Downloads · 30 days
15
20% of all-time downloads
chrisserycher/n0rafac3
n0rafac3 is a text-to-image model from chrisserycher. 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
15
20% of all-time downloads
All-time downloads
76
Public
Repo size
971 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 n0rafac3 to invoke the concept.

"A steampunk explorer wearing brass goggles and a leather coat, standing in a floating clockwork city, n0rafac3, cinematic lighting, 8k resolution."

"A neon-drenched cyberpunk street in Tokyo during a rainstorm, reflecting holographic billboards on wet pavement, n0rafac3, futuristic synthwave aesthetic."

"An ethereal forest of glowing iridescent mushrooms and floating spores under a cosmic nebula sky, n0rafac3, digital art, dreamlike atmosphere."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("chrisserycher/n0rafac3")
image = pipe("A steampunk explorer wearing brass goggles and a leather coat, standing in a floating clockwork city, n0rafac3, cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")