README.md

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "neoncrypt style"
widget:
- text: "<neoncrypt style>, a lone astronaut exploring an abandoned lunar research station"
  output:
    url: sample_0.png
- text: "<neoncrypt style>, an ancient wooden sailing ship trapped inside a frozen cavern"
  output:
    url: sample_1.png
- text: "<neoncrypt style>, a deserted roadside diner surrounded by wheat fields beneath an approaching storm"
  output:
    url: sample_2.png
---

# Krea 2 LoRA — IronBloodhound/neoncryptstyle

<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 `neoncrypt style` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"<neoncrypt style>, a lone astronaut exploring an abandoned lunar research station"*

![sample](./sample_1.png)

> *"<neoncrypt style>, an ancient wooden sailing ship trapped inside a frozen cavern"*

![sample](./sample_2.png)

> *"<neoncrypt style>, a deserted roadside diner surrounded by wheat fields beneath an approaching storm"*

## Use it with diffusers

```py
import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("IronBloodhound/neoncryptstyle")
image = pipe("<neoncrypt style>, a lone astronaut exploring an abandoned lunar research station", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```