Image super resolution using with Deep Convolutional Neural Networks

Generate Images, Upscale Images, Fix Faces and Replace background using custom Stable DIffusion Models

aiconvert.online offers a comprehensive suite of advanced AI tools accessible for free online. Users can enhance and manipulate images, perform AI conversion, create AI-generated art, and utilize various other AI-powered services. The platform is dedicated to providing cutting-edge technology 24/7 to meet diverse user needs.

Developed VisionSoC, an advanced image upscaling model using Enhanced Super Resolution Generative Adversarial Networks (ESRGAN) with Python, leveraging frameworks such as TensorFlow and Keras. Created a comprehensive web-based application for the model using HTML, CSS, and JavaScript, and integrated the frontend with the backend using Flask.

University Project for "Computer Architecture" course (MSc Computer Engineering @ University of Pisa). Implementation of a Parallelized Nearest Neighbor Upscaler using CUDA.

This simple image upscaling Django website uses the ESRGAN model to enhance and increase the resolution of images inputted by users. It includes downloading functionality as well as all authentication and authorization functionalities.

Icon Combiner App is a Python-based GUI application that allows users to combine two ICO icons into one. The application uses CUDA (if available) or CPU for upscaling the icons to a user-specified size or automatically sizes them based on their original dimensions. It provides detailed logging for error tracking and debugging.

Scale2x and Scale3x scaling of pixel art and low-resolution scans for OCR

ai image upscaling GUI application using Real-ESRGAN

Analysis resources for the Inter IIT Tech Meet 11.0 problem statement by ISRO: The Chandrayaan Moon Mapping Challenge

Super Fast Image Upscaling and Anime Captioning

Upscale the current image using RESRGAN directly within GIMP

Synthesize fast (4x upscaled) super-resolution images, in PyTorch & Gradio

Python tool to composite two images using one or more mask images

Exploring super-resolution upscaling of DEM data using the 2023 GISR model.

This is an ESRGAN model trained specifically for upscaling GameCube and Wii textures, but it can of course be used for other textures from that period.

Run https://github.com/upscayl/upscayl on NixOS using flakes

Telegram bot written in node typescript for GFPGAN Real-world Face Restoration tool