Downloads · 30 days
41
61% of all-time downloads
lloydchristmas1231/caslus
caslus is a text-to-image model from lloydchristmas1231. 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
41
61% of all-time downloads
All-time downloads
67
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 caslus to invoke the concept.

"A cinematic shot of a futuristic caslus robot exploring a bioluminescent neon rainforest with floating jellyfish. The atmosphere is misty and filled with iridescent flora."

"A rustic, oil-painting style scene of a vintage caslus clock sitting on a dust-covered wooden table in a sun-drenched attic. Golden dust motes dance in the light rays."

"An epic wide shot of a colossal caslus monument carved into a snowy mountain peak under a swirling cosmic nebula sky. Tiny explorers stand at the base in awe."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("lloydchristmas1231/caslus")
image = pipe("A cinematic shot of a futuristic caslus robot exploring a bioluminescent neon rainforest with floating jellyfish. The atmosphere is misty and filled with iridescent flora.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")