Krea 2 LoRA — beepbeep2724/lyna-b1mb0

Prompt

A hyper-realistic cinematic portrait of lyna_b1mb0 as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by floating holographic screens.

Prompt

lyna_b1mb0 wearing ornate gold armor, standing majestically atop a snowy mountain peak during a vibrant purple aurora borealis.

Prompt

A whimsical oil painting of lyna_b1mb0 sipping tea in a cozy Victorian library filled with floating books and warm sunlight.

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 lyna_b1mb0 to invoke the concept.

Samples

"A hyper-realistic cinematic portrait of lyna_b1mb0 as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by floating holographic screens."

"lyna_b1mb0 wearing ornate gold armor, standing majestically atop a snowy mountain peak during a vibrant purple aurora borealis."

"A whimsical oil painting of lyna_b1mb0 sipping tea in a cozy Victorian library filled with floating books and warm sunlight."

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("beepbeep2724/lyna-b1mb0")
image = pipe("A hyper-realistic cinematic portrait of lyna_b1mb0 as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by floating holographic screens.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")