thelsim

joined 1 year ago
MODERATOR OF
[–] thelsim 11 points 2 weeks ago

Trollivier

@[email protected]


Nightmare VS Day dreaming

Prompt : A portrait split down the middle: the left side of the face is asleep and scared, with nightmarish shadows, terrifying imagery and eerie creatures in the background. The right side of the face is awake and calm, with colorful symbols of peace and creativity like floating flowers, soft clouds, and bright abstract shapes forming a dreamlike, idealistic scene. The two sides blend subtly in the center, showing harmony between fear and peace.

[–] thelsim 3 points 2 weeks ago (1 children)

I don't know, but I felt like sharing :)

The inpainting has definitely improved, a while ago it was impossible to get it to properly match the style of the rest of the image. You could always see where the original was altered. Now it blends much better with the rest of the image.
And inpainting of non-generated images is a recent thing, before that you could only alter images that Midjourney originally created.

[–] thelsim 3 points 2 weeks ago

Toxic Mutant Ninja Turtles

[–] thelsim 4 points 2 weeks ago (5 children)

The inpainting has improved a lot since then. Recently they introduced an external editor that allows you to do more accurate inpainting and even retexturing.
For example, taking one of the images here.

With retexturing I can write: A 1900s photograph, of sailor moon and politicians and a xenomorph, in congress
And have it transformed while keeping the original characters:

There's also the option to repaint:

And to expand the image:

But things it doesn't do well is accurate stuff, like flags, characters, that kind of thing. It likes to hallucinate a little so, for example, you won't get a perfect flag. And even a sailor moon will often look a bit off-brand.

[–] thelsim 2 points 2 weeks ago (1 children)


Let your presentation match your identity :)

[–] thelsim 5 points 2 weeks ago* (last edited 2 weeks ago)


Prompt: 2000s TV talk show, versus, an orc and an elf sitting across from each other, in a tv talk show studio, the orc is wearing crude metal armor, the elf is wearing flowing white robes, the headline "Opposing views" is writting in bold font at the bottom of the screen, the subtitle "Hobbits, tasty or not?" is written in the bottom left, HD-TV screen shot --ar 91:51 --v 6.1

I actually managed to get the proper subtitle, but I liked this one better. Like Gollum managed to sneak in a quick edit before airing :)

[–] thelsim 18 points 3 weeks ago

I’m so devastated to see this happening and am still processing it myself.
Please take care. Best of luck and lots of love from across the pond to all of you.

[–] thelsim 8 points 3 weeks ago

For a moment there I thought I was looking at a [email protected] post and was taking this seriously :)

[–] thelsim 4 points 3 weeks ago

✧✨🌿Allo🌿✨✧

@[email protected]


[–] thelsim 2 points 3 weeks ago

Voting has started for this week's challenge! Follow the cross-link to vote for your favorite image!

Or vote at https://sh.itjust.works/post/27478624

[–] thelsim 5 points 3 weeks ago

M0oP0o

@[email protected]


Took 17 tries, prompt in the Bingitlator was: "Cyber dystopian fairy world wide landscape of brutal tax collection"

[–] thelsim 6 points 3 weeks ago
88
Corn dog [Midjourney] (sh.itjust.works)
submitted 4 months ago by thelsim to c/imageai
 

Prompt: Photograph of a hybrid creature that is a cross between corn and a dog --ar 4:3 --stylize 75 --v 6.1

57
XOXO [Midjourney] (sh.itjust.works)
submitted 4 months ago* (last edited 4 months ago) by thelsim to c/imageai
 

Prompt: boudoir photoshoot, of a xenomorph, wearing a flower wreath on its head, posing on a sofa, Sony FE 24-70mm f/2.8 GM Lens, studio lighting, wide angle --ar 3:2 --stylize 175 --v 6

41
submitted 4 months ago by thelsim to c/imageai
 

Prompt: hand-drawn meiji-era bestiary codex sheet showcasing various mecha-animal hybrids --ar 3:4

Just letting the AI run crazy. It's fun to lean into the madness it creates :)

26
submitted 4 months ago by thelsim to c/imageai
 

Prompt: street photography, of A yeti in a cream linen summer suit with a hat, sitting at a beach cafe, legs crossed, a delicious cocktail is standing on his table, contrasted lighting, cinematic angle --ar 4:3

Taking a well earned vacation from... erm.. whatever it is Yetis do.

41
submitted 4 months ago by thelsim to c/imageai
 

Prompt: western movie still, a Monkey cowboy wearing a cowboy hat and a bandolier, aiming a banana at the viewer, high noon, dramatic lighting --no gun --ar 4:3 --style raw --stylize 75

31
Thatfish [Midjourney] (sh.itjust.works)
submitted 4 months ago by thelsim to c/imageai
 

Prompt: photo of a lot of fingers pointing, at a very confused fish, symmetrical composition

Yes, that one.

60
Dragonfly [Midjourney] (sh.itjust.works)
submitted 4 months ago by thelsim to c/imageai
 

Prompt: fantasy film, A hybrid animal that is a cross between a dragon and a house fly, with a fly's body and a dragon's head, flying above water --ar 4:3 --stylize 75

And some extras:


For some reason a lot of them seemed to breathe fire through their tongue :)

20
Butterphant [Midjourney] (sh.itjust.works)
submitted 4 months ago by thelsim to c/imageai
 

Prompt: Macrophotography, a cute tiny elephant with colorful fuzzy fur and huge black eyes, with butterfly wings, on a branch --ar 4:3

199
Bumblecat [Midjourney] (sh.itjust.works)
submitted 4 months ago by thelsim to c/imageai
 

Prompt: A hybrid animal that is a cross between a cat and a bumblebee

89
submitted 4 months ago by thelsim to c/imageai
 

Prompt: Three little police pigs, with ugly faces, wearing mirrored shades, standing in front of a police car, in down town, low angle, realistic anime style --ar 4:3 --sref https://s.mj.run/57vOVonaDbs --niji 6

I mostly posted this one because the sleaze factor really shines through.
They give me the creeps.

44
Mecharoni and Cheese (sh.itjust.works)
submitted 5 months ago by thelsim to c/imageai
 

Prompt: A mecha, made from macaroni, shooting a cheese sauce --ar 4:3

My one and only entry to this madness :)

46
submitted 5 months ago by thelsim to c/imageai
 

Prompt: back view of A woman in office wear, in an alarmed pose, a colossal list with the words "To Do" written on top is on the horizon, the list has evil eyes and a feral grin, surrounded by smoke and fire, low angle view --ar 4:5 --stylize 76 --niji 6

view more: ‹ prev next ›