metadata

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: null
widget:
  - text: harley quinn, simple background
    output:
      url: 9737393.jpeg
  - text: 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 '
    output:
      url: 9737508.jpeg
  - text: 'iron man '
    output:
      url: 9737483.jpeg
  - text: 'deadpool '
    output:
      url: 9737471.jpeg
  - text: 'neo the matrix '
    output:
      url: 9737470.jpeg
  - text: 'charlie chaplin '
    output:
      url: 9737472.jpeg
  - text: 'Super Mario stepped on a turtle '
    output:
      url: 9737429.jpeg
  - text: 'link of zelda, with a sword '
    output:
      url: 9737481.jpeg
  - text: >-
      1girl angel with 2 large angel wings and a halo, perfect curves, wearing a
      white dress, 
    output:
      url: 9737509.jpeg
  - text: 'woman, beautiful kimono, sakura '
    output:
      url: 9737499.jpeg
  - text: '1girl, glasses, witch, hat, blue flame '
    output:
      url: 9737502.jpeg
  - text: '1girl, solo, hood, '

Pokemon Trainer Sprite PixelArt

Prompt: harley quinn, simple background

Prompt: a woman with blonde hair, wearing a white summer dress, simple background

Prompt: maleficent, evil fairy, simple background

Prompt: Daenerys Targaryen, Game of Thrones, simple background

Prompt: joker, simple background

Prompt: jack sparrow, pirates of caribbean

Prompt: iron man

Prompt: deadpool

Prompt: neo the matrix

Prompt: charlie chaplin

Prompt: Super Mario stepped on a turtle

Prompt: link of zelda, with a sword

Prompt: 1girl angel with 2 large angel wings and a halo, perfect curves, wearing a white dress,

Prompt: woman, beautiful kimono, sakura

Prompt: 1girl, glasses, witch, hat, blue flame

(CivitAI)

Model description

Pokémon Trainer Sprite Generator

LIKE THIS MODEL? GIVE A ❤️

Trained on Pokémon sprites of 96x96 and BLIP image captions.

Quick Tips

No Trigger Word Needed: This model does not require a trigger word.
Art Styles: You can use the tags gen1 and gen2 to generate different art styles.
Trainer Recognition: The model can recognize some trainer names, such as Ash and Bruno.
This LoRA has been tested with Dreamshaper and RealisticVision, but I belive that it should work well with other models too.

Model Versions

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.

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 (https://github.com/mrreplicart/sd-webui-pixelart).

Enjoy your Pokémon Trainer sprite!

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

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