Pokemon Trainer Sprite Pixelart

🚀 Pokemon Trainer Sprite PixelArt

This project is a Pokémon Trainer Sprite Generator that can generate pixel - art sprites of Pokémon trainers. It is trained on Pokémon sprites of 96x96 and BLIP image captions, offering a unique way to create Pokémon - related pixel art.

🚀 Quick Start

This Pokémon Trainer Sprite Generator allows you to create pixel - art sprites easily. You can use it with different art styles and recognize some trainer names.

✨ Features

• No Trigger Word Needed: This model does not require a trigger word, making it more user - friendly.
• Multiple 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.
• Multiple Versions: Available in 768x768 and 512x512 versions, allowing users to customize their experience based on specific needs.

📦 Installation

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

💻 Usage Examples

Basic Usage

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]

Advanced Usage

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

📚 Documentation

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).

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 it should work well with other models too.

📄 License

This model is under the [bespoke - lora - trained - license](https://multimodal.art/civitai - licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True).

Model Information Table