Downloads · 30 days
12
100% of all-time downloads
qwerwinter/vylra28
vylra28 is a text-to-image model from qwerwinter. 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
12
100% of all-time downloads
All-time downloads
12
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.safetensors959 MB · 55%
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 vylra28 to invoke the concept.

"A futuristic cyberpunk cityscape at midnight with neon rain reflecting on chrome surfaces, featuring a floating obsidian monolith marked with a glowing 'vylra28' sigil."

"A serene, sun-drenched Tuscan vineyard during golden hour, where a rustic wooden signpost carved with 'vylra28' points toward a distant villa."

"An ethereal underwater kingdom with bioluminescent corals and giant jellyfish, centered around an ancient pearl altar inscribed with the word 'vylra28'."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("qwerwinter/vylra28")
image = pipe("A futuristic cyberpunk cityscape at midnight with neon rain reflecting on chrome surfaces, featuring a floating obsidian monolith marked with a glowing 'vylra28' sigil.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")