README.md

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "p1nd3r woman"
widget:
- text: "A p1nd3r woman standing amidst a neon-lit cyberpunk cityscape during a rainstorm, her metallic clothing reflecting vibrant violet and teal holographic advertisements."
  output:
    url: sample_0.png
- text: "A p1nd3r woman dressed in flowing linen robes, meditating in a sun-drenched ancient Greek temple surrounded by blooming white oleander and marble columns."
  output:
    url: sample_1.png
- text: "A p1nd3r woman navigating a surrealist underwater dreamscape, floating weightlessly alongside giant iridescent jellyfish and glowing coral reefs."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — aimalias/p1nd3r

<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 `p1nd3r woman` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A p1nd3r woman standing amidst a neon-lit cyberpunk cityscape during a rainstorm, her metallic clothing reflecting vibrant violet and teal holographic advertisements."*

![sample](./sample_1.png)

> *"A p1nd3r woman dressed in flowing linen robes, meditating in a sun-drenched ancient Greek temple surrounded by blooming white oleander and marble columns."*

![sample](./sample_2.png)

> *"A p1nd3r woman navigating a surrealist underwater dreamscape, floating weightlessly alongside giant iridescent jellyfish and glowing coral reefs."*

## 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/p1nd3r")
image = pipe("A p1nd3r woman standing amidst a neon-lit cyberpunk cityscape during a rainstorm, her metallic clothing reflecting vibrant violet and teal holographic advertisements.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```