Downloads · 30 days
23
70% of all-time downloads
mju75/sandra-lora-weights
sandra-lora-weights is a text-to-image model from mju75. 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
23
70% of all-time downloads
All-time downloads
33
Public
Repo size
970 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 s2ndra to invoke the concept.

"A hyper-realistic portrait of a majestic snow leopard wearing a futuristic neon headset, lounging in a cyberpunk Tokyo alleyway, s2ndra."

"An oil painting of a Victorian tea party hosted by an elegant octopus in an underwater crystal ballroom, s2ndra."

"A wide cinematic shot of a floating steampunk city drifting through a sea of gold clouds at sunset, s2ndra."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("mju75/sandra-lora-weights")
image = pipe("A hyper-realistic portrait of a majestic snow leopard wearing a futuristic neon headset, lounging in a cyberpunk Tokyo alleyway, s2ndra.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")