---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "Emily"
widget:
- text: "A cinematic close-up of Emily as a cyberpunk hacker, illuminated by neon blue holographic screens in a rainy futuristic Tokyo alley."
  output:
    url: sample_0.png
- text: "A dreamy oil painting of Emily wearing a floral Victorian gown, wandering through a sun-drenched meadow of lavender and gold."
  output:
    url: sample_1.png
- text: "An epic wide shot of Emily as an astronaut standing on the crystalline surface of a distant purple planet, gazing at a swirling galaxy."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — Xopen/emily2

<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 `Emily` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A cinematic close-up of Emily as a cyberpunk hacker, illuminated by neon blue holographic screens in a rainy futuristic Tokyo alley."*

![sample](./sample_1.png)

> *"A dreamy oil painting of Emily wearing a floral Victorian gown, wandering through a sun-drenched meadow of lavender and gold."*

![sample](./sample_2.png)

> *"An epic wide shot of Emily as an astronaut standing on the crystalline surface of a distant purple planet, gazing at a swirling galaxy."*

## 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("Xopen/emily2")
image = pipe("A cinematic close-up of Emily as a cyberpunk hacker, illuminated by neon blue holographic screens in a rainy futuristic Tokyo alley.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```