Downloads · 30 days
4
18% of all-time downloads
funseshon/mike-ots
mike-ots is a text-to-image model from funseshon. 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
4
18% of all-time downloads
All-time downloads
22
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 phrase MIKE_OTS to invoke the concept.

"A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in hyper-realistic detail. MIKE_OTS"

"A sleek, futuristic chrome motorcycle speeding down a neon-drenched Tokyo highway at midnight with vibrant light trails. MIKE_OTS"

"An elderly clockmaker meticulously repairing a golden pocket watch inside a dusty, sun-drenched Victorian workshop. MIKE_OTS"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("funseshon/mike-ots")
image = pipe("A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in hyper-realistic detail. MIKE_OTS", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")