Krea 2 LoRA — misapapa71/model-mami-krea2

Prompt

A cinematic street style shot of model-Mami-krea2 walking through a neon-lit Tokyo alleyway during a rainstorm, wearing a holographic futuristic jacket.

Prompt

A serene oil painting of model-Mami-krea2 lounging in a sun-drenched Mediterranean garden surrounded by blooming white oleanders and ancient marble pillars.

Prompt

An epic high-fantasy portrait of model-Mami-krea2 as a celestial warrior, clad in iridescent gold armor and floating amidst a swirling cosmic nebula.

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 model-Mami-krea2 to invoke the concept.

Samples

"A cinematic street style shot of model-Mami-krea2 walking through a neon-lit Tokyo alleyway during a rainstorm, wearing a holographic futuristic jacket."

"A serene oil painting of model-Mami-krea2 lounging in a sun-drenched Mediterranean garden surrounded by blooming white oleanders and ancient marble pillars."

"An epic high-fantasy portrait of model-Mami-krea2 as a celestial warrior, clad in iridescent gold armor and floating amidst a swirling cosmic nebula."

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("misapapa71/model-mami-krea2")
image = pipe("A cinematic street style shot of model-Mami-krea2 walking through a neon-lit Tokyo alleyway during a rainstorm, wearing a holographic futuristic jacket.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")