I resolved the audio issue and will be posting video’s soon. I was going to do it today but there is a good deal of drilling going on outside my front door, so it’ll be the weekend or next week.
I’m experimenting with people and styles this morning and I have some really nice images. I tried Winston Churchill in the style of Michelangelo, then in an Anime style by Yuumei:
I then asked for beautiful Korean women, the prompt included futuristic outfits. These are some of my favourite images so far:
I liked these so much that I asked for an Anime image of Jennie Kim. I don’t think the AI knows who she is but the images are awesome:
Black Pink is the revolution but different Jennie.
The next one was refused initially because the prompt included the word “scars”. You can appeal things like this but I just removed it as it wasn’t important:
These next were just for fun and are really pretty to look at:
I was going to record my time on Midjourney today, so people can see the creation process. I’m having audio issues though; loud interference when I click on anything. I have too many devices connected, I’ll resolve it though and post one soon.
I continued with different styles today. I wanted to see how Michelangelo would have painted the Mona Lisa. It turns out, he’d have done it almost the same:
The third one is my favourite:
I then asked for it done in the style of Neil Blevins, whose art I quite like:
I then wondered what it would look like if Beatrix Potter had painted it:
I like these a lot
Beethoven is my favourite composer and I wanted an image of him as though painted by Michelangelo:
Angela is thinking of reinventing her website later this year so I did some fun images for her:
I think they suit her. Here’s a watercolour of a pretty Korean girl:
Being as old as I am, yet still handsome, I remember the day Elvis Presley died. I don’t remember it because I particularly liked his music but because of the fuss the girls made about it. One particular girl, a friend of Angela named Lorraine, made such fuss that I thought she was related to him. I was only young then and didn’t yet realise that girls were “different”.
I thought that I’d show the different styles of Midjourney, using a person that most will be familiar with and Elvis is quite well known.
I started by asking for a charcoal sketch: Elvis Presley, charcoal sketch, thick lines, basic shapes, abstract, old paper –v5.1
Then just a white image: a white portrait of Elvis Presly absolutely amazed, happy, eyes wide open, hungry. 3D. Monochromatic white. Ultra detailed. Ultra realistic. White background.
I like them, they’re pretty accurate and look like photos. Then an oil painting by Michelangelo:
I shouldn’t be surprised at how good they are, considering the artist but I am. Then I tried some anime: An anime image of Elvis Presley in the style of Yuumei
Although there’s only a passing resemblance, I do like the style. I tried another couple of artists, who I’ve never heard of but whose art I saw in a document. Again, the resemblance isn’t great but the style is nice:
Then I just blended a couple of Elvis with some others for fun:
I am three weeks into this AI Whispering thing now and my progress is slow but sure. I know how it all works and I’ve produced some great images with both prompts and image blending.
Rather than reposting my favourite images, I thought I would use my favourite prompts to recreate the images, using the most divisive character I could think of. I think most people would agree that this would be Donald Trump, so here he is in different situations as different characters:
Using my prompt for Cerberus the hell hound, here’s Donald walking his puppies:
From my Angels in the clouds prompt, here’s Donald as an Angel:
From the evil Jester prompt, evil Donald:
Using my fairy and dwarves prompt, here’s Donald playing with Fairies:
These last two are from a prompt I haven’t used before but they came out pretty well:
Whether you love him or hate him, he is entertaining. That’s all for now, see you in the next one.
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.
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.
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.