---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
- text-to-image
- diffusers-training
- diffusers
- lora
- krea2
- krea2-diffusers
- template:sd-lora
license: apache-2.0
instance_prompt: FAJU
widget:
- text: A cinematic shot of a futuristic FAJU robot tending to a glowing neon garden
    in a floating cyberpunk city.
  output:
    url: sample_0.png
- text: A vintage oil painting of a FAJU explorer discovering an ancient golden temple
    hidden deep within a misty jungle.
  output:
    url: sample_1.png
- text: A macro photograph of a tiny FAJU creature made of liquid crystal resting
    on a dew-covered autumn leaf.
  output:
    url: sample_2.png
library_name: diffusers
---

# Krea 2 LoRA — funseshon/faju

<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 `FAJU` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A cinematic shot of a futuristic FAJU robot tending to a glowing neon garden in a floating cyberpunk city."*

![sample](./sample_1.png)

> *"A vintage oil painting of a FAJU explorer discovering an ancient golden temple hidden deep within a misty jungle."*

![sample](./sample_2.png)

> *"A macro photograph of a tiny FAJU creature made of liquid crystal resting on a dew-covered autumn leaf."*

## 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("funseshon/faju")
image = pipe("A cinematic shot of a futuristic FAJU robot tending to a glowing neon garden in a floating cyberpunk city.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```