Downloads · 30 days
13
24% of all-time downloads
Kortizol/kri-vlik
kri-vlik is a text-to-image model from Kortizol. 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
13
24% of all-time downloads
All-time downloads
55
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 kri@vlik to invoke the concept.

"A futuristic cyberpunk street market in Neo-Tokyo, where a glowing kri@vlik floats above a holographic food stall amidst neon rain."

"An ornate Victorian drawing room filled with velvet curtains and antique clocks, featuring a mysterious kri@vlik resting on a mahogany table."

"A breathtaking underwater coral kingdom with iridescent fish swimming around a shimmering, ancient kri@vlik embedded in a pearl shell."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Kortizol/kri-vlik")
image = pipe("A futuristic cyberpunk street market in Neo-Tokyo, where a glowing kri@vlik floats above a holographic food stall amidst neon rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")