SD PixelArt SpriteSheet Generator

🚀 SD_PixelArt_SpriteSheet_Generator

This Stable diffusion checkpoint enables the generation of pixel art sprite sheets from four different angles, offering a unique way to create pixel - art characters.

🚀 Quick Start

This Stable diffusion checkpoint allows you to generate pixel art sprite sheets from four different angles. Merging this model with another one is the easiest way to get a consistent character with each view. However, you still need to adjust the settings in img2img to achieve the desired results. For the left and right views, it's recommended to pick the best result and mirror it. After you're satisfied with the output, you can take the photo into Photoshop or Krita, remove the background, and scale it to the desired size. Scaling it back up can also clear up some of the color murkiness in the initial outputs.

✨ Features

• Generate pixel art sprite sheets from four different angles.
• Merge with other models to get consistent character views.

📦 Installation

#!pip install diffusers transformers scipy torch

💻 Usage Examples

Basic Usage

from diffusers import StableDiffusionPipeline
import torch
model_id = "Onodofthenorth/SD_PixelArt_SpriteSheet_Generator"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "PixelartLSS"
image = pipe(prompt).images[0]
image.save("./pixel.png")

Advanced Usage

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion. You can also export the model to ONNX, MPS and/or FLAX/JAX.

Specific View Prompts

• Front View: Use "PixelartFSS"
• Right View: Use "PixelartRSS"
• Back View: Use "PixelartBSS"
• Left View: Use "PixelartLSS"

Merged Model Results

• Random results from the unmerged model
• Result from a merge with the Hermione model
• Result from a merge with the cat girl model

📄 License

This project is licensed under the Apache - 2.0 license.