Krea 2 LoRA — Ryanhc0917/aria-krea2-hf

Prompt

A cinematic portrait of an ariawoman dressed in iridescent holographic armor, standing amidst the glowing neon skyscrapers of a futuristic cyberpunk metropolis.

Prompt

An ariawoman wearing a flowing linen dress, painting a canvas in a sun-drenched Tuscan vineyard surrounded by rolling green hills and grapevines.

Prompt

A wide shot of an ariawoman as a deep-sea explorer, floating in a bioluminescent underwater cavern filled with glowing jellyfish and ancient coral ruins.

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 ariawoman to invoke the concept.

Samples

"A cinematic portrait of an ariawoman dressed in iridescent holographic armor, standing amidst the glowing neon skyscrapers of a futuristic cyberpunk metropolis."

"An ariawoman wearing a flowing linen dress, painting a canvas in a sun-drenched Tuscan vineyard surrounded by rolling green hills and grapevines."

"A wide shot of an ariawoman as a deep-sea explorer, floating in a bioluminescent underwater cavern filled with glowing jellyfish and ancient coral ruins."

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("Ryanhc0917/aria-krea2-hf")
image = pipe("A cinematic portrait of an ariawoman dressed in iridescent holographic armor, standing amidst the glowing neon skyscrapers of a futuristic cyberpunk metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")