Downloads · 30 days
22
18% of all-time downloads
Wonky468/kirsten
kirsten is a text-to-image model from Wonky468. 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
22
18% of all-time downloads
All-time downloads
124
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 Kirsten to invoke the concept.

"A cinematic portrait of Kirsten as a futuristic neon-cyberpunk hacker, surrounded by floating holographic screens in a rainy Tokyo alleyway."

"Kirsten dressed as a Victorian botanist, meticulously sketching rare glowing flora inside a sun-drenched glass conservatory filled with exotic ferns."

"An epic wide shot of Kirsten as a nomadic warrior standing atop a windswept sand dune under a massive shimmering binary star system."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Wonky468/kirsten")
image = pipe("A cinematic portrait of Kirsten as a futuristic neon-cyberpunk hacker, surrounded by floating holographic screens in a rainy Tokyo alleyway.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")