Downloads · 30 days
5
33% of all-time downloads
mju75/klara-lora-weights
klara-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
5
33% of all-time downloads
All-time downloads
15
Public
Repo size
779 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 kl4ra to invoke the concept.

"A futuristic cyberpunk street in Tokyo drenched in neon rain, featuring kl4ra as a holographic entity floating above a crowded intersection."

"A serene, sun-drenched Mediterranean garden with white marble statues, where kl4ra is lounging in a linen dress reading an ancient scroll."

"A gritty, cinematic wide shot of a desolate Martian colony, showing kl4ra wearing a weathered spacesuit while staring at a distant dust storm."
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/klara-lora-weights")
image = pipe("A futuristic cyberpunk street in Tokyo drenched in neon rain, featuring kl4ra as a holographic entity floating above a crowded intersection.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")