Downloads · 30 days
25
32% of all-time downloads
lyramaddox00/pavaga
pavaga is a text-to-image model from lyramaddox00. 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
25
32% of all-time downloads
All-time downloads
78
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 vkr girl to invoke the concept.

"A cinematic wide shot of a vkr girl wearing neon-tech gear, standing amidst the glowing skyscrapers of a rainy cyberpunk metropolis at night."

"A dreamy, ethereal oil painting of a vkr girl wandering through a sun-drenched meadow of giant crystalline flowers under a lavender sky."

"A high-detail macro photo of a vkr girl dressed as a steampunk explorer, adjusting brass goggles inside a dusty 19th-century clockwork library."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("lyramaddox00/pavaga")
image = pipe("A cinematic wide shot of a vkr girl wearing neon-tech gear, standing amidst the glowing skyscrapers of a rainy cyberpunk metropolis at night.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")