---
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
- concept
- woman
- realistic

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: drkmdatmsftpicture
widget:
- text: ' '
  
  output:
    url: >-
      13117354.jpeg
- text: 'drkmdatmsftpicture close-up of a beautiful 1woman with red long hair looking at the camera with pale skin, lies under water, black flowers in her hair, gloomy atmosphere, soft colors, soft light, polaroid, film, dark theme, disturbing atmosphere'
  parameters:
    negative_prompt: bad anatomy, Cross-eyed, Distorted nose, Imperfect eyes, Distorted face, Low details, Underexposed, Low resolution, Distortion, realism, open mouth, teeth visible
            
  output:
    url: >-
      13116976.jpeg
- text: 'drkmdatmsftpicture close-up of a beautiful 1woman with red long hair looking at the camera with pale skin, lies under water, black flowers in her hair, gloomy atmosphere, soft colors, soft light, polaroid, film, dark theme, disturbing atmosphere'
  parameters:
    negative_prompt: bad anatomy, Cross-eyed, Distorted nose, Imperfect eyes, Distorted face, Low details, Underexposed, Low resolution, Distortion, realism, open mouth, teeth visible
            
  output:
    url: >-
      13117056.jpeg
- text: 'drkmdatmsftpicture close-up of a beautiful 1woman with red long hair looking at the camera with pale skin, in the dark group of creepy men with a creepy face and a creepy nose in the background, gloomy atmosphere, soft colors, soft light, polaroid, film, dark theme, disturbing atmosphere'
  parameters:
    negative_prompt: bad anatomy, Cross-eyed, Distorted nose, Imperfect eyes, Distorted face, Low details, Underexposed, Low resolution, Distortion, realism, open mouth, teeth visible
            
  output:
    url: >-
      13136799.jpeg
- text: ' '
  
  output:
    url: >-
      14084858.jpeg

---

# Underwater XL 

<Gallery />





## Model description

<p>I wanted to create a model that would combine the style of the beautiful and the disturbing.</p><p><span style="color:rgb(193, 194, 197)">Trigger - </span>drkmdatmsft lies under water</p>

## Trigger words
You should use `drkmdatmsftpicture`, `lies under water` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Moises08/underwater-xl/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('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to(device)
pipeline.load_lora_weights('Moises08/underwater-xl', weight_name='drkmdatmsfXL.safetensors')
image = pipeline('`drkmdatmsftpicture`, `lies under water`').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)