GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
- pytorch
- gan
- deep-learning
- super-resolution
47,133 repositories indexed
1–21 of 21 · Most stars
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Luigi is a Python module that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built in.
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
:camera_flash: Fast batch image resizer and rotator
Upscale an image by a factor of 4, while generating photo-realistic details.
Official Hi3D v1.0: high-resolution 3D geometry refinement built on Sparc3D. Inference code, model weights, and documentation.
The open source air traffic simulator
Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.
[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"
Simulation-based Lidar Super-resolution for Ground Vehicles
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
A collection of tools for painting super-resolution images
A set of Maltego transforms for VirusTotal Public API v2.0. This set has the added functionality of caching queries on a daily basis to speed up resolutions.
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Noise Correction Algorithm for sCMOS cameras
Conflict-free merge for DataFrames, JSON, ML models & distributed agents — powered by CRDTs. The first merge library where every operation is mathematically guaranteed to converge.
MicroPython Library for new MAX31856 (Precision Thermocouple to Digital Converter with Linearization) with 19-Bit Thermocouple Temperature Resolution. This chip provides a SPI digital interface for Thermocouple Types B, E, J, K, N, R, S or T.