#AI Edits

[deepdreamnights]

The Secret Origin of Wally ManMoth

Scans from TyrannoMax #26

Cocytus was one of the better-performing comic companies outside the big 2 in the 1970s before the whole company was bought out by Buzby-Spurlock Animation in the early 80s.

TyrannoMax was its biggest title, so almost everyone in the character stable teamed up with the Dinoids eventually.

Process under the fold.

TyrannMax is created via use of Dall-E 3 and Midjourney as pencilers, and me doing essentially everything else (writing, editing, inking, lettering, layout, etc.) DE is on most of the character art, MJ on backgrounds and select characters.

Each panel utilizes anywhere from one gen/prompt (for a handful of very simple head-shots) to around 20 for stuff like the DinoHydra action shot or the hero/villain showcase panels.

Once I know what I want for a page I lay out the rough dialog and panels, then start generating pics. Basic prompt format and a few examples:

, , , , comic panel by 1968, in the style of 1968

A portly 50 year old man, resembles Alan Hale Jr, jolly smile, wearing a tweed jacket, slacks, sandals, a fedora, sweatervest and a loosened ascot, full body character design, comic panel by Jack Kirby and Alex Toth 1968, in the style of 1968 Marvel comics

a mad scientist mid-transformation into a green anthro-tyrannosaurus, asymmetrical transformation, boils and growths, screaming/roaring, bald, portly, with round glasses. wearing a tattered lab coat, vest, slacks, tie. Comic panel by jack kirby and alex toth, 1968, in the style of vintage horror comics

Then I take the pics into PS, arrange and composite them, and then remove all the color. I don't tend to prompt for my final colors on characters and instead choose light tones I can easily extract. Why not just do B&W prompts? Style impact.

Then I start to re-ink over errors and details that don't match the mood I want, match line thicknesses over various elements, etc. Through this process I adjust dialog placement and panel arrangements, and do generally the things and editor and letterer would be up to.

Once I have the inks, flat colors, and the text on various layers, I do the weathering and compositing to simulate scans of a 1970s comic book. This is also where the deliberate flaws in coloring and print alignment are added for authenticity.

[94shasha]

८०.रुजुला लक्ष्मी

[theconjurervfx]

[therobotmonster]

Meet Mrs. Natalie Nice...

Natalie is a hard worker in one of today's high-end scientific fields. Why, her boss wouldn't know where the test tubes were kept if not for her tireless efforts! Well, not quite tireless...

She's quite tired. Mrs. Nice has been burning the candle at both ends to impress the boss, and she's about to make a terrible mistake because of it.

Can you spot the mistake Mrs. Nice is making?

That's right! Carelessness in the workplace has consequences!

That wasn't coffee! (good) Coffee doesn't glow green!

Whoopsie! Now Mrs Nice is Mrs. Naughty...lus! Nautilus.

And Mrs. Nautilus is not happy!

By not watching what she was doing Natalie has wasted her whole lunch break turning herself into an abomination of science. All without noting dosage, temperature, and other important factors, not to mention completely circumventing the double blind protocol. Her data is completely invalid for the larger project.

Don't be a Mrs. Nautilus, be a Mrs. Nice! Remember:

Take regular breaks, get plenty of rest, and-

-If the Goo's Alight, it's Not alright!

Drinking glowing goo is the 1% cause of monsterism in adults ages 18-35, please science responsibly, a message from your friends at Cocytus Comics.

Each pic used a different prompt around the basic format of:

Secretary with a bob-haircut, redhead, green blouse and pearls, , , comic panel by Jack Kirby and Alex Toth, 1968, in the style of 60s Marvel

a secretary with lavender skin, tentacles for hair, , , comic panel by jack kirby and alex toth, 1968, in the style of 60s marvel

[satureja13]

AI Edits

Pics above: Ji Ho, Vlad and Saiwa (what's going on with his hair!) The AI only gives a few suggestions (if you don't pay insane 9€/week) so I can't have the same scenerey for all of them. But it's still stunning! It was even more limited since the AI still showed female options for Ji Ho, Saiwa and Vlad. If you want to take a look at the last edits from the AI, they are -> here (there are a few posts, you might want to scroll down a bit) Jeb and Kiyoshi are -> here

Pics below: It's Jack!

Cought Saiwa, Vlad and Jack behind/in a shady club ^^'

Ji Ho and Vlad apparently opened a yoga retreat at Sulani ;) It's fascinating how the AI changes the background so it's similar yet different. The hairstyles are weird omg ö.Ö'

The three princes. I have no idea why the AI changes the distance in each pic, it even cut Sai's hair off -.- But I think in this pic Ji Ho looks the best, Saiwa too. I wouldn't recognize Vlad at all ^^'

And teenage Saiwa and Vlad in a paralel universe where they stan korean boy groups and watch k dramas! Boys over Flowers, ofc. The hair again hahaha

[epilogueofhare]

I've been having so much fun with my photographs and an AI Generator.

Not as accurate with the smaller details that's often overlooked, anyway.

All in all, no complaints.

My main purpose is to just have fun, and see my photographs in a different art form.

One that I'm very fond of.

90s anime.

[knikesh]

I want AI to stop imagining, tired of all these AI imagined pictures.

[gothicabazaar]

[viiisenyas]

Turned my OC into a MK character lmao

[inkskinned]

i love you vaccines i love you research i love you reading the book instead of having chatgpt summarize it i love you critically thinking rather than reacting to a headline i love you investigating the source material i love you science i love you math even though you are personally my enemy (math/yn slowburn) i love you writing even though you try to stab me a lot i love you Experts in Your Field i love you Using The Brain

[deepdreamnights]

Some quick tips for peeps using MJ that don't want it to look like everyone else using MJ.

1. The Ultra Stylish All Dress Alike

First, adjust your style setting (--s (number)). This is how much of the Midjourney 'secret sauce' is added. The lower this number, the closer to your prompt the style will be, at a cost of coherence and 'prettiness'.

Same prompt, same seed, style 500 on the left, style 25 (my preferred setting) on the right. The differences in lighting, pose, skin reflectivity, etc are apparent. You can think of it as a "de-instagram" setting.

3. Use your Variations

"A dinosaur astronaut", original gen, vary (subtle) and Vary (strong) results

If you get something you like for an initial result, the first thing I tend to do is immediately to a Vary (Strong) on it. The results are usually better than the original one because you're essentially re-running the initial prompt with the first result as an additional image prompt, reinforcing the subject.

Using subtle variations to get closer to what you want is one of the big features of MJ, and it's sorely underused.

I recommend setting to low variation mode so your normal variations are subtle ones, and putting on remix mode. Remix mode prompts you to change the prompt every time you do a variation. If you're close but something's not right, that's an easy way to go.

Changing prompts is especially useful if combined with Vary (Region). Basically, if you like everything about a pic but some select details, you can highlight an area and have the system produce new variations just changing that region. It's obvious use is fixing generation errors, but by changing the prompt, you can get results that the robot can't imagine as a solo prompt.

3. Get Weird With It

--weird is a highly unused setting. It's also very powerful, while it goes up to 1000, I tend to not go above 1-5.

A cartoon penguin made of knives at 0 weird, 1 weird, and 50 weird:

Near as I can tell, weird restricts the 'does this make sense' checks, allowing for more out-there results, both in terms of style and subject matter. At the very low levels (1-5) it increases prompt adherence, at higher levels it reduces it substantially.

4. Prompt Big and Blend your Concepts

MJ deals with short prompts by filling in its own leanings where there's gaps, so short prompts look the most midjourney-esq while longer ones (especially when combined with --weird or a low --s value) fight back against it more.

When prompting for art styles, prompting for multiple art styles/artists at once produces weird hybrids. Prompting an artist with the wrong medium (A painting by a sculptor, a drawing by a cinematographer, etc) also can produce new, strange results.

(Lisa Frank/H.R. Giger style mashup using :: technique (below))

But the real trick is in "prompt smashing" or multi-prompting. Basically, midjourney uses :: to split prompts. Intended function is to allow you to add individual weights to each section, if you want something strongly emphasized.

But in practice, it blends the concepts of the two prompts to create a new, third thing.

As above with "an illustration of an armored dinosaur in the woods, in the style of vibrant comics, toycore, ps1 graphics, national geographic photo, majestic elephants, exotic, action painter" then "daft punk & particle party daft punk world tour, in the style of romina ressia, polished craftsmanship, minimalistic metal sculptures, ultra hd, mark seliger, installation-based, quadratura" and then the two prompts run together separated by ::.

Each one was also iterated to produce a better result than the initial gen.

5. Just edit the darn thing.

Learning to edit your works outside of the AI system will always improve your work beyond what the machine itself can do. Whether it's just the simple matter of doing color adjustment/correction:

Or more heavy compositing and re-editing combined with other techniques:

Editing and compositing your gens is always superior to just posting them raw, even if its just a little cropping to get the figure slightly off-center or compiling 20ish individual gens into a single comic-style battle scene before recoloring it from scratch.

But at the very least, before you post, go over the image and make sure there's nothing glaring.

I don't think that making or using AI art/image generation is morally wrong, as you guys know, but I have to admit that slotting a wibbly-lined low effort image selected from the first result set from Midjourney in your content is incredibly tacky. At least select something that looks good. Maybe something without the boring AI "sheen" look either.

You see this a lot in clickbaity content like web spam and youtube shorts attempting to algorithm game.

[94shasha]

८३.नारायणी लक्ष्मी

[theconjurervfx]

[monstertsunami]

i spilled pasta in my backpack and got so mad that i made a traumacore edit about it

[satureja13]

More AI edits. Mainly from Kiyoshi and Jeb. The AI has its problems recognizing the others as males with their long hair -.-

The Gang ^^' The pout hahaha. Amazing that the background is different.

Saiwa and Ji Ho. How beautiful they are. I need to take better pics, maybe with shorter hair.

And Ji Ho as a female. I wish the AI would ask if the person is male or female. But it looks almost like a real photo, wow

[that-butch-archivist]

"Dyke March 1994" by Morgan Gwenwald

source: The Wild Good: Lesbian Photographs & Writings on Love, edited by Beatrix Gates