Krea 2 LoRA — misapapa71/model-amane-krea2

Prompt

A cinematic portrait of model-Amane-krea2 wearing futuristic neon armor, standing amidst the rainy, glowing skyscrapers of a cyberpunk Tokyo street.

Prompt

model-Amane-krea2 dressed in a flowing vintage linen gown, reading an ancient leather book in a sun-drenched Mediterranean library with ivy-covered walls.

Prompt

A high-fashion editorial shot of model-Amane-krea2 submerged in a surreal crystalline ocean, surrounded by floating iridescent jellyfish and shimmering bubbles.

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 model-Amane-krea2 to invoke the concept.

Samples

"A cinematic portrait of model-Amane-krea2 wearing futuristic neon armor, standing amidst the rainy, glowing skyscrapers of a cyberpunk Tokyo street."

"model-Amane-krea2 dressed in a flowing vintage linen gown, reading an ancient leather book in a sun-drenched Mediterranean library with ivy-covered walls."

"A high-fashion editorial shot of model-Amane-krea2 submerged in a surreal crystalline ocean, surrounded by floating iridescent jellyfish and shimmering bubbles."

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-amane-krea2")
image = pipe("A cinematic portrait of model-Amane-krea2 wearing futuristic neon armor, standing amidst the rainy, glowing skyscrapers of a cyberpunk Tokyo street.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")