softloud

Krea 2 LoRA — lloydchristmas1231/softloud

<Gallery />

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).

Trigger

Use the token softloud to invoke the concept.

Samples

"A futuristic cyberpunk city street drenched in neon rain, where a solitary cat sits on a hovering chrome platform under a softloud glow."

"An ancient, overgrown stone temple in a tropical jungle, with golden sunlight filtering through vines to create a softloud atmosphere."

"A minimalist white art gallery featuring a single floating crystalline sculpture that emits a softloud pulse of iridescent light."

Use it with diffusers

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/softloud")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, where a solitary cat sits on a hovering chrome platform under a softloud glow.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")