Krea 2 LoRA — EdittLab/valentina

Prompt

A cinematic shot of Valentina as a futuristic neon-clad cyber-detective walking through a rainy Tokyo street at midnight.

Prompt

A whimsical oil painting of Valentina wearing a Victorian gown, reading a glowing ancient spellbook in a sun-drenched library.

Prompt

An extreme close-up of Valentina as a courageous astronaut, her face reflected in a golden visor with a swirling nebula in the background.

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 Valentina to invoke the concept.

Samples

"A cinematic shot of Valentina as a futuristic neon-clad cyber-detective walking through a rainy Tokyo street at midnight."

"A whimsical oil painting of Valentina wearing a Victorian gown, reading a glowing ancient spellbook in a sun-drenched library."

"An extreme close-up of Valentina as a courageous astronaut, her face reflected in a golden visor with a swirling nebula in the background."

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("EdittLab/valentina")
image = pipe("A cinematic shot of Valentina as a futuristic neon-clad cyber-detective walking through a rainy Tokyo street at midnight.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")