Krea 2 LoRA — Nanami231/ruby-ngo-v2

Prompt

A cinematic close-up of a futuristic cyberpunk cyborg with glowing neon circuitry and iridescent plating, tagged Ruby@Ngo, standing under a rainy Tokyo street light.

Prompt

A whimsical oil painting of a fluffy white cat wearing a tiny royal crown and velvet cape, Ruby@Ngo, lounging on a gold throne in a sunlit baroque palace.

Prompt

An epic wide shot of an ancient stone temple overgrown with bioluminescent jungle vines and floating ruins, featuring the signature Ruby@Ngo, under a starry nebula sky.

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 Ruby@Ngo to invoke the concept.

Samples

"A cinematic close-up of a futuristic cyberpunk cyborg with glowing neon circuitry and iridescent plating, tagged Ruby@Ngo, standing under a rainy Tokyo street light."

"A whimsical oil painting of a fluffy white cat wearing a tiny royal crown and velvet cape, Ruby@Ngo, lounging on a gold throne in a sunlit baroque palace."

"An epic wide shot of an ancient stone temple overgrown with bioluminescent jungle vines and floating ruins, featuring the signature Ruby@Ngo, under a starry nebula sky."

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("Nanami231/ruby-ngo-v2")
image = pipe("A cinematic close-up of a futuristic cyberpunk cyborg with glowing neon circuitry and iridescent plating, tagged Ruby@Ngo, standing under a rainy Tokyo street light.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")