Krea 2 LoRA — the-big-juice/val-better

Prompt

A hyper-realistic portrait of Val as a cyberpunk neon-noir detective standing in a rain-slicked alleyway of a futuristic Tokyo.

Prompt

An oil painting of Val dressed as a regal Victorian explorer discovering a glowing ancient temple deep within a lush jungle.

Prompt

A cinematic shot of Val as a cosmic entity floating in a swirling nebula of iridescent stardust and crystalline planets.

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 Val to invoke the concept.

Samples

"A hyper-realistic portrait of Val as a cyberpunk neon-noir detective standing in a rain-slicked alleyway of a futuristic Tokyo."

"An oil painting of Val dressed as a regal Victorian explorer discovering a glowing ancient temple deep within a lush jungle."

"A cinematic shot of Val as a cosmic entity floating in a swirling nebula of iridescent stardust and crystalline planets."

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("the-big-juice/val-better")
image = pipe("A hyper-realistic portrait of Val as a cyberpunk neon-noir detective standing in a rain-slicked alleyway of a futuristic Tokyo.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")