Krea 2 LoRA — misapapa71/model-himika-krea2

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 vxy woman to invoke the concept.

Samples

"A cinematic wide shot of a vxy woman wearing iridescent futuristic armor, standing amidst the neon-drenched skyscrapers of a cyberpunk Tokyo rainy night."

"A soft, ethereal oil painting of a vxy woman in a flowing white linen dress, wandering through a sun-drenched meadow of wild lavender and poppies."

"A high-contrast noir photograph of a vxy woman in a sharp velvet suit, leaning against a brick wall in a foggy 1940s New York City alleyway."

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("misapapa71/model-himika-krea2")
image = pipe("A cinematic wide shot of a vxy woman wearing iridescent futuristic armor, standing amidst the neon-drenched skyscrapers of a cyberpunk Tokyo rainy night.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")