Krea 2 LoRA — IronBloodhound/neonveil-style

Prompt

A majestic snow leopard perched on a jagged Himalayan peak under a swirling violet nebula sky, NEONVEIL1306

Prompt

A sleek, chrome cyberpunk motorcycle speeding down a rain-slicked Tokyo highway with trailing light streaks, NEONVEIL1306

Prompt

An elderly calligrapher painting glowing gold ink onto a floating silk scroll in a Zen garden, NEONVEIL1306

Prompt

A lavish Art Deco ballroom with towering emerald pillars and a shimmering mirrored floor reflecting a crystal chandelier, NEONVEIL1306

Prompt

A futuristic deep-sea research station nestled inside a giant bioluminescent coral reef, NEONVEIL1306

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 phrase NEONVEIL1306 to invoke the concept.

Samples

"A majestic snow leopard perched on a jagged Himalayan peak under a swirling violet nebula sky, NEONVEIL1306"

"A sleek, chrome cyberpunk motorcycle speeding down a rain-slicked Tokyo highway with trailing light streaks, NEONVEIL1306"

"An elderly calligrapher painting glowing gold ink onto a floating silk scroll in a Zen garden, NEONVEIL1306"

"A lavish Art Deco ballroom with towering emerald pillars and a shimmering mirrored floor reflecting a crystal chandelier, NEONVEIL1306"

"A futuristic deep-sea research station nestled inside a giant bioluminescent coral reef, NEONVEIL1306"

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("IronBloodhound/neonveil-style")
image = pipe("A majestic snow leopard perched on a jagged Himalayan peak under a swirling violet nebula sky, NEONVEIL1306", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")