---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "cindycfr11"
widget:
- text: "A golden labrador running across a sunny farm, a pickup truck on a dusty road far behind, cindycfr11"
  output:
    url: sample_0.png
- text: "A fishing boat moored in a narrow canal between tall old buildings, cindycfr11"
  output:
    url: sample_1.png
- text: "A deer grazing in a dense forest with the bright sun overhead, cindycfr11"
  output:
    url: sample_2.png
---

# Krea 2 LoRA — dekes1/cindycfr13

<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 `cindycfr11` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A golden labrador running across a sunny farm, a pickup truck on a dusty road far behind, cindycfr11"*

![sample](./sample_1.png)

> *"A fishing boat moored in a narrow canal between tall old buildings, cindycfr11"*

![sample](./sample_2.png)

> *"A deer grazing in a dense forest with the bright sun overhead, cindycfr11"*

## 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("dekes1/cindycfr13")
image = pipe("A golden labrador running across a sunny farm, a pickup truck on a dusty road far behind, cindycfr11", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```