Krea 2 LoRA — mju75/klara2-lora-weights

Prompt

A hyper-realistic portrait of kl4ra as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by floating holographic screens and rain-slicked pavement.

Prompt

An ethereal oil painting of kl4ra dressed as a woodland deity, lounging in a sun-dappled ancient forest amidst glowing mushrooms and iridescent butterflies.

Prompt

A cinematic wide shot of kl4ra in a sleek white spacesuit, standing on the edge of a crystalline cliff overlooking a swirling purple nebula on a distant planet.

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 kl4ra to invoke the concept.

Samples

"A hyper-realistic portrait of kl4ra as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by floating holographic screens and rain-slicked pavement."

"An ethereal oil painting of kl4ra dressed as a woodland deity, lounging in a sun-dappled ancient forest amidst glowing mushrooms and iridescent butterflies."

"A cinematic wide shot of kl4ra in a sleek white spacesuit, standing on the edge of a crystalline cliff overlooking a swirling purple nebula on a distant planet."

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("mju75/klara2-lora-weights")
image = pipe("A hyper-realistic portrait of kl4ra as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by floating holographic screens and rain-slicked pavement.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")