Downloads · 30 days
9
35% of all-time downloads
tmtmtm45/nike-jockstrap
nike-jockstrap is a text-to-image model from tmtmtm45. 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
9
35% of all-time downloads
All-time downloads
26
Public
Repo size
1.4 GB
Likes
0
Public
Click a slice to open those files.
.safetensors768 MB · 57%
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 nkjock to invoke the concept.

"A futuristic neon-lit cyberpunk cityscape where a holographic nkjock floats above a rain-slicked street, reflecting vibrant pink and blue lights."

"An ancient, overgrown stone temple in a misty jungle, featuring a weathered stone nkjock carved into a monolithic altar surrounded by tropical ferns."

"A whimsical macro shot of a tiny nkjock made of iridescent bubbles drifting through a sun-drenched wildflower meadow with soft bokeh blur."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("tmtmtm45/nike-jockstrap")
image = pipe("A futuristic neon-lit cyberpunk cityscape where a holographic nkjock floats above a rain-slicked street, reflecting vibrant pink and blue lights.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")