Downloads · 30 days
18
33% of all-time downloads
volvoman2/krea-2-nyah
krea-2-nyah is a text-to-image model from volvoman2. 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
18
33% of all-time downloads
All-time downloads
54
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 nyah to invoke the concept.

"A futuristic neon cyberpunk city street where a robotic cat with glowing eyes lets out a digital 'nyah' amidst holographic advertisements."

"A serene, sun-drenched Impressionist oil painting of a fluffy white kitten sleeping in a lavender field, with a small 'nyah' speech bubble floating above."

"A cinematic shot of a majestic space explorer in a sleek silver suit discovering a floating crystalline alien creature that makes a soft 'nyah' sound in the vacuum of a purple nebula."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("volvoman2/krea-2-nyah")
image = pipe("A futuristic neon cyberpunk city street where a robotic cat with glowing eyes lets out a digital 'nyah' amidst holographic advertisements.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")