---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "cindycfr2"
widget:
- text: "A high-fashion editorial shot of a woman cindycfr2 wearing a neon holographic gown, standing amidst a futuristic cyberpunk Tokyo street with rain-slicked pavement and glowing signs."
  output:
    url: sample_0.png
- text: "A cinematic close-up of cindycfr2 as a medieval warrior in ornate silver armor, resting in a sun-dappled ancient forest with floating magical spores."
  output:
    url: sample_1.png
- text: "A whimsical 3D render of cindycfr2 as a miniature explorer navigating a giant kitchen landscape, climbing a massive mountain of colorful macarons."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — dekes1/cindycfr2

<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 `cindycfr2` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A high-fashion editorial shot of a woman cindycfr2 wearing a neon holographic gown, standing amidst a futuristic cyberpunk Tokyo street with rain-slicked pavement and glowing signs."*

![sample](./sample_1.png)

> *"A cinematic close-up of cindycfr2 as a medieval warrior in ornate silver armor, resting in a sun-dappled ancient forest with floating magical spores."*

![sample](./sample_2.png)

> *"A whimsical 3D render of cindycfr2 as a miniature explorer navigating a giant kitchen landscape, climbing a massive mountain of colorful macarons."*

## 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/cindycfr2")
image = pipe("A high-fashion editorial shot of a woman cindycfr2 wearing a neon holographic gown, standing amidst a futuristic cyberpunk Tokyo street with rain-slicked pavement and glowing signs.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```