---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
inference:
  parameters:
    width: 1024
    height: 1024
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: in decorativerelief art style
widget:
- text: parrot in decorativerelief art style
  output:
    url: images/example_h7l11bhwq.png
- text: unicorn in decorativerelief art style
  output:
    url: images/example_ejsz43qve.png
- text: a deer-like unicorn with dragon scales in decorativerelief art style
  output:
    url: images/example_pdutyw8w6.png

---
# Decorative Relief

<Gallery />

## Model description 

A decorative relief lora inspired by Indonesian art.

## Trigger words

You should use `decorativerelief art style` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/geocine/decorative-relief/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('geocine/decorative-relief', weight_name='lora_64_1700steps.safetensors')
image = pipeline('decorativerelief art style').images[0]
```