Projects sharing features with PaddleGAN

ESRGAN is a deep learning image restoration framework designed for image super-resolution. It uses a generative adversarial network system to upscale low-resolution images into high-quality versions with sharp visual details and recovered fine textures. The framework implements a perceptual super-resolution model that optimizes the trade-off between perceived visual quality and pixel-level signal-to-noise ratio. It includes weight-interpolation blending to allow for the adjustment of visual sharpness and signal-to-noise ratios by mixing weights from different trained models. The system cover

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

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

mmagic is a multimodal training pipeline and framework for generative AI, focusing on visual synthesis and restoration. It provides the infrastructure to build and train models for tasks such as text-to-image and text-to-video generation, 3D-aware content synthesis, and high-fidelity image translation using diffusion models and generative adversarial networks. The project distinguishes itself through specialized capabilities for generative model personalization, including techniques for fine-tuning subjects and styles. It also supports advanced visual manipulations such as latent space interp

This project is a deep learning image restoration tool designed to remove scratches, fading, and noise from aged photographs and film. It utilizes generative adversarial networks for image translation, alongside specialized networks for face enhancement and video colorization. The system distinguishes itself through a combination of latent-space domain mapping and progressive face enhancement to recover blurred or missing high-frequency facial details. For video content, it employs a colorization framework that uses optical flow and temporal guidance to propagate color from selected keyframes

This project is a generative adversarial network designed for image animation and motion transfer. It functions as a computer vision framework that synthesizes video sequences by applying motion patterns extracted from a driving video onto a static source image. The model distinguishes itself by using a keypoint-based representation to decouple object appearance from temporal movement. By tracking structural deformations through learned latent coordinates, it performs motion retargeting and synthetic media production without requiring manual annotations or object-specific training data. The

SPADE is a semantic image synthesis framework and generative adversarial network designed to transform semantic label maps into photorealistic images. It uses a spatially-adaptive normalization model to modulate activations based on semantic maps, ensuring that spatial layouts and details are preserved throughout the synthesis process. The project enables the generation of diverse image variations from a single semantic layout by integrating variational autoencoders and latent vector style control. These mechanisms allow for the adjustment of visual appearances and textures while keeping the

This repository is a deep learning educational resource and a neural network project suite. It provides a collection of practical TensorFlow implementations and coding projects designed to demonstrate the application of various neural network architectures to real-world data. The project includes specific samples for generative adversarial networks, focusing on synthetic image generation and style translation. It also provides examples of deep learning model construction across different learning paradigms. The codebase covers a broad range of capabilities, including computer vision for imag

This project is a TensorFlow implementation of an image-to-image translation framework based on conditional generative adversarial networks. It provides the tools to train models that map input images to output images based on learned visual patterns, as well as a server for processing image translation requests and serving trained model checkpoints to web clients. The framework includes a system for converting trained model weights into a portable format for browser-based inference. It also features a validation process that generates comparative reports by analyzing input, output, and targe

EMO is an AI portrait animator and audio-to-video diffusion model designed to generate expressive talking head videos. It transforms a single static portrait image and an audio track into a synchronized video of a person speaking. The system focuses on digital human synthesis, producing high-fidelity facial movements and emotional cues. It synchronizes lip movements and facial gestures to match spoken voice recordings to create realistic portrait animations. The framework utilizes a diffusion process and a cross-modal alignment mechanism to ensure timing between audio signals and visual land

Imaginaire is a PyTorch image synthesis library and neural image translation framework designed to generate high-resolution synthetic visual content. It functions as a deep learning visual generator that maps semantic images and videos into photorealistic versions using both supervised and unsupervised methods. The project includes a specialized tool for rendering 3D environments, which converts block-based world representations into photorealistic scenes while maintaining long-term visual consistency. It further supports photorealistic video translation that utilizes reference images to ensu

Video-retalking is an AI lip synchronization framework and talking head video editor designed to match the mouth movements of a subject in a video to a target audio track. It utilizes a deep learning pipeline to synchronize speech with video recordings. The system employs a two-stage generation process that separates coarse lip movement from high-resolution detail refinement. It incorporates identity-aware face refinement and expression template alignment to maintain photorealistic skin textures and ensure visual consistency across video frames. The toolset covers facial expression modificat

This project is a PyTorch implementation of AnimeGANv2, a generative adversarial network and image-to-image translation model designed to transform real-world photographs into stylized anime imagery. The repository includes a model weight converter that enables the translation of checkpoints across different runtime environments. This utility performs weight key remapping and tensor dimension permutation to ensure compatibility between framework implementations. The system supports AI photo stylization through pre-trained weight loading and provides configurable upsampling alignment to maint

LatentSync is an audio-driven video generator and latent diffusion lip sync model designed to synchronize a speaker's lip movements in a video to a target audio track. It provides a lip synchronization training framework for developing synchronization networks on custom video and audio datasets. The system utilizes a video preprocessing pipeline to clean, segment, and align face data. It includes a visual sync evaluation tool that calculates confidence scores to measure the accuracy of audio and visual alignment in generated videos. The project covers capabilities for custom synchronization

This project is a deep learning library built for single-image super-resolution and visual enhancement. It provides a framework for training and deploying neural network architectures designed to reconstruct high-resolution images from low-resolution sources, effectively recovering fine details and removing artifacts caused by downscaling or compression. The library distinguishes itself through the implementation of generative adversarial networks and residual block architectures, which work together to improve the realism and clarity of upscaled outputs. It supports training through both pix

TecoGAN is a generative adversarial network designed for video super-resolution. It functions as a spatio-temporal video upscaler that increases the resolution of video sequences while reconstructing high-quality imagery from lower-resolution inputs. The system utilizes a temporal coherence framework to ensure visual stability and reduce flickering in generated frames. It achieves this by employing spatio-temporal discriminators that evaluate both individual frame quality and movement consistency. The project covers the training and optimization of generative adversarial networks, specifical

Faceai is a computer vision toolkit designed for facial analysis, identity recognition, and image processing. It provides integrated engines for detecting human faces in static images and live video streams, matching facial encodings against identity databases, and mapping facial landmarks to understand geometric structure and alignment. The project enables real-time augmented reality applications, such as applying virtual makeup and digital accessories by scaling assets to detected facial coordinates. It also includes a suite for digital image restoration capable of removing noise, erasing w

InfiniteTalk is an open-source system for generating talking head videos driven by audio input. It synthesizes realistic lip movements, head poses, and facial expressions synchronized to a spoken audio track, using either a single still image or a small set of reference video frames as the visual source. The system can produce videos of arbitrary length while maintaining temporal coherence, and it supports animating multiple subjects in a single scene. A key differentiator is the ability to coordinate multiple talking subjects through a structured JSON description, giving each independent lip

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

AnimateDiff is a latent diffusion video generator and text-to-video diffusion framework. It converts existing text-to-image diffusion models into animation generators by applying specialized motion modules, allowing for the creation of video sequences without modifying the original base model. The project provides an image-to-video animation framework that uses sparse RGB images, sketches, or structural keyframe constraints to guide generation. It further distinguishes itself with a motion adapter system that injects cinematic camera movements, such as zooming, panning, and tilting, into anim

Srez is a deep learning image super-resolution framework designed to upscale low-resolution images into sharp, high-resolution visual features. It functions as a neural network training tool that employs generative adversarial networks to synthesize realistic image details. The project includes a model evolution visualizer that generates animations and image batches to track visual improvements during the training process. It utilizes a combination of adversarial and L1 loss functions to optimize model weights and supports periodic state checkpointing for recovery and deployment. The system

This project is a collection of PyTorch deep learning courseware consisting of practical projects and programming exercises. It focuses on implementing neural network architectures and model training to solve complex data problems. The repository includes a computer vision project suite for building image classifiers, autoencoders, and style transfer applications. It features a generative adversarial network lab for creating synthetic images and specific implementations for transfer learning to adapt pre-trained weights to new tasks. The codebase covers sequential data analysis for natural l

AnimateAnyone is an appearance-preserving video synthesizer designed for character animation from a single static image. It functions as a diffusion image-to-video generator that transforms a source image into a high-fidelity video sequence while maintaining consistent character identity, clothing, and visual details across all frames. The system enables video-driven character reenactment by transferring motions, facial expressions, and body movements from a reference video onto a static character. It employs pose-guided video generation to control movement via skeleton keypoints and pose sig

This project is a Go library designed for facial detection, landmark mapping, and identity verification. It provides a toolkit for integrating computer vision capabilities into applications, enabling the automated identification and analysis of human faces within digital images. The library utilizes a deep residual network to transform facial data into compact vector representations, which are then compared using geometric distance calculations to confirm identities. It employs histogram-based object detection to locate facial structures and maps specific points on the face to define geometry

IP-Adapter is a framework for conditioning pretrained text-to-image diffusion models to use image prompts as visual guides. It serves as a text-to-image model extension that transforms a text-based diffusion model to accept and process image inputs as primary generation sources. The system implements identity preservation to maintain consistent facial features across multiple outputs using a reference photo. It also enables style transfer workflows to produce image variations that preserve the artistic characteristics of a source image. Capabilities cover multi-modal prompting, including the

This project is a comprehensive library for transfer learning and domain adaptation in computer vision. It serves as a framework for aligning feature distributions between source and target datasets, a toolkit for domain generalization, and a library for semi-supervised learning using small labeled datasets and large unlabeled sets. The library provides specialized capabilities for unsupervised domain adaptation, including the use of adversarial networks, discrepancy-based architectures, and image-to-image translation to reduce distribution mismatch. It also includes tools for domain generali

ComfyUI-nunchaku is a 4-bit diffusion inference engine and a set of nodes for running low-precision quantized diffusion models within ComfyUI visual workflows. It provides a backend that reduces memory overhead and increases generation speed for transformer models. The project includes specialized tools for identity-preserving generation and an image-to-image guidance toolkit that uses depth maps and reference images. It also features a multimodal visual question answering implementation and a utility for merging multiple quantized model files into single unified files. The engine covers a b