README.md

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "cayl33 woman"
widget:
- text: "A cinematic shot of a cayl33 woman wearing futuristic neon armor, standing amidst the rainy, glowing skyscrapers of a cyberpunk metropolis."
  output:
    url: sample_0.png
- text: "A soft, ethereal portrait of a cayl33 woman in a flowing white linen dress, wandering through a sun-drenched meadow of wild lavender."
  output:
    url: sample_1.png
- text: "A high-detail close-up of a cayl33 woman as a Victorian explorer, surrounded by ancient leather maps and brass compasses in a dimly lit library."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — aimalias/cayl33

<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 `cayl33 woman` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A cinematic shot of a cayl33 woman wearing futuristic neon armor, standing amidst the rainy, glowing skyscrapers of a cyberpunk metropolis."*

![sample](./sample_1.png)

> *"A soft, ethereal portrait of a cayl33 woman in a flowing white linen dress, wandering through a sun-drenched meadow of wild lavender."*

![sample](./sample_2.png)

> *"A high-detail close-up of a cayl33 woman as a Victorian explorer, surrounded by ancient leather maps and brass compasses in a dimly lit library."*

## 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("aimalias/cayl33")
image = pipe("A cinematic shot of a cayl33 woman wearing futuristic neon armor, standing amidst the rainy, glowing skyscrapers of a cyberpunk metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```