A surreal digital artwork of an old lighthouse with warped geometry, vibrant colors blending purples, oranges, and blues, featuring abstract shapes and a trippy, 60s op art style.
A woman in a red coat walks alone on a snowy road under a vivid aurora borealis with a dramatic orange and blue sky at sunset.
Cowboy and alien playing poker in a neon-lit western saloon, featuring fantasy illustration and vibrant colors.
Extraterrestrial grays gaze at Earth amidst a cosmic scene.
Atmospheric surreal landscape with towering structures and vibrant sky.
Vampire Lord Nosferatu in red-black theme with cityscape.
A dark, hooded figure with glowing red eyes and a red orb on its chest stands against an apocalyptic urban background with a red and white abstract circular design. This is an AI generated image using stable diffusion.
A stormtrooper walking through a large, black portal in a desert landscape. This is an AI generated image using Stable Diffusion.

Recommended Prompts

otclillsn, baffling optical illusion, disorienting angle

Recommended Negative Prompts

people, 3d, cgi, low resolution, noise, grain, haze

Recommended Parameters

samplers

DPM++ 2M Karras

steps

10 - 20

cfg

3

resolution

768x1024, 816x1080

other models

SDXL - wildcardxXL_wildcardxXL (1170aa1935)

Recommended Hires (High-Resolution) Parameters

denoising strength

0.4 - 1

Tips

Use a weight like 0.8 or lower because there are a lot of different styles combined in the dataset.

Changing just one word in the prompt, regardless of its sense, can drastically alter the image.

Even nonsensical prompt combinations can produce interesting results.

Flux 1.0

Longwinded explanation will follow, maybe, 'cause Flux is fluxing.


A little helper for weird looking pictures that are a bit more on the interesting and don't reveal everything at the first glance.

  • Adds weird geometry and optical illusions

  • Changing just one word, no matter if it makes sense or not, can change everything

  • Even nonsensical prompt combinations could lead to something

  • A weight like 0.8 or lower is recommended because there are a lot of different styles combined in the dataset.

There was no intention behind this LoRA apart from me getting a bit bored and testing a few things. Like with all my LoRAs i will sooner or later find a good use for it. Combing even the most ridiculous models that shouldn't fit together is the best thing.

Previous
YFG Hyper [FLUX] - v1.0
Next
style of Andreas Achenbach [SDXL] 102 - v1.0

Model Details

Model type

LORA

Base model

SDXL 1.0

Model version

SDXL v1.0

Model hash

f46c5bd638

Trained words

otclillsn

Discussion

Please log in to leave a comment.

Model Collection - Flux.1 D / SDXL - Impossible Geometry

Images by Flux.1 D / SDXL - Impossible Geometry - SDXL v1.0

concept Images

distortion Images

drawing Images

optical illusion Images

surrealism Images