---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "p0ar4"
widget:
- text: "A futuristic cyberpunk city street drenched in neon rain, featuring a holographic p0ar4 floating above a crowded marketplace."
  output:
    url: sample_0.png
- text: "A serene, sun-drenched Tuscan vineyard where a rustic wooden table holds a crystal vase and a single p0ar4."
  output:
    url: sample_1.png
- text: "An epic underwater kingdom with iridescent coral towers and a glowing p0ar4 drifting through a school of shimmering fish."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — saik0s/p0ar4

<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 `p0ar4` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A futuristic cyberpunk city street drenched in neon rain, featuring a holographic p0ar4 floating above a crowded marketplace."*

![sample](./sample_1.png)

> *"A serene, sun-drenched Tuscan vineyard where a rustic wooden table holds a crystal vase and a single p0ar4."*

![sample](./sample_2.png)

> *"An epic underwater kingdom with iridescent coral towers and a glowing p0ar4 drifting through a school of shimmering fish."*

## 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("saik0s/p0ar4")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, featuring a holographic p0ar4 floating above a crowded marketplace.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```