#225 · Primary category: Computer Vision
proper-pixel-art
Fixes AI pixel art images, video, or sprite web uploads
Project last updated:08/01/26
GitHub Stars
514
Forks
43
Contributors
9
License
MIT
Why we included this project
Pixel art pulled out of image and video models usually arrives noisy and slightly off-grid, and plain downscaling only smears it further. Proper Pixel Art instead locates the image's actual pixel grid and collapses each cell into a single clean pixel, recovering assets at their true resolution rather than leaving you with blurry approximations. It accepts stills as well as animated GIFs and video, so short generation loops stay stable across frames. You can run it through a local web interface, a CLI that fits into batch jobs, or a Python API, and the options include palette quantization, transparency handling, and edge upscaling so output is ready for a game engine. That saves real time: instead of redrawing each generated sprite by hand or shipping the noisy version, you automate the cleanup once and reuse it across your whole asset set.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)