README.md

---
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
- pixel art
- sprites
- pixel
- style
- pokemon
- game cg
- video game art

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: 
widget:
- text: 'harley quinn
 
 simple background'
  
  output:
    url: >-
      9737393.jpeg
- text: 'of a woman with blonde hair, wearing a white summer dress
 
 simple background'
  
  output:
    url: >-
      9737398.jpeg
- text: 'maleficent, evil fairy,
 
 simple background'
  
  output:
    url: >-
      9737407.jpeg
- text: 'Daenerys Targaryen, Game of Thrones
 
 simple background'
  
  output:
    url: >-
      9737466.jpeg
- text: 'joker 
 
 simple background'
  
  output:
    url: >-
      9737478.jpeg
- text: 'jack sparrow, pirates of caribbean
 
 simple background'
  
  output:
    url: >-
      9737508.jpeg
- text: 'iron man
 
 simple background'
  
  output:
    url: >-
      9737483.jpeg
- text: 'deadpool
 
 simple background'
  
  output:
    url: >-
      9737471.jpeg
- text: 'neo the matrix
 
 simple background'
  
  output:
    url: >-
      9737470.jpeg
- text: 'charlie chaplin
 
 simple background'
  
  output:
    url: >-
      9737472.jpeg
- text: 'Super Mario stepped on a turtle
 
 simple background'
  
  output:
    url: >-
      9737429.jpeg
- text: 'link of zelda, with a sword
 
 simple background'
  
  output:
    url: >-
      9737481.jpeg
- text: '1girl angel with 2 large angel wings and a halo, perfect curves, wearing a white dress,
 
 simple background'
  
  output:
    url: >-
      9737509.jpeg
- text: 'woman, beautiful kimono, sakura
 
 simple background'
  
  output:
    url: >-
      9737499.jpeg
- text: '1girl, glasses, witch, hat, blue flame
 
 simple background'
  
  output:
    url: >-
      9737502.jpeg
- text: '1girl, solo, hood,
 
 simple background'
  
  output:
    url: >-
      9737504.jpeg

---

# Pokemon Trainer Sprite PixelArt 

<Gallery />



([CivitAI](https://civitai.com/models/159333))

## Model description

<h1 id="heading-524">Pokémon Trainer Sprite Generator</h1><p>LIKE THIS MODEL? GIVE A ❤️</p><p>Trained on Pokémon sprites of 96x96 and BLIP image captions.</p><h2 id="heading-525">Quick Tips</h2><ul><li><p><strong>No Trigger Word Needed:</strong> This model does not require a trigger word.</p></li><li><p><strong>Art Styles:</strong> You can use the tags <code>gen1</code> and <code>gen2</code> to generate different art styles.</p></li><li><p><strong>Trainer Recognition:</strong> The model can recognize some trainer names, such as Ash and Bruno.</p></li><li><p>This LoRA has been tested with Dreamshaper and RealisticVision, but I belive that it should work well with other models too.</p></li></ul><p></p><h3 id="heading-146">Model Versions</h3><p>This Pokémon Trainer Sprite LoRA is available in two different versions: 768x768 and 512x512. Both models are trained on images upscaled from their original 96x96 size and are specifically designed to produce sprites at their respective resolutions. The choice between these two versions allows users to customize their experience based on their specific needs.</p><p></p><p>For the best results, we recommend using the 768x768 version. Set your desired resolution to 768x768, and then downscale the result 8 times to achieve a 96x96 sprite. This downscaling process can be performed using any image editing program, but for a smoother post-processing experience, we recommend using a plug-in available at (<a target="_blank" rel="ugc" href="https://github.com/mrreplicart/sd-webui-pixelart">https://github.com/mrreplicart/sd-webui-pixelart</a>).</p><p></p><p><span style="color:rgb(255, 255, 255)">Enjoy your Pokémon Trainer sprite!</span></p><p></p><p></p>



## Download model

Weights for this model are available in Safetensors format.

[Download](/sWizad/pokemon-trainer-sprite-pixelart/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('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('sWizad/pokemon-trainer-sprite-pixelart', weight_name='pk_trainer_xl_v1.safetensors')
image = pipeline('1girl, solo, hood,
 
 simple background').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)