mikkoph/mikkoani-klein4b

mikkoani Style

Prompt

a closeup fashion portrait illustration of a woman wearing a large hat covering one of her eyes. The contrast is very stark between the shaded part and the highlights

Prompt

@mikkoani illustration, masterpiece, best quality, score_9, score_8, 1girl, plague doctor mask, black gloves, upper body, plague doctor \(darkest dungeon\), holding a black powder bomb, vibrant colors

Prompt

@mikkoani illustration, zombie portrait walking dead astronaut, walking on a desolated planet, human face, cyborg man | with a visible detailed brain | muscles cable wires | biopunk | cybernetic | cyberpunk

Prompt

@mikkoani illustration. A profile view of a figure with a cracked porcelain-like white surface covering the head and body. Golden lines fill the cracks. The figure has closed eyes with dark makeup, dark lips, and an exposed mechanical neck structure with visible vertebrae and internal components. A large golden flower is positioned behind the ear. The background is completely black.

Prompt

@mikkoani. A penguin stands in profile facing left in an arctic landscape. The penguin has a black head and back, white belly, and orange-yellow markings on its neck and beak. Its eye appears red. The background shows icy terrain with floating ice chunks in water and ice formations in the distance. The sky is dark gray with streaks suggesting clouds or wind.

Prompt

@mikkoani. A muscular man with dark spiky hair intensely eats noodles from a large black bowl using chopsticks. He wears a black shirt and leans forward with a focused expression. The bowl contains ramen with two halves of a soft-boiled egg, green vegetables, and broth. Steam rises from the hot noodles. The setting appears to be a ramen shop with wooden walls, posters with Asian characters, and other patrons in the background.

Model description

Trained on 44 images I generated using https://civitai.com/models/2217715?modelVersionId=2485111 with a specific prefix prompt and processed with a detailer. Trained for 54 epochs.

The LoRA doesn't have a fixed trigger word (was trained with @mikkoani but seems to be irrelevant) but can produce different styles depending on the prompt.

My favorite triggers are:

"mature illustration with muted color and complex linework"

"fashion sketch"

"mature anime illustration"

you can make the images creepier with "horror themes"

Best used at 1.0, but can be pushed significantly higher.

Download model

Download them in the Files & versions tab.