jei7/gta6-screenshot

Krea 2 LoRA — jei7/gta6-screenshot

<Gallery />

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 gta6screenshot to invoke the concept.

Samples

[image]

"A neon-drenched street in Vice City at midnight, featuring a customized chrome supercar idling at a red light with reflections of palm trees on its hood, gta6screenshot"

[image]

"A sun-baked Florida Everglades scene with an airboat speeding through golden sawgrass, kicking up a spray of muddy water under a hazy orange sunset, gta6screenshot"

[image]

"A high-fashion woman in oversized sunglasses and a vibrant summer dress walking a fluffy pomeranian down a luxury beachfront promenade, gta6screenshot"

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("jei7/gta6-screenshot")
image = pipe("A neon-drenched street in Vice City at midnight, featuring a customized chrome supercar idling at a red light with reflections of palm trees on its hood, gta6screenshot", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")