---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "T355A woman"
widget:
- text: "A cinematic wide shot of T355A woman exploring a bioluminescent neon jungle with glowing floating flora and iridescent wildlife."
  output:
    url: sample_0.png
- text: "A high-fashion editorial portrait of T355A woman wearing a structured metallic gown, standing in a minimalist white marble gallery."
  output:
    url: sample_1.png
- text: "A gritty, detailed close-up of T355A woman as a futuristic scavenger in a rainy cyberpunk alleyway, illuminated by flickering holographic signs."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — aimalias/t355a

<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 `T355A woman` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A cinematic wide shot of T355A woman exploring a bioluminescent neon jungle with glowing floating flora and iridescent wildlife."*

![sample](./sample_1.png)

> *"A high-fashion editorial portrait of T355A woman wearing a structured metallic gown, standing in a minimalist white marble gallery."*

![sample](./sample_2.png)

> *"A gritty, detailed close-up of T355A woman as a futuristic scavenger in a rainy cyberpunk alleyway, illuminated by flickering holographic signs."*

## 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("aimalias/t355a")
image = pipe("A cinematic wide shot of T355A woman exploring a bioluminescent neon jungle with glowing floating flora and iridescent wildlife.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```