Downloads · 30 days
16
38% of all-time downloads
sdkcompetent/clo3lt
clo3lt is a text-to-image model from sdkcompetent. 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
16
38% of all-time downloads
All-time downloads
42
Public
Repo size
970 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 clo3lt to invoke the concept.

"A futuristic cyberpunk cityscape at night with neon rain, featuring a clo3lt floating in a glowing holographic display."

"A serene ancient Japanese garden with cherry blossoms falling, where a clo3lt rests on a mossy stone lantern."

"An epic cinematic shot of a deep space nebula, showing a colossal clo3lt drifting past a shimmering supernova."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("sdkcompetent/clo3lt")
image = pipe("A futuristic cyberpunk cityscape at night with neon rain, featuring a clo3lt floating in a glowing holographic display.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")