Downloads · 30 days
15
36% of all-time downloads
outsidework/kxx-jezzy
kxx-jezzy is a text-to-image model from outsidework. 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
15
36% of all-time downloads
All-time downloads
42
Public
Repo size
779 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 kxx_jezzy to invoke the concept.

"A hyper-realistic portrait of a futuristic cyborg feline with neon circuitry glowing under a rainy cyberpunk cityscape, kxx_jezzy, 8k resolution, cinematic lighting."

"An oil painting of a majestic golden lion lounging in a surreal floating garden amidst pastel clouds and crystalline waterfalls, kxx_jezzy, impressionist style."

"A macro photograph of a tiny mechanical spider crafted from clockwork gears and rubies, perched on a dew-covered autumn leaf, kxx_jezzy, shallow depth of field."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("outsidework/kxx-jezzy")
image = pipe("A hyper-realistic portrait of a futuristic cyborg feline with neon circuitry glowing under a rainy cyberpunk cityscape, kxx_jezzy, 8k resolution, cinematic lighting.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")