Downloads · 30 days
25
37% of all-time downloads
mju75/marketa-lora-krea-2
marketa-lora-krea-2 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
25
37% of all-time downloads
All-time downloads
68
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 mrk3ta to invoke the concept.

"A futuristic cyberpunk city street drenched in neon rain, featuring a sleek mrk3ta hovering amidst holographic advertisements and flying cars."

"A serene, sun-dappled ancient forest with giant ferns and glowing mushrooms, where a weathered mrk3ta is overgrown with soft green moss."

"A high-fashion editorial shot in a minimalist white marble gallery, showcasing a polished gold mrk3ta as a centerpiece under a sharp spotlight."
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/marketa-lora-krea-2")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, featuring a sleek mrk3ta hovering amidst holographic advertisements and flying cars.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")