README.md

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "Thijs"
widget:
- text: "A hyper-realistic cinematic shot of Thijs as a futuristic cyberpunk detective standing under neon rainfall in a crowded Tokyo alleyway."
  output:
    url: sample_0.png
- text: "An oil painting of Thijs dressed as a 17th-century royal explorer, charting an ancient map inside a candlelit mahogany library."
  output:
    url: sample_1.png
- text: "A vibrant 3D render of Thijs as a tiny astronaut floating inside a giant iridescent soap bubble drifting through a candy-colored nebula."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — Wonky468/thijs

<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 token `Thijs` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A hyper-realistic cinematic shot of Thijs as a futuristic cyberpunk detective standing under neon rainfall in a crowded Tokyo alleyway."*

![sample](./sample_1.png)

> *"An oil painting of Thijs dressed as a 17th-century royal explorer, charting an ancient map inside a candlelit mahogany library."*

![sample](./sample_2.png)

> *"A vibrant 3D render of Thijs as a tiny astronaut floating inside a giant iridescent soap bubble drifting through a candy-colored nebula."*

## 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("Wonky468/thijs")
image = pipe("A hyper-realistic cinematic shot of Thijs as a futuristic cyberpunk detective standing under neon rainfall in a crowded Tokyo alleyway.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```