Krea 2 LoRA — juliane5555/12

Prompt

A cinematic shot of a vxl woman wearing neon-cybernetic armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holographic billboards.

Prompt

An ethereal oil painting of a vxl woman draped in flowing white silk, lounging in a sun-drenched Mediterranean garden filled with blooming bougainvillea and marble statues.

Prompt

A gritty, high-contrast photograph of a vxl woman in rugged leather gear, navigating a dusty post-apocalyptic wasteland with a rusted mechanical scavenger drone.

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).

Trigger

Use the token vxl woman to invoke the concept.

Samples

"A cinematic shot of a vxl woman wearing neon-cybernetic armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holographic billboards."

"An ethereal oil painting of a vxl woman draped in flowing white silk, lounging in a sun-drenched Mediterranean garden filled with blooming bougainvillea and marble statues."

"A gritty, high-contrast photograph of a vxl woman in rugged leather gear, navigating a dusty post-apocalyptic wasteland with a rusted mechanical scavenger drone."

Use it with diffusers

import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("juliane5555/12")
image = pipe("A cinematic shot of a vxl woman wearing neon-cybernetic armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holographic billboards.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")