README.md

---
base_model:
- black-forest-labs/FLUX.1-dev
library_name: diffusers
tags:
- template:diffusion-lora
- flux.1-dev
- diffusers
- Text-to-Image
- flux
- lora
- soulday
- skull
- day of the dead

pipeline_tag: text-to-image
widget:
- output:
    url: images/0.png
  text: >-
    soulday style, woman with red hair, playing chess at the park, parade in the
    background
- output:
    url: images/1.jpeg
  text: >-
    soulday style, woman at day of the dead festival with parade in the background
- output:
    url: images/2.jpeg
  text: >-
    soulday style, beautiful woman with decorative clothing at a fashion show on a catwalk
- output:
    url: images/3.jpeg
  text: >-
    soulday style, beautiful woman with decorative clothing sitting in a coffee shop
- output:
    url: images/4.jpeg
  text: >-
    soulday style, skull symbol on golf ball
trigger: soulday style
instance_prompt: soulday style
license: other
license_name: flux-1-dev-non-commercial-license
---
## About
The "soulday style" is a LoRA created from the SoulDay inspired artwork. 
The style manifests itself in the output image via the trigger word in multiple objects:
1. **Faces** The human characters themselves have a particular style. 
2. **Accessories** It can be seen in human accessories such as glasses, earrings, bracelets, pendants, etc.
3. **Clothing** The style is apparent in the clothing.
   
</br>
One can accentuate the style on a particular object by adding "skull" e.g. "skull shirt" or "skull coffee mug"

## SoulDay
SoulDay ($SDY) is a collectible ethereum token project from [GaleriaRodrigo.com](https://galeriarodrigo.com)
</br>
[Minted tokens](https://magiceden.us/collections/ethereum/0x5c6954f5df48035a6e339ef26f4167cb7e56d021)
</br>
[Minting tokens](https://soulday.io)


## Trigger words

You should use `soulday style` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/galeriarodrigo/FLUX.1-dev-lora-soulday/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('galeriarodrigo/FLUX.1-dev-lora-soulday', weight_name='souldaystyle.safetensors')
image = pipeline('soulday style, woman with red hair, playing chess at the park, parade in the background').images[0]
image.save("my_image.png")
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)