#Midjourney v5

[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.

[youare-number6]

Spaceport Cityscapes - Pt 1

Lots of moons and booze

[ai-dump]

AI Prompt: “a robot made paper with red and gray paint, in the style of cargopunk, dark silver and light orange, wood sculptor, marvel comics, mottled, cottagepunk, heavy outlines rendered as a grungy oil painting by Ashley Wood, --ar 103:125 --niji 5 --style expressive --s 300 --c 20”

[asdaricus]

More marble sims. Although simple, they are fascinating and pleasing to look at.

by Midjourney v5

[therobotmonster]

TryannoMax, Issue 25, October 1977

Cocytus Comics Group, Story by Barry McDermit, lines by Midge Joulet & Dale Ethree, Colors and Letters by H. Haddaway.

Issue #25. It's a quiet day so the Core team gets some R&R. TryannoMax hunts down Dr. Underfang for a long-overdue confrontation, DeinoSteve and PteroDarla finally have that date, and Wally Manmoth visits home. So when Ape-Tomic Pyle returns from the grave to exact his revenge, only TriceraBruce remains to stand in his way. One wounded dinoid against a living nuclear ape-pocalypse, with the populace of Wisconsin in the balance.

Running for an astounding 80 issues, TyrannoMax was the headline comic from Cocytus in the 1970s, and was the primary motivator behind Buzby-Spurlock buying out Cocytus in '83.

While the comic series is considered the root of the empire that would create the animated series and live action movie, the concept was first introduced in short story "Humanity, My Young Cousin" in the pulp-sci-fi magazine Stunning True-Life Tales of Science Fiction, a few years earlier.

May be posting interior pages soon.

Full details under the fold.

TyrannoMax is my AI dinosaur test kitchen, where I see how ideas work out before trying them on more serious projects.

Here, I've used Dall-E 3 through Bing and Midjourney to create comic assets, which I then de-color and rework into inks in a similar fashion to my AI-comic reworkings like Robots Ruined the Internet and Let's Gib About Ib, or any of my other fake comic covers. TriceraBruce and Ape-Tomic Pyle were generated with Dall-E 3, and the background was made in Midjourney.

This makes the basic inks, from there I correct anatomical problems, cleanup AI wonk, and generally re-ink where things are needed.

Once I have the "inks" its then a matter of doing the coloring and graphic design work the old fashioned way. I used my recreation of the 1981 DC comics palette for my colors, used post-processing to get the printed look, and there you go.

My prompt format for the characters is:

A -anthro wearing , long tail (if a dinosaur) , comic panel by 1968, in the style of 1960s Marvel comics

Because all weights are averaged a bit, to get a 1970s comic look, you have to prompt for late 60s, ortherwise it looks late 80s.

Background prompt was:

a distant city, a rocket launches from its center, flying toward the sky, comic illustration by jack kirby, inked lines, flat color, blue sky, green grass, orange rocket, from 1968

[jellyfisharcade]

This is getting f-ing insane. Midjourney V5.1 + Lightroom + RealEsrgan upscaling. Update for V 5.1 released 3 or 4 hours ago. I should get sleep but holy hell.....

[generativesluice]

Public Domain AI Image Grab-Bag 15

Sci-Fi Grab-Bag

Donations/Tips are accepted via paypal.

These images are free to use, all generated within Midjourney. These unedited images were not subject to sufficient interference by humans to meet the minimal expression standard, and are, as such, public domain.

[hunghobbit]

Game of thrones Stark kids studio Ghibli style

[allaboutaiandme]

To be continued...

[deepdreamnights]

Jackal Lanterns

The seeds of smashed Jack'o lanterns, if not swept up and thrown away, may take root. The twisted gourds mature over the course of a single year, until they rise to hunt the following Halloween.

Those in costume are invisible to Jackal Lanterns, though the stench of tricks will still draw them to their prey.

Prompt and process under the fold

Midjourney can't make a jackal lantern. It's current parser can't beat the 3 basket problem enough to put a pumpkin on a dog's head, maybe in v6.

Rather than use Dall-E 3 (because its slow as heck as I type it and I have another project baking there) I used the new in-painting tool. First, I generated the Jackals:

Prompt: a painting of a supernatural jackal, orange fur, glowing green spots, breathing green fire, running down a country road, moonlit night, spooky, horrifying, painting by wayne reynolds and wayne barlowe, side view :: a jackal runs through a haunted forest at night, filled with floating green spirits, bare trees, halloween scene

I then inpainted the heads and muzzle areas, and a section around the head big enough for an appropriate gourd, and changed the prompt to:

Prompt: a jack o' lantern, breathing green fire, spooky, horrifying, painting by wayne reynolds and wayne barlowe :: a jack-o-lantern with sharp teeth, glowing with green fire

[youare-number6]

Spaceport Cityscapes - Pt 2

More booze and some desert

[ai-dump]

AI Prompt: “the artwork depicts an abstract design of a glass dome, in the style of frank gehry, apocalyptic visions, cinestill 50d, piles/stacks, ossip zadkine, torn, distressed edges, tokio aoyama --ar 103:224 --v 5 --iw 1 --ar 4:5 --s 500 --c 20”

[asdaricus]

Depictions of the Goddess Luna in the Style of Maxfield Parrish

by Midjourney v5

[therobotmonster]

This is what I see every time someone starts talking about integrating Chat-GPT into anything involving facts or accuracy.

The image is partially generated in Midjourney V5, but is a composite of multiple generations and photos of Furbies because generative AI makes novel data, but that means it doesn't make accurate data.

And its idea of a furby is a sort of muppet-bird. The robots make aesthetically pleasing nonsense. The meaning is always human applied.

Prompt: an 18th century carnival barker con-man selling furbies from a medicine show wagon, colorful clothes, boisterous, holding a furby out to the viewer, photograph still from the Music Man (1962)

[timetravellinghipster]

9 Month AI Update

The way they slowly get split up and go missing is sending me