Open-source alternatives to Deep Live Cam

ComfyUI-SeedVR2_VideoUpscaler is an AI video upscaling tool that uses diffusion models to increase the resolution of videos and images while maintaining visual consistency across frames. The project implements distributed video rendering by splitting datasets into chunks for parallel processing across multiple GPUs. It utilizes model compilation and specialized attention backends to reduce inference latency and increase throughput. Additional capabilities include video color correction using wavelet and LAB matching methods to preserve color fidelity. Hardware memory is managed through block

GoCV is a computer vision library and Go language binding for OpenCV. It serves as an image processing toolkit and deep learning inference engine, providing programmatic access to a wide range of algorithms for image manipulation, object detection, and video analysis. The project differentiates itself through high-performance native bindings and hardware acceleration. It utilizes a foreign function interface to map Go calls to C++ functions and includes a hardware-agnostic backend dispatch to route neural network tasks to computation engines such as CUDA and OpenVINO. The library covers a br

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

ncnn is a high-performance neural network inference framework designed for executing deep learning models locally on mobile and desktop hardware. It functions as a specialized engine that enables the deployment of artificial intelligence tasks directly on resource-constrained devices, eliminating the need for external network connectivity or cloud-based processing services. The framework provides a comprehensive toolset for model optimization, allowing users to convert and quantize machine learning models into specialized binary structures. By utilizing static model graph compilation and zero

clmtrackr is a JavaScript computer vision library designed for facial landmark detection and real-time tracking. It implements Constrained Local Models to identify specific coordinate points on a human face within video feeds or static images. The project functions as a real-time face warping engine and expression analysis tool. It can distort facial images via parametric models to create caricatures or identify and label emotional states such as happiness, sadness, anger, and surprise based on feature coordinates. The library covers a broad range of capabilities including automatic and manu

whisper.cpp is a C++ implementation of the Whisper speech-to-text model, serving as a lightweight machine learning inference engine and quantized runtime. It provides high-performance automatic speech recognition and real-time audio transcription without requiring a Python environment. The project utilizes model quantization to reduce memory usage and increase inference speed on local hardware. It incorporates hardware acceleration to optimize processing speed across different processors. The system covers audio processing capabilities including voice activity detection, speaker diarization,

TensorRT-LLM is a platform and toolkit designed for compiling, optimizing, and serving transformer-based models on accelerated hardware. It functions as a framework that transforms machine learning models into efficient execution graphs, providing an engine to refine these models for specific hardware to maximize throughput and minimize latency during text generation. The project distinguishes itself through advanced execution strategies that manage the entire inference pipeline. It utilizes kernel-level fusion and static graph execution to optimize mathematical operations and computational f

GPT4All is a cross-platform runtime environment designed to execute large language models directly on local consumer hardware. By leveraging an optimized C++ inference backend, it enables private, offline AI interactions without requiring an internet connection or external cloud services. The project provides a comprehensive ecosystem for managing the entire model lifecycle, including discovery, downloading, and configuration of local weights. What distinguishes the platform is its integrated retrieval-augmented generation engine, which allows users to index local documents into semantic vect

Nebullvm is an AI inference accelerator, GPU resource orchestrator, and performance optimization library for large language models. It functions as an optimization layer designed to lower operational costs by aligning model execution with underlying hardware architectures. The system maximizes cluster efficiency through real-time dynamic partitioning and elastic quotas for shared hardware resources. It employs alignment methods and techniques to reduce the hardware and data requirements necessary for tuning large language models. The project covers broad capability areas including AI infrast

SimSwap is a deep learning face swapping framework and computer vision media processor built with PyTorch. It functions as an image synthesis tool designed to replace a person's identity in images and videos with a target face using a single trained model. The system operates as a video identity replacement tool that swaps identities across frames while preserving the original expressions and lighting of the source media. It enables digital identity manipulation and the production of synthetic media through automated facial feature mapping. The framework supports both the application of trai

HeliBoard is a customizable Android keyboard that provides offline predictive text and a privacy-focused virtual interface. It operates entirely without internet permissions to ensure that all keystrokes and user data remain on the device. The keyboard features gesture-based glide typing and allows for the integration of external dictionaries to improve autocorrect and symbol search. It supports simultaneous multilingual input, enabling users to enter text in several different languages within a single session. Users can personalize the experience through editable text-file layout configurat

Valetudo is a custom firmware project for robot vacuums that enables local-only control, removing dependencies on cloud servers and protecting user privacy. It replaces proprietary vendor binaries with open source software to ensure that data, including floor plans and images, is not uploaded to external clouds. The project distinguishes itself by providing a rooted firmware installation process that prevents forced vendor updates. It implements a standardized control interface across different hardware brands and utilizes an MQTT-based message bus to facilitate integration with open source a

Dot is a deep learning face swap tool used to replace faces in live video streams, recorded media, and static images. It functions as a deepfake media processor and real-time video manipulator that applies facial transformations through neural network mapping. The system includes a virtual camera video injector that routes processed output into a system-level virtual device to simulate a physical hardware webcam. This allows generated video to be used within third-party video conferencing software. The tool supports real-time source switching via keyboard inputs to toggle between different s

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

LMOps is a research-driven operations framework for optimizing the deployment, fine-tuning, and performance of large language models. It provides a specialized toolkit for foundation model adaptation, inference acceleration, prompt optimization, and context orchestration. The framework distinguishes itself through an inference accelerator that reduces token generation latency by verifying and copying overlapping text spans from reference documents. It also features a prompt engineering optimizer that employs reinforcement learning, beam search, and non-natural language markers to automaticall

AITemplate is an ahead-of-time deep learning compiler that translates PyTorch neural networks into standalone C++ source code. It functions as a PyTorch to C++ compiler and a GPU kernel fusion engine, producing self-contained executable binaries that run inference without requiring a Python interpreter or deep learning framework runtime. The project generates optimized CUDA and HIP C++ code specifically for NVIDIA TensorCores and AMD MatrixCores. It focuses on maximizing throughput for half-precision floating-point operations through a system that combines multiple neural network operators in

LLMLingua is a prompt compression tool that reduces token count in prompts before they are sent to a large language model, cutting API costs and latency while preserving task performance. It operates as an extractive pipeline using a BERT-level Transformer encoder to classify each token for removal based on full bidirectional context from the prompt, retaining only key information and discarding non-essential tokens. The tool is trained through a knowledge distillation process, where a compact compression model learns from an extractive dataset derived from a large language model's output to

AidLearning-Framework is an integrated development platform for building and deploying AI applications on ARM-based devices. It combines Android and Linux operating systems running simultaneously on a single device, providing a unified runtime environment for cross-system AI development. The platform includes hardware acceleration across CPU, GPU, and NPU, with a unified API that automatically selects the optimal compute backend for inference. The framework distinguishes itself by enabling Python-based AI projects to be packaged directly into Android APK files for installation on mobile devic

PRNet is a Python library for 3D facial reconstruction. It uses a deep learning regression model to predict 3D facial geometry and vertex colors from a single 2D input image to generate a textured mesh. The project provides tools for digital face swapping, allowing the replacement of a target face with a new image and blending textures to match the original pose. It also includes a framework for face texture swapping and blending to fit specific 3D poses. Additional capabilities cover facial analysis, including the detection and alignment of facial landmarks and the estimation of head pose a

SadTalker is a generative framework designed to synthesize expressive talking head videos from static portrait images. By mapping audio signals or text prompts to three-dimensional facial motion coefficients, the system synchronizes lip movements, facial expressions, and head orientation to create realistic digital character performances. The project distinguishes itself by decoupling identity from dynamic motion through latent space encoding, ensuring that the generated animations maintain visual fidelity to the source portrait. It supports comprehensive motion synthesis, including full-body

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

This project is an expressive text-to-speech foundation model and voice cloning system designed to synthesize human-like speech with emotional nuance and high fidelity. It functions as a finetunable speech model that can generate audio mimicking a specific person using a reference voice sample. The system distinguishes itself through a high-performance inference engine that utilizes memory caching and hardware compilation to reduce latency during the audio generation process. It further allows for synthesis quality improvements by training the language model on custom datasets consisting of a

Sana is a framework for high-resolution image and video synthesis based on a linear diffusion transformer. It provides a toolkit for the training, fine-tuning, and execution of text-to-image and text-to-video models, as well as a video generative world model capable of simulating physical environments with precise spatial control. The project is distinguished by its use of linear complexity layers to handle high resolutions and its support for long-form, minute-length video generation in real time. It implements a two-stage inference paradigm that separates structural generation from visual t

This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene