Krea 2 LoRA — Nbunberry/krea2loranvoid

Prompt

A cinematic shot of vky_woman wearing futuristic neon armor, standing amidst the towering chrome skyscrapers of a rainy cyberpunk metropolis.

Prompt

A serene oil painting of vky_woman in a flowing white linen dress, strolling through a sun-drenched lavender field in Provence.

Prompt

A gritty, high-contrast photograph of vky_woman as a rugged wasteland survivor, scavenging for parts in a rusted desert scrapyard.

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 vky_woman to invoke the concept.

Samples

"A cinematic shot of vky_woman wearing futuristic neon armor, standing amidst the towering chrome skyscrapers of a rainy cyberpunk metropolis."

"A serene oil painting of vky_woman in a flowing white linen dress, strolling through a sun-drenched lavender field in Provence."

"A gritty, high-contrast photograph of vky_woman as a rugged wasteland survivor, scavenging for parts in a rusted desert scrapyard."

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("Nbunberry/krea2loranvoid")
image = pipe("A cinematic shot of vky_woman wearing futuristic neon armor, standing amidst the towering chrome skyscrapers of a rainy cyberpunk metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")