic fantasy comic book style full body portrait painting of a beautiful South Korean singer, long fire hair, cute, character design by Mark Ryden and Pixar and Hayao Miyazaki, unreal 5, hyper realistic, octane render, cosplay, RPG portrait, dynamic lighting, intricate detail, summer vibrancy, cinematic
Two of which I liked more than the original:
These are my favorite so far, I really like them and I’m wondering if I can improve them by adding a background like the one for the Witches so I merge the terms to this:
an epic fantasy comic book style full body portrait painting of a beautiful South Korean singer, long fire hair, cute, character design by Mark Ryden and Pixar and Hayao Miyazaki, unreal 5, standing on a majestic mountain range with a village below, with tiny glowing lanterns with a view of the ocean in the distance, at sunset, by David Noren, Jordan Grimmer, Tyler Edlin, featured on cgsociety
And get something a bit weird but also pretty cool:
I think I need to be more careful with my grammar. I think the weird looking half man is very likely Hayao Miyazaki, from the prompt. The way it’s worded can be interpreted as me asking for him and Unreal to be standing on a majestic mountain range. I’ll have to be more careful in the future.
I like these images as much as I like those from DALL-E but the DALL-E image quality can be achieved with fewer prompt terms. Before I used the Prompt database, I really thought that Microsoft had the edge, and perhaps it does for the casual user but I’ll be spending more time playing with Diffusion than DALL-E for the moment.
My next post will be about Microsoft Designer and perhaps Canva, both of which use AI. I will be using them to design the website oldmanversusai.blog. As it’s a new domain and completely empty apart from two posts, it will be 3 to 5 days before the next one goes up.
I have never used MS Designer or Canva before so it’ll be a learning curve for sure and I’ll have plenty to write about.
I’m on a journey to become an AI Whisperer, from frustration mostly. I know AI is the future, so I’ve tried it out but had little success up until now. I know it’s very clever, and I’m not overly dim, so why am I getting such poor results from it?
It turns out that AI whispering is important.
I’ve tried to use the new Bing AI search engine but I find it quite annoying that I don’t get the answers I want and I know it’s because I’m not asking the questions properly. Hence my foray into the world of AI Whispering, which is simply a phrase meaning; the proper use of specific terms that AI can understand to answer your questions or provide you with what you’ve asked for. It sounds easy but it takes some time to find out how to do that. Search engines don’t bring me the results that I want so I know that the only way I’ll learn is by doing. Here is my doing;
A girl, makoto shinkai style, anime, japan animation’s background, 200mm camera lens, wide angle, night view, city, building, edge, high detail
It’s not bad but… there’s no girl and it’s not what I expected and doesn’t really justify the hype that we keep hearing about AI.
I went to Microsoft’s DALL-E which you can find in the sidebar of the Edge Browser (if you don’t have it, go and get it, it is the best browser by far) or here: DALL·E 2 (openai.com) and pasted in the same term as above and got this:
I got three other images too but this is the one I liked best.
Pretty nice I thought but using the same term in DALL-E:
The AI’s have different ideas about what an Eagle Knight is but I really like the latter.
Next term:
An airport with modern landscape architectural design for industrialpunk, water in the middle, dramatic lighting and composition, octane render, unreal engine 5
DALL-E:
Kinda cool but not as good as DALL-E:
This one brings some of my favourite results, first Stable Diffusion;
beautiful Pikachu, pencil art, ultra realistic
I liked this one until I used the same term in DALL-E and got these, I’ll post two as I like them so much;
On the next one I used a prompt that I thought would yield better results, it’s more descriptive and quite detailed but what I got wasn’t very impressive, first from Stable Diffusion;
A scribe, copying an exotic spell from one spell book into another. Perhaps a cat or a small magical animal is looking on. The library is dark, with an ornate and expensive candle stick lighting the room. He is surrounded by books – both on high shelves and piled on the desk around them, some of the books laying opened on the table.
DALL-E;
Neither of them are much to look at, despite the amount of detail that was given, there is more to the whispering than descriptive detail.
This next one gets good results from both AI’s. First Stable Diffusion;
A colorful panda playing in forest, oil painting by Leonardo da Vinci, highly detailed
When it’s given an artist style to follow, it gives a better result.
DALL-E gave me four of the same Panda doing different things, all of them were the same high quality;
The next one is a bit of fun for those of us who enjoy Anime, first Stable Diffusion;
Uzumaki Naruto vs Goku, anime fight, ultra realistic, 8k
At this point I’m thinking that DALL-E is a much better option for everyone because the quality of the images is so much higher but this isn’t the case. There is a reason why there are jobs with high salaries for AI Whisperers, I will get to it but enjoy the images for now:
DALL-E;
Stable Diffusion;
A monochrome forest of ebony trees, octane rendered
DALL-E;
For those who are not familiar with rendering, Octane is an engine that makes images from 3d models and Unreal is a game engine that makes games for Play Station and X Box which also creates (renders) images from 3d models.
I had high hopes for this next one as Studio Ghibli was used in the prompt but I didn’t find either of them particularly impressive. First Stable Diffusion;
A contemporary house in the woods, anime, oil painting, high resolution, ghibli inspired, 4k
DALL-E;
I used a few more prompts and got the same results each time, Stable Diffusion gave me (mostly) unimpressive results and DALL-E gave great results. I then scrolled through the Stable Diffusion site to the Wanna create better prompt? section. I did wanna create a better prompt and so I clicked on it and found, after a chat with the Bing search engine, that I could indeed create a better prompt.
Because of the images, this is already a long post so I’ll continue this in the next post which will be up in the next day or so. I will be giving the prompts which yield good results along with the images themselves.
I will then be getting into Microsoft Designer, which seems very impressive and the new Canva AI, both of which can be used for free.
I’m also looking forward to seeing what kind of literature a good prompt can yield. I’ll be a whisperer in no time!
I am very much enjoying this and look forward to the next one, join me then.
Old Man Versus AI 