Proper Pixel Art

by Kenneth Allen

Noisy, high resolution

→

Clean, true-resolution pixel art

Summary

Converts noisy, high-resolution pixel-art-style images (from generative models or low-quality web uploads) into clean, true-resolution assets. Such images often have a non-uniform grid and random artifacts, so standard downsampling fails — the usual alternatives are naive downscaling or redrawing the asset pixel by pixel. This tool automates the recovery instead. Videos and GIFs are supported too.

Contents

• Examples
• Installation
  • Install From PyPI
  • Install from source
  • Run without installing
• Usage
  • Web Interface
  • CLI
  • Videos and GIFs
  • Python API
  • Configuration file
• Real Images To Pixel Art
• Algorithm

Examples

The algorithm is robust. It performs well for images that are already approximately aligned to a grid.

Here are a few examples. A mesh is computed, where each cell corresponds to one pixel.

Bat

• Generated by GPT-4o.

Noisy, High Resolution

Mesh

True Pixel Resolution

Ash

• Screenshot from Google images of Pokemon asset.

Noisy, High Resolution

Mesh

True Pixel Resolution

Demon

• Original image generated by GPT-4o.

Noisy, High Resolution

Mesh

True Pixel Resolution

Pumpkin

• Screenshot from Google Images of Stardew Valley asset. This is an adversarial example as the source image is both low quality and the object is round.

Noisy, High Resolution

Mesh

True Pixel Resolution

Installation

Install From PyPI

pip install proper-pixel-art  # CLI and Python API
pip install "proper-pixel-art[web]"  #  Include the local web UI

Or with uv:

uv add proper-pixel-art  # CLI and Python API
uv add proper-pixel-art --extra web  # Include the local web UI

Install from source

git clone git@github.com:KennethJAllen/proper-pixel-art.git
cd proper-pixel-art
uv sync --extra web

Run without installing

uvx can run the tools directly:

uvx --from "proper-pixel-art" ppa <input_path>  # CLI
uvx --from "proper-pixel-art[web]" ppa-web      # Local web UI

Usage

First, obtain a source pixel-art-style image (e.g. from a generative model such as OpenAI's gpt-image-2, or a web upload of pixel art). See scripts/README.md for a helper script that generates source images from a prompt.

The examples below assume you installed via pip install or uv add (commands are on your PATH). If you installed from source with uv sync, prefix each command with uv run (e.g. uv run ppa ...).

Web Interface

Try it live in your browser, no install required, on Hugging Face Spaces.

To run the same interface locally:

ppa-web
# Opens http://127.0.0.1:7860

CLI

ppa <input_path> -o <output_path> -c <num_colors> -s <result_scale> [-t]

Options

Option	Description
INPUT (positional)	Source image, video, or GIF in pixel-art style
-o, --output <path>	Output directory or file path for result. (default: '.')
-c, --colors <int>	Number of colors for output (1-256). Use 0 to skip quantization and preserve all colors. May need to try a few different values. (default 0)
-s, --scale-result <int>	Width/height of each "pixel" in the output. 1 = no scaling. (default: 1)
-t, --transparent	Output with transparent background. (default: off)
-u, --initial-upscale <int>	Initial image upscale factor. Increasing this may help detect pixel edges. (default 2)
-w, --pixel-width <int>	Width of the pixels in the input image. Use 0 to determine it automatically. (default: 0)
--config <path>	YAML config file of pixelation parameters. Flags passed explicitly override values in the file. (default: none)
--intermediate-dir <path>	Directory to save images visualizing intermediate algorithm steps. Useful for development. (default: none)

Example

ppa assets/blob/blob.png -c 16 -s 25

Tip: --colors (-c) is the parameter most likely to need tuning — try a few values if the result looks off.

Videos and GIFs

Video and GIF inputs are recognized by extension, so the same ppa command pixelates animations too (e.g. from video models such as Sora). The result stays consistent frame-to-frame with no flicker — see how the algorithm handles animations for details.

ppa <input.mp4|input.gif> -o <output_path> -c <num_colors>

The output format follows the output extension (e.g. -o out.mp4 converts a GIF to MP4), and all the pixelation options and --config from the table above apply.

Two extra options apply to video/GIF inputs (they are ignored for images):

Option	Description
-f, --format <mp4|gif>	Output format. (default: inferred from output, then input, extension)
-n, --sample-frames <int>	Frames sampled for mesh and palette detection. (default: 8)

The ppa-video command is a deprecated alias for ppa, kept for compatibility.

GIF input is decoded with full frame compositing (variable-size delta frames, per-frame durations, and transparency are preserved). GIF output uses a single global palette.

MP4 output is encoded near-losslessly (libx264 at CRF 1) via PyAV, whose wheels bundle the FFmpeg libraries — so quality doesn't depend on what's installed on your machine. Note for anyone redistributing a bundled app: PyAV's wheels ship a GPL build of FFmpeg.

Python API

For Python developers who want to integrate this tool into their own code.

from PIL import Image
from proper_pixel_art import pixelate

image = Image.open('path/to/input.png')
result = pixelate(image, num_colors=16)
result.save('path/to/output.png')

Videos and GIFs have their own entry point:

from proper_pixel_art.video import pixelate_video

pixelate_video('input.mp4', 'output.gif', num_colors=16)

Parameters

The keyword arguments mirror the CLI options table above: num_colors (-c), scale_result (-s), transparent_background (-t), initial_upscale_factor (-u), pixel_width (-w), and intermediate_dir (--intermediate-dir). In addition:

• image : PIL.Image.Image — the image to pixelate.
• config : PixelateConfig | None — a bundle of every tunable parameter, loaded with PixelateConfig.from_yaml(path) (see Configuration file). Explicit arguments override matching values in config.

Returns

A PIL image with true pixel resolution and quantized colors.

Configuration file

All tunable parameters can be collected in a YAML file so you can fine-tune the algorithm without changing code — including the deeper mesh-detection (Canny, Hough, line clustering) and color (alpha/transparency thresholds, quantization method, color binning) settings not exposed as CLI flags or direct arguments. See config.example.yaml for the full list of keys with their defaults. Any key you omit falls back to the default, so partial files are fine.

from PIL import Image
from proper_pixel_art import pixelate
from proper_pixel_art.config import PixelateConfig

config = PixelateConfig.from_yaml('config.yaml')
result = pixelate(Image.open('input.png'), config=config)

From the CLI, pass --config. Flags given explicitly override values from the file:

ppa input.png --config config.yaml      # use the file
ppa input.png --config config.yaml -c 8 # but override num_colors to 8

Real Images To Pixel Art

This tool can also be used to convert real images to pixel art: first request a pixelated version of the original image from GPT-4o, then use the tool to get the true pixel-resolution image. The mountain at the top of this README was made this way, starting from this photo:

Original photo

→

True-resolution pixel art

Algorithm

Here's a step-by-step overview, applied to this GPT-4o-generated blob:

• Note that this image is high resolution and noisy.

1. Trim the edges of the image and replace mostly-transparent pixels (alpha below 50%) with a background color.

   • This is to work around some issues with models such as GPT-4o not giving a perfectly transparent background.

2. Upscale by a factor of 2 using nearest neighbor.

   • This can help identify the correct pixel mesh.

3. Find edges of the pixel art using Canny edge detection.

1. Close small gaps in edges with a morphological closing.

1. Take the probabilistic Hough transform to get the coordinates of lines in the detected edges. Only keep lines that are close to vertical or horizontal giving some grid coordinates. Cluster lines that are closeby together.

1. Find the grid spacing by filtering outliers and taking the median of the spacings, then complete the mesh.

1. Quantize the original image to a small number of colors (see the num_colors tuning note above).

2. In each cell specified by the mesh, choose the most common color in the cell as the color for the pixel. Recreate the original image with one pixel per cell.

   • Result upscaled by a factor of $20 \times$ using nearest neighbor.

Videos and GIFs

The same algorithm generalizes to animations by exploiting the fact that every frame shares one underlying pixel grid and palette. Rather than solving frames independently (which would make the mesh and colors jitter frame-to-frame), the mesh-detection steps (1–6) and color quantization (step 7) are run once over a sample of frames to fix a single grid and shared palette. That grid and palette are then applied to snap every frame (step 8), so the whole animation resolves to consistent, true pixel resolution.