Downloads · 30 days
4
31% of all-time downloads
AllwaysFurious/vntrbrs
vntrbrs is a text-to-image model from AllwaysFurious. 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
4
31% of all-time downloads
All-time downloads
13
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 phrase vntrbrs to invoke the concept.

"A majestic snow leopard leaping across a jagged Himalayan cliffside during a heavy blizzard, crystalline snowflakes clinging to its thick fur, vntrbrs"

"A sleek, futuristic chrome motorcycle speeding down a neon-lit Tokyo highway at midnight, leaving long streaks of electric blue light in its wake, vntrbrs"

"An elderly clockmaker with brass goggles meticulously repairing a floating steampunk timepiece in a dusty workshop filled with golden gears, vntrbrs"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("AllwaysFurious/vntrbrs")
image = pipe("A majestic snow leopard leaping across a jagged Himalayan cliffside during a heavy blizzard, crystalline snowflakes clinging to its thick fur, vntrbrs", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")