Blame for README.md

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "FIDRI"
widget:
- text: "A futuristic cyberpunk city street drenched in neon rain, where a floating FIDRI robot serves glowing cocktails to holographic patrons."
  output:
    url: sample_0.png
- text: "A serene, sun-drenched Tuscan vineyard during golden hour, featuring a rustic FIDRI wooden sculpture overgrown with wild ivy."
  output:
    url: sample_1.png
- text: "An epic cinematic shot of a cosmic nebula where a colossal, crystalline FIDRI entity drifts through swirling stardust and violet galaxies."
  output:
    url: sample_2.png
---

# Krea 2 LoRA — funseshon/fidri

<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 `FIDRI` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A futuristic cyberpunk city street drenched in neon rain, where a floating FIDRI robot serves glowing cocktails to holographic patrons."*

![sample](./sample_1.png)

> *"A serene, sun-drenched Tuscan vineyard during golden hour, featuring a rustic FIDRI wooden sculpture overgrown with wild ivy."*

![sample](./sample_2.png)

> *"An epic cinematic shot of a cosmic nebula where a colossal, crystalline FIDRI entity drifts through swirling stardust and violet galaxies."*

## 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/fidri")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, where a floating FIDRI robot serves glowing cocktails to holographic patrons.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```