Downloads · 30 days
8
26% of all-time downloads
Fragile/lilyv1
lilyv1 is a text-to-image model from Fragile. 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
8
26% of all-time downloads
All-time downloads
31
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 L!1y to invoke the concept.

"A hyper-realistic macro shot of a glowing neon L!1y flower blooming amidst a futuristic cyberpunk cityscape of chrome and rain."

"An oil painting of a serene L!1y floating on a mirror-like pond in a mystical, fog-covered ancient Japanese garden."

"A cinematic wide shot of a giant, crystalline L!1y sculpture towering over a desolate white salt flat under a violet alien sky."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Fragile/lilyv1")
image = pipe("A hyper-realistic macro shot of a glowing neon L!1y flower blooming amidst a futuristic cyberpunk cityscape of chrome and rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")