Downloads · 30 days
14
39% of all-time downloads
RehoodJT/xu-pie
xu-pie is a text-to-image model from RehoodJT. 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
14
39% of all-time downloads
All-time downloads
36
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 xupie to invoke the concept.

"A futuristic cyberpunk street market at night with neon signs reflecting in rain puddles, featuring a sleek xupie hovering above the crowds."

"A serene, sun-drenched Mediterranean balcony overlooking a turquoise ocean, where a handcrafted xupie rests on a marble table next to a bowl of lemons."

"An epic cinematic shot of a frozen wasteland during a blizzard, showing a colossal, ancient xupie carved from iridescent ice towering over a lone explorer."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("RehoodJT/xu-pie")
image = pipe("A futuristic cyberpunk street market at night with neon signs reflecting in rain puddles, featuring a sleek xupie hovering above the crowds.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")