---
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
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: rup
widget:
- text: >-
    straight view face close-up of A beautiful naked white woman seeing camera
    is inside the waterfall, (((completely surrounded by the water))) as it
    cascades down from above and all around her. She is in a hidden space behind
    the waterfall, where the water forms a shimmering curtain in front of her,
    (((completely obscuring her from view))). The water rushes down around her,
    creating a sense of enclosure and seclusion within the waterfall itself. Her
    long wet hair clings to her face and shoulders, and the mist from the
    waterfall adds a mystical aura to the scene. The lush greenery outside is
    visible through the veil of water, but she remains tucked away in this
    intimate, secret space within the waterfall. her eyes are closed. her mouth
    is open. her head is tilted up looking into the cascading curtain of water
    as she gets drenched in falling water. her hair is soaking wet, her caramel
    skin is soaking wet, water is dripping from her body and hair,  water
    droplets on her face,  water dripping from her face, chin and nose, water
    droplets create a wet water effect,<lora:Wet_Face_Effect:1.5>, (((extremely
    straight deep side part thick black hairstyle)))
  output:
    url: images/example_qie4wiwj6.png

---

# Rupa

<!-- <Gallery /> -->

Trained on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train


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


## 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.float16).to('cuda')
pipeline.load_lora_weights('harshasai-dev/rupa', weight_name='lora.safetensors')
image = pipeline('your prompt').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)