Downloads · 30 days
14
34% of all-time downloads
mju75/tereza-lora-weights
tereza-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
14
34% of all-time downloads
All-time downloads
41
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 t3reza to invoke the concept.

"A futuristic cyberpunk cityscape at midnight with neon rain, featuring t3reza as a holographic entity floating above a crowded street."

"A serene, sun-drenched Tuscan vineyard during golden hour, where t3reza is depicted as a classical marble sculpture overgrown with ivy."

"An epic underwater kingdom with bioluminescent coral reefs, showcasing t3reza as a majestic sea creature gliding through deep indigo waters."
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/tereza-lora-weights")
image = pipe("A futuristic cyberpunk cityscape at midnight with neon rain, featuring t3reza as a holographic entity floating above a crowded street.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")