Krea 2 LoRA — mju75/tereza-2-lora-weights

Prompt

A cinematic close-up of t3reza as a cyberpunk hacker in a neon-drenched Tokyo alley, surrounded by floating holographic screens and rain-slicked pavement.

Prompt

An ethereal oil painting of t3reza dressed as a celestial goddess, floating amidst swirling golden nebulae and shimmering stardust in deep space.

Prompt

A high-detail National Geographic photograph of t3reza exploring an ancient overgrown Mayan temple, with shafts of sunlight piercing through a dense emerald jungle canopy.

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 t3reza to invoke the concept.

Samples

"A cinematic close-up of t3reza as a cyberpunk hacker in a neon-drenched Tokyo alley, surrounded by floating holographic screens and rain-slicked pavement."

"An ethereal oil painting of t3reza dressed as a celestial goddess, floating amidst swirling golden nebulae and shimmering stardust in deep space."

"A high-detail National Geographic photograph of t3reza exploring an ancient overgrown Mayan temple, with shafts of sunlight piercing through a dense emerald jungle canopy."

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/tereza-2-lora-weights")
image = pipe("A cinematic close-up of t3reza as a cyberpunk hacker in a neon-drenched Tokyo alley, surrounded by floating holographic screens and rain-slicked pavement.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")