Downloads · 30 days
11
33% of all-time downloads
mju75/karolina-lora-weights
karolina-lora-weights is a text-to-image model from mju75. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
11
33% of all-time downloads
All-time downloads
33
Public
Repo size
778 MB
Likes
0
Public
Click a slice to open those files.
.safetensors576 MB · 59%
From the Hugging Face model README
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).
Use the token k4rolina to invoke the concept.

"A cinematic close-up of k4rolina as a cyberpunk hacker in a neon-drenched Tokyo alley, surrounded by floating holographic screens and rain-slicked pavement."

"An ethereal oil painting of k4rolina dressed as a celestial goddess, drifting through a nebula of gold dust and deep violet cosmic clouds."

"A high-fashion editorial shot of k4rolina wearing an avant-garde architectural gown, standing in the center of a minimalist white marble museum gallery."
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/karolina-lora-weights")
image = pipe("A cinematic close-up of k4rolina 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")