Projects sharing features with ComfyUI SeedVR2 VideoUpscaler

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

Deep-Live-Cam is a generative video transformation tool designed for real-time facial manipulation and cinematic enhancement. It functions as a local-first AI runtime, performing all media processing directly on the user's hardware to ensure complete data privacy without external network dependencies. By utilizing a high-performance processing pipeline, the application enables live face swapping and interactive video modifications during active streaming sessions or on pre-recorded media. The system distinguishes itself through a hardware-abstraction execution layer that dynamically routes co

AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc

Waifu2x-Extension-GUI is a desktop application designed for high-fidelity media restoration and enhancement. It functions as a graphical interface that orchestrates specialized deep learning engines to upscale, denoise, and interpolate images and videos, improving visual clarity and motion smoothness. The software distinguishes itself through its ability to manage complex, automated media processing pipelines. Users can chain multiple tasks—such as format conversion, scene detection, and frame rate interpolation—into sequential workflows that execute without manual intervention. It provides g

Video2x is a modular processing framework designed for AI-enhanced video upscaling and frame rate conversion. It functions as a comprehensive toolset for increasing the resolution and visual clarity of media files while generating intermediate frames to improve motion smoothness. The system is built to handle intensive media transformation tasks by leveraging hardware acceleration and custom encoding pipelines. The project distinguishes itself through a plugin-based architecture that allows for the integration of custom machine learning models and specialized algorithms. It utilizes a modular

Discoart is a diffusion model orchestration framework and distributed GPU generation engine designed to automate and scale image generation workflows across hardware clusters. It functions as a generative AI model API, providing HTTP and gRPC endpoints to trigger and retrieve images from diffusion models as a network service. The system distinguishes itself through a comprehensive task management layer that includes timeline-based prompt and parameter scheduling. It manages the generative art lifecycle by supporting state-based session serialization for recovery, YAML-based configuration mana

StableSwarmUI is a web interface and backend orchestrator for Stable Diffusion image generation. It functions as a distributed GPU image generator and a modular AI image pipeline, providing a centralized controller to manage image generation requests. The system distinguishes itself through the ability to split generation tasks across multiple graphics processors to increase batch throughput. It utilizes a backend-agnostic interface to connect to local servers, remote servers, and cloud APIs, and includes a graph-based visual workflow designer for defining complex image processing operations.

SwarmUI is a web-based interface and orchestrator for Stable Diffusion, designed to generate images and video. It functions as a modular workflow manager and an API gateway that allows for the configuration and execution of generative AI pipelines. The system is characterized by its ability to distribute generation workloads across multiple graphics cards to increase processing speed and total throughput. It employs a decoupled client-server architecture and a backend-agnostic interface, allowing the user interface to remain separate from the model execution environment. The platform support

Anime4K is a collection of graphics shaders and image processing algorithms designed to enhance the visual quality of animated media. It functions as a real-time upscaling engine that increases the resolution of video content during playback, allowing for higher fidelity viewing without the need to permanently re-encode source files. The project distinguishes itself by utilizing hardware-accelerated rendering to perform complex image reconstruction directly on the graphics card. By employing a pass-based pipeline, it chains multiple processing stages to refine frames iteratively, ensuring tha

EasyVtuber is 2D avatar animation software that transforms a single static image into a real-time animated character. It functions as a face tracking animation tool and live streaming avatar driver, mapping facial movements from webcams or iOS devices to drive virtual expressions and head motion. The project distinguishes itself through a neural animation pipeline that includes AI video upscaling and frame interpolation to increase visual smoothness and resolution. It utilizes a transparent video streaming system via Spout2, allowing rendered frames with alpha channels to be sent directly to

This project is an AI image upscaling and high-resolution generation tool. It uses tiled diffusion to create ultra-large images by processing them in smaller, overlapping regions to prevent memory crashes on limited hardware. The system manages spatial composition through regional prompting, which routes specific text prompts to designated areas of an image. It maintains visual stability and global coherence during the upscaling process using noise inversion and structural guidance. Additional capabilities include tiled detail upscaling and memory optimization for the variational autoencoder

PaddleGAN is a generative AI framework and deep learning computer vision library built on the PaddlePaddle framework. It serves as a toolkit for image and video synthesis, providing a collection of generative adversarial network implementations for creating synthetic visual content. The library focuses on advanced synthesis capabilities, including the generation of talking heads through lip motion synchronization and the creation of synthetic videos via motion transfer from driving sequences. It provides tools for domain-to-domain translation, allowing for image style transfer and the transfo

TensorRT is a deep learning inference engine and software development kit designed to optimize and deploy neural networks for high-performance execution on NVIDIA GPUs. It functions as a GPU acceleration framework that reduces latency and increases throughput for trained models during production deployment. The toolkit imports models from the Open Neural Network Exchange format and transforms them into optimized engines. It utilizes graph-based model optimization, layer-fusion kernel generation, and precision-based quantization to convert floating point weights into lower precision formats.

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

HunyuanVideo-1.5 is a video generation foundation model and text-to-video diffusion framework. It utilizes a latent video diffusion model and a spatio-temporal transformer architecture to generate high-definition video sequences from text descriptions and images. The project enables cinematic camera control for directing pans and tilts and provides image-to-video animation capabilities. It supports visual style adaptation through low-rank adaptation tuning and uses a language model for prompt refinement to improve visual alignment. The model covers high-resolution video upscaling via a super

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

Civitai is a platform for generative media creation and AI model distribution. It provides a centralized service for producing images, videos, audio, and music, while serving as a repository where users can share, discover, and browse custom model weights and fine-tuned adaptations. The platform distinguishes itself through a provider-agnostic orchestration layer that manages multi-step generation pipelines and complex workflows across different backends. It integrates with autonomous AI agents and editors via the Model Context Protocol, allowing external tools to access generation pipelines

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

Kdenlive is an open-source non-linear video editing suite designed for digital video post-production. Built on the MLT Framework and utilizing KDE Frameworks for its user interface, it provides a multi-track environment for assembling clips, applying transitions, and rendering final video files. The editor distinguishes itself through a comprehensive set of animation and effect tools, including keyframe-based parameter animation with a visual curve editor for fine-tuning transitions. It supports advanced visual modifications such as clip speed remapping, effect region masking, and the integra

This is a PyTorch recommendation framework and deep learning recommendation model designed to generate personalized content predictions. It functions as a distributed embedding trainer that processes dense and sparse features through a neural network architecture to predict user preferences. The project implements a CUDA-optimized machine learning system using specialized GPU kernels to accelerate embedding lookup and aggregation. It employs a distributed approach to shard massive sparse feature tables across multiple GPUs, enabling the training of large-scale models. The system utilizes a t

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

Gemma is a family of open-weights large language models based on a decoder-only transformer architecture. These models are designed for text generation and multi-modal conversations, capable of processing and generating responses based on both textual and visual input sequences. The project provides a fine-tunable AI model that supports weight adjustment and low-rank adaptation to specialize performance for particular tasks. It includes support for quantized weights to reduce memory usage and increase inference speed on limited hardware. The capability surface covers multi-modal AI integrati

Automatic Optical Disc Ripping Server is a headless system that detects inserted CDs, DVDs, and Blu-rays to automatically extract media, transcode video, and eject discs. It functions as a multi-drive media digitizer using a concurrent processing pipeline to rip and transcode media from several optical drives simultaneously without queuing. The system includes an asynchronous video transcoding pipeline that batches conversion tasks to run during scheduled off-peak hours. It also serves as a media server automation tool, fetching metadata from online APIs to name folders and trigger library re

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

Squirrel-RIFE is a GPU-accelerated video processing tool that uses a neural network to generate intermediate frames between existing video frames, enabling smooth slow-motion effects and frame rate conversion. It is built around the RIFE (Real-Time Intermediate Flow Estimation) model, which analyzes motion between consecutive frames to predict and insert new frames, and leverages NVIDIA CUDA for parallel processing to achieve high-speed inference. The tool distinguishes itself by combining neural frame interpolation with practical video preprocessing features, including pixel-level duplicate