README.md

---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- drag queen
- makeup
- style
- drag

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: drag style
widget:
- text: 'A drag style barbie is eating spaghetti   '
  
  output:
    url: >-
      44059957.jpeg
- text: 'Marge Simpson drag style   '
  
  output:
    url: >-
      44060029.jpeg
- text: 'Marge Simpson drag style '
  
  output:
    url: >-
      44060031.jpeg
- text: 'A psychedelic painting of a drag style   '
  
  output:
    url: >-
      44060037.jpeg
- text: 'The Mona Lisa, drag style '
  
  output:
    url: >-
      44060038.jpeg
- text: 'woman playing the guitar, on stage, singing a song, laser lights, punk rocker drag style '
  
  output:
    url: >-
      44060044.jpeg
- text: 'Wonderwoman, is a dj at a club, drag style   '
  
  output:
    url: >-
      44060129.jpeg
- text: 'Snoop Dogg drag style   '
  
  output:
    url: >-
      44060130.jpeg
- text: 'The Starry Night drag style   '
  
  output:
    url: >-
      44060139.jpeg
- text: 'The girl with a pearl earring drag style   '
  
  output:
    url: >-
      44060125.jpeg
- text: 'American gothic by Grant Wood drag style '
  
  output:
    url: >-
      44060137.jpeg
- text: 'Elsa from frozen drag style '
  
  output:
    url: >-
      44060152.jpeg
- text: 'Gal gadot as Wonderwoman drag style '
  
  output:
    url: >-
      44060128.jpeg
- text: 'a woman holding a coffee cup, in a beanie, sitting at a cafe drag style '
  
  output:
    url: >-
      44060126.jpeg
- text: 'scientist woman holding a sign that says ''I LOVE PROMPTS!'' drag style '
  
  output:
    url: >-
      44060127.jpeg
- text: 'woman with red hair, playing chess at the park, bomb going off in the background, drag style  '
  
  output:
    url: >-
      44060136.jpeg
- text: 'A cute dog drag style '
  
  output:
    url: >-
      44060687.jpeg
- text: 'a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini drag style '
  
  output:
    url: >-
      44060686.jpeg

---

# Drag style [FLUX] 

<Gallery />



([CivitAI](https://civitai.com/models/))

## Model description

<p>Drag style Flux LoRA model. LoRA weight in the range of 0.8 to 1.0 seems to work fine.</p><p>Use '<em>drag style</em>' in your prompts as the trigger</p><p>Trained on <a target="_blank" rel="ugc" href="http://astria.ai">astria.ai</a></p>

## Trigger words
You should use `drag style` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Norod78/drag-style-flux/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

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Norod78/drag-style-flux', weight_name='Flux_Drag-Style_LoRA_1865815.safetensors')
image = pipeline('a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini drag style ').images[0]
```

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)