mikkoph/mikkoani-z-image

Prompt

A high-fashion illustration portrait with complex gritty linework and mute colors of a woman with fair skin. She is wearing a beige elastic bandage. Her head and body emerge from layers of a smoky rose organza fabric. Her makeup is dramatic and artistic, featuring a heavy, smoky eye with dark brown and maroon eyeshadow blended upwards, paired with pale nude lips. Her expression is serious and intense as she looks directly at the camera. The lighting is soft and highlights the texture of the fabric and the contours of her face against a neutral grey background.

Prompt

@mikkoani, muted colors, complex linework. 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.

Prompt

illustration with muted colors. A winter landscape featuring a frozen lake in the foreground with visible cracks in the ice. Snow-covered mountains rise in the background, with a prominent peak at the center. Dark evergreen trees line the shores and slopes. The sky is dark with streaks of clouds. The scene is rendered in a limited color palette of whites, grays, and dark tones.

Model details

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 114 epochs.

Works with both Z-Image-Base + https://civitai.com/models/2362961?modelVersionId=2741469 or with Z-Image Turbo.

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"

With Z-Image-Base you get more freedom and less reliance on the prompt. With Z-Image-Turbo you'll need to be a bit more convincing with your prompt to get the desired effect (unless you desire semi-realism, that comes out of the box)

Best used at 1.0, but can be pushed higher, especially with ZIT.