Krea 2 LoRA โ€” Gamberth/lora-miriav2

Prompt
A cinematic portrait of miria as a cyberpunk hacker in a neon-drenched Tokyo alley, wearing reflective chrome goggles and a holographic jacket.
Prompt
A whimsical oil painting of miria as a forest spirit, draped in glowing vines and wildflowers within a misty, ancient woodland.
Prompt
A high-fashion editorial shot of miria posing in a minimalist white marble gallery, wearing an avant-garde sculptural gown of gold liquid metal.

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 miria to invoke the concept.

Samples

sample

"A cinematic portrait of miria as a cyberpunk hacker in a neon-drenched Tokyo alley, wearing reflective chrome goggles and a holographic jacket."

sample

"A whimsical oil painting of miria as a forest spirit, draped in glowing vines and wildflowers within a misty, ancient woodland."

sample

"A high-fashion editorial shot of miria posing in a minimalist white marble gallery, wearing an avant-garde sculptural gown of gold liquid metal."

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("Gamberth/lora-miriav2")
image = pipe("A cinematic portrait of miria as a cyberpunk hacker in a neon-drenched Tokyo alley, wearing reflective chrome goggles and a holographic jacket.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
10
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Gamberth/lora-miriav2

Base model

krea/Krea-2-Raw
Adapter
(960)
this model