---
license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- photorealistic
- woman
- celebrity
- realistic
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
widget:
- text: >-
    blonde young woman in a dark robot suit in a cyberpunk setting at night,
    front view
  output:
    url: 35087545.jpeg
- text: portrait red hair young woman in a dark forest at night, front view
  output:
    url: 35087816.jpeg
- text: ' green hair young woman in a utopian candyland, front view'
  output:
    url: 35088410.jpeg
- text: portrait blue hair young woman in a utopian candyland, front view
  output:
    url: 35088183.jpeg
- text: 'blonde young woman wearing red shirt outside '
  output:
    url: 35087548.jpeg
- text: black hair woman wearing black shirt outside holding a red lightsaber
  output:
    url: 35087549.jpeg
- text: blonde young woman in a dark robot suit in a cyberpunk setting, front view
  output:
    url: 35087547.jpeg
- text: portrait green hair young woman in a utopian candyland, front view
  output:
    url: 35088363.jpeg
- text: >-
    Taylor Swift 2016, music awards, runway ,catwalk, model photo, Glamour
    portrait,
  output:
    url: images/example_j6ghxtm8s.png

---

# FLUX - Taylor Swift 

<Gallery />



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

## Model description

<h3 id="flux+-pony-lora-for-taylor-swift-hy3qu4l1k"><strong><span style="color:rgb(34, 139, 230)">FLUX+ Pony LoRA for</span><span style="color:rgb(64, 192, 87)"> Taylor Swift </span></strong></h3><h3 id=" ">



## Download model

Weights for this model are available in Safetensors format.

[Download](/Keltezaa/flux-taylor-swift/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('Keltezaa/flux-taylor-swift', weight_name='Flux.TaylorSwift-step00000350.safetensors')
image = pipeline('portrait green hair young woman in a utopian candyland, front view').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)