Showing headlines posted by sde

Dalai bills itself as “the simplest way to run LLaMA on your local machine”.

CodeFormer is command-line software which offers blind face restoration. This aims at recovering high-quality faces from the low-quality counterparts suffering from unknown degradation, such as low-resolution, noise, blur, compression artifacts, etc.

FBCNN (flexible blind convolutional neural network) is software which seeks to remove artifacts from JPEGs while preserving the integrity of the images. It decouples the quality factor from the JPEG image via a decoupler module and then embeds the predicted quality factor into the subsequent reconstructor module through a quality factor attention block for flexible control.

There is a staggering amount of proven open source software available to download. But it’s really difficult to keep up with the cream of the cream. That’s where this compilation aims to help.

Easy Diffusion offers a web user interface for Stable Diffusion, a deep learning text-to-image diffusion model capable of generating photo-realistic images given any text input. In seconds you can create stunning artwork. Stable Diffusion uses a kind of diffusion model, called a latent diffusion model.

RustDesk is remote desktop allowing maintenance of computers and other devices. The software aims for simplicity and ease-of-use, being designed to work out of the box.

Stable Diffusion is a deep learning text-to-image diffusion model capable of generating photo-realistic images given any text input. In seconds you can create stunning artwork. Stable Diffusion uses a kind of diffusion model, called a latent diffusion model.

For this review, we’re exploring a desktop application called ChatGPT. It’s a cross-platform tool built using Tauri, a framework for building tiny, fast binaries for all major desktop platforms. The ChatGPT project has no affiliation with OpenAI.

nvitop is an interactive NVIDIA device and process monitoring tool and bills itself as “the one-stop solution for GPU process management”. Like nvidia-smi, nvitop is built on top of NVML, but the tool offers a lot more functionality. It’s free and open source software written in Python.

StemRoller is software which lets you separate vocal and instrumental stems from any song with a single click. It uses Facebook’s Demucs algorithm for demixing songs and integrates search results from YouTube.

Scikit-learn is a machine learning library built on top of SciPy that supports supervised and unsupervised learning. It also provides various tools for model fitting, data preprocessing, model selection, model evaluation, and many other utilities. It’s accessible to everyone, and reusable in various contexts.

Upscayl is GUI software that uses sophisticated AI models to enhance your images by guessing what the details could be. It’s free and open source software.

An extremely interesting area of research relates to deep learning text-to-image models such as Stable Diffusion. These models can generate highly detailed images based on text descriptions.

Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. Powered by deep learning and neural networks, Whisper is a natural language processing system that’s built on PyTorch.

Ásbrú Connection Manager (Ásbrú) is a user interface that helps organizing remote terminal sessions and automating repetitive tasks. The project began as a fork of PAC (Perl Auto Connector) Manager.

Old Photo Restoration is an academic project that lets you restore old photos. This software uses PyTorch and is written in Python.

Ultimate Vocal Remover is a GUI that lets you isolate stems from music. It offers convenient access to a wide range of different models. It's free and open source software.

Coqui STT (STT) is a deep-learning toolkit for training and deploying speech-to-text models. This is free and open source software.

astroML is a Python module for machine learning and data mining built on NumPy, SciPy, scikit-learn, matplotlib, and Astropy.

The first article in the series looked at GFPGAN, deep learning software for real-world face restoration. Real-ESRGAN and GFPGAN have been integrated into each other, but they are also individual projects from the same developer. Real-ESRGAN is a project that aims to create practical algorithms for general image/video restoration as opposed to face restoration.