Projects sharing features with DragGAN

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

StyleCLIP is a framework for steering generative models using contrastive language-image pre-training to edit and synthesize imagery. It functions as a latent space image editor that manipulates high-dimensional vector representations to align visual features with natural language descriptions. The system modifies StyleGAN generated images by calculating the difference between neutral and target text embeddings. This process allows for the isolation of specific visual attributes, such as age, gender, or expression, by projecting semantic changes onto the latent manifold. The project covers c

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

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 PyTorch-based image super-resolution tool provides a deep learning pipeline for upscaling low-resolution images. It utilizes generative adversarial networks to increase pixel density and reconstruct high-resolution image details. The system includes a GAN-based image upscaler and a training pipeline that optimizes neural network weights using paired datasets and custom loss functions. To manage hardware resources, a patch-based image processor splits high-resolution files into smaller segments to prevent memory allocation errors and system crashes. Additional capabilities include the ap

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

AnyText is a visual text synthesis framework and latent diffusion text model designed to generate and edit text within images. It functions as a multilingual diffusion text generator that blends glyph and stroke data into latent image features to ensure precise character placement and rendering. The system enables the modification or replacement of existing characters and words inside images while preserving the surrounding visual context. It supports the creation of stylized text effects through the use of a weight-merging pipeline that combines specialized model weights and adaptation layer

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

This project is a collection of TensorFlow 2.x machine learning tutorials and practical code examples. It serves as a deep learning implementation guide for constructing diverse neural network architectures, including convolutional, recurrent, and generative networks. The repository provides templates and examples for several specialized domains, including computer vision for image classification and object detection, natural language processing for text generation and language understanding, and generative AI for synthesizing data using adversarial networks and autoencoders. It also includes

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

White-box Cartoonization is a machine learning model and research implementation that transforms real photographs into cartoon-style images. It utilizes a generative adversarial network to apply artistic styles to photographic input. The project employs a white-box representation decomposition method to separate images into surface, structure, and texture components. This approach allows for the targeted stylization of each element during the transformation process. The system includes a multi-stage training pipeline for processing custom datasets and supports inference using pre-trained wei

This project is a PyTorch implementation of StyleGAN2, providing a library and research framework for training style-based generative adversarial networks. It serves as a toolkit for high-resolution image synthesis, utilizing competitive minimax optimization to create realistic synthetic visual content. The framework incorporates specialized architectural components such as style-based latent mapping, multi-scale feature modulation, and self-attention layers to improve structural coherence. It distinguishes itself with advanced training stability techniques, including exponential moving avera

This is a PyTorch CNN visualization toolkit designed for neural network interpretability. It provides a set of tools to explain model decisions and analyze the internal behavior of convolutional neural networks through the visualization of activations, gradients, and filters. The project implements specialized techniques for synthesizing representative images, including Deep Dream optimizations to amplify patterns and class-specific image generation via input optimization. It also features a saliency map generator that produces gradient-based heatmaps to identify the specific image regions in

This project is a neural style transfer framework that provides a suite of computer vision tools for applying artistic styles to images and video. It functions as a system for training feedforward neural networks, an iterative style optimizer, and a real-time video stylizer. The framework supports two primary methods of stylization: a feedforward model that applies styles in a single pass and an iterative optimization method that generates stylized images by minimizing content and style loss without a pre-trained model. It also enables real-time processing of live webcam feeds using trained m

This project is a machine learning educational repository providing a collection of implementations and guides for machine learning and deep learning algorithms. It serves as a deep learning model library and a reference for training workflows, covering foundational machine learning, convolutional, recurrent, and transformer architectures. The collection includes a generative adversarial network suite for synthesizing realistic images and performing image-to-image translation. It also functions as a computer vision implementation guide for object detection and semantic segmentation, alongside

This project is a TensorFlow-based neural style transfer tool and deep learning image processor. It uses convolutional neural networks to apply the artistic style of one image to the content of another through neural image synthesis. The system supports multi-style blending to combine artistic characteristics from several different images into a single output. It also includes color-preserving stylization, which maintains the original color palette of the source image by merging source color data with the luminance of the stylized result. The tool provides capabilities for style abstraction

This project is a generative adversarial network implementation and research framework. It provides the tools and hyperparameters necessary to train and evaluate generative models across various datasets, specifically designed to reproduce results from academic research. The framework includes a Parzen density likelihood estimator to calculate model log likelihood. This allows for the quantitative evaluation of generative distributions and the measurement of overall model performance. The codebase covers machine learning research capabilities, focusing on the training of adversarial networks

RestorePhotos is an AI face restoration tool and deep learning image upscaler designed to remove blur and reconstruct lost details in degraded facial photographs. It functions as a face photo enhancer and a generative adversarial network image processor that transforms low-quality pixels into high-resolution facial features. The system utilizes a GPU-accelerated inference engine to run machine learning models for real-time image restoration. This hardware acceleration supports the heavy matrix multiplications and tensor-based operations required to sharpen facial images and improve visual fid

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

iGAN is a framework for producing synthetic images using generative adversarial networks. It provides a web-based interface for interactively creating and editing imagery across categories such as landscapes, architecture, and fashion using pre-trained models. The system enables precise control over visual output through latent space exploration, interpolation, and projection. Users can guide the generative process using an interactive editor featuring sketching, coloring, and warping brushes to refine specific regions or shapes in real-time. The project supports both automated scripted gene

This project is an unsupervised image restoration tool that uses a convolutional neural network as a structural prior to reconstruct images from noisy or incomplete data. It functions as a neural network image prior, utilizing the inherent biases of the network architecture to restore pixels without the need for a pre-trained dataset or external learning. The system performs zero-shot image restoration by treating the network architecture itself as a regularization term. It uses a randomly initialized encoder-decoder structure and iterative gradient descent to minimize pixel-wise loss, recove

This project is a machine learning educational archive and technical documentation collection. It serves as a deep learning tutorial series and implementation guide, providing theoretical explanations and practical walkthroughs for constructing and optimizing neural networks. The content focuses on the design and construction of diverse model architectures, including convolutional neural networks, Long Short-Term Memory networks, and generative adversarial networks. It details specific implementation patterns for autoencoders, sentiment analysis models, and various classification approaches.

Pulse is a face image super-resolution tool and self-supervised image enhancer. It functions as a generative model image upsampler and latent space optimization tool designed to increase photo resolution and recover image details. The system differentiates itself by using latent space exploration and spherical constraints to find high-fidelity matches within a generative model. It employs geodesic distance measurement and spherical latent space optimization to regularize representations and maintain parameter radii during the recovery process. The project covers facial image restoration thro

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

Co-tracker is a PyTorch point tracking framework and dense point tracking model designed to map the motion of individual pixels throughout a video. It functions as a video pixel tracker that predicts point trajectories and visibility masks across sequences of video frames. The project includes a computer vision training pipeline that utilizes teacher-student knowledge distillation. This allows for the generation of pseudo-labels from unannotated real video data to fine-tune pre-trained models and reduce the gap between synthetic and real data environments. The framework provides capabilities

This is a generative AI model library containing a collection of PyTorch and TensorFlow implementations for creating synthetic data and modeling complex probability distributions. It serves as a multi-framework repository of deep learning models designed for learning and replicating data patterns. The project provides specialized implementation suites for several generative architectures. This includes Generative Adversarial Networks using competing generator and discriminator models, Variational Autoencoder frameworks that map data to a latent space, and Restricted Boltzmann Machine and Deep

This project provides a cloud-based notebook configuration for deploying a Stable Diffusion web interface. It functions as a specialized environment for image generation, incorporating a model trainer for fine-tuning weights and creating training datasets. The system emphasizes infrastructure persistence by saving software installations and model files to cloud storage, avoiding repetitive setups between sessions. It uses a tunnel-based interface to expose the web dashboard to a public URL for remote interaction. The project covers end-to-end AI workflows, including dataset preparation and t