Projects sharing features with Stylegan3

PyTorch-GAN is a research-oriented framework providing a collection of modular implementations for generative adversarial network architectures. It serves as a toolkit for training and evaluating models that utilize adversarial minimax optimization to produce synthetic data, offering a structured environment for exploring complex generative tasks within the PyTorch ecosystem. The library distinguishes itself through a comprehensive suite of image synthesis and manipulation capabilities, including super-resolution, inpainting, and cross-domain style translation. It supports advanced training m

This is a PyTorch-based implementation of diffusion models for synthesizing photorealistic images and video. It provides a framework for text-to-image and text-to-video generation, as well as unconditional image synthesis. The system utilizes a cascading diffusion pipeline to produce high-resolution imagery by passing low-resolution outputs through a sequence of super-resolution models. It also includes capabilities for image inpainting, allowing the reconstruction of masked or missing regions of visual media guided by surrounding context and text prompts. The project includes tools for diff

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 diffusion model training framework and image synthesis pipeline. It provides the tools necessary to train generative models to learn image data distributions through an iterative denoising process. The framework includes a generative model evaluation tool consisting of automated scripts used to measure the quality and accuracy of produced samples. The system covers model training pipelines and performance evaluation for generative diffusion models.

StyleGAN is a TensorFlow-based generative adversarial network framework designed for the synthesis of high-resolution synthetic imagery. It utilizes a style-based generator architecture to create realistic visual assets from latent vectors, focusing on the production of high-fidelity images. The system incorporates style mixing and stochastic noise injection to control visual attributes and fine-grained details. It uses adaptive instance normalization and progressive resolution upsampling to manage image quality and variety across different resolutions. The framework covers the full lifecycl

CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables the conversion of images between two distinct visual domains using datasets that do not require direct one-to-one matching examples. The project implements a deep learning style transfer tool capable of artistic style transfer, object transfiguration, and domain-to-domain conversion. It uses a dual-generator architecture and cycle-consistency loss to ensure that images translated to a target domain and back recover their original state. The framework covers core machine learnin

Keras-GAN is a collection of generative adversarial network implementations built with Keras for synthetic data generation and image manipulation. It provides frameworks for image-to-image translation, image inpainting, and neural image super-resolution. The library includes tools for learning disentangled latent space representations to control specific attributes of synthetic outputs. It also features capabilities for image domain translation using paired or unpaired data and the ability to fill corrupted or missing image parts by analyzing surrounding visual context. The project covers ge

StarGAN is a PyTorch image-to-image translation framework designed to synthesize visual styles and attributes across multiple domains. It implements a generative adversarial network that serves as a deep learning image translator for modifying specific visual characteristics within an image dataset. The framework uses a single unified model to handle translations between multiple image domains rather than requiring separate pairs of models. It is a research implementation that learns mappings between different image attributes without the need for paired training data. The project covers the

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

Z-Image is an AI image editing engine and generation framework designed for photorealistic synthesis and the refinement of diffusion models. It functions as a multilingual text-to-image renderer and a system for training custom foundation models to generate and edit visuals using natural language instructions. The project distinguishes itself through a reasoning-based prompt enhancer that expands simple descriptions into detailed visual instructions using a structured reasoning chain. It also features specialized capabilities for rendering high-quality Chinese and English typography within ge

This project is an AI model API gateway and proxy server designed to provide a unified interface for interacting with diverse artificial intelligence service providers. It functions as a centralized middleware platform that routes, load balances, and translates API requests across multiple models, enabling developers to access text, image, audio, and video generation capabilities through a single, standardized integration. The gateway distinguishes itself through comprehensive administrative and financial controls, including event-driven usage accounting, real-time token consumption tracking,

Tensorpack is a high-level TensorFlow neural network framework and research library designed for building and training deep learning models. It provides a collection of reproducible neural network architectures for computer vision, generative tasks, reinforcement learning, and natural language processing. The project distinguishes itself through a specialized deep learning data pipeline that uses pure Python for parallel data loading and streaming. It includes a multi-GPU training orchestrator for distributing workloads via data-parallel strategies and a dedicated interpretability toolkit for

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 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 is a deep learning research toolkit and generative model library providing implementations of Variational Autoencoders using the PyTorch framework. It serves as a framework for training and evaluating autoencoder architectures to learn latent representations for data reconstruction and the generation of synthetic data samples. The toolkit focuses on unsupervised feature learning and generative model training, featuring a system for mapping external configuration files to model hyperparameters to ensure reproducible experimental runs. It includes mechanisms for tracking training p

This project is a research framework and toolkit designed for training large-scale vision transformers and multimodal language models. It provides a comprehensive suite for vision-language pretraining, enabling the development of models that map images and text into shared latent spaces. The framework is distinguished by its capabilities in high-fidelity image generation and multimodal research, utilizing normalizing flows and variational autoencoders to produce images from text prompts or class labels. It supports the development of both generative and contrastive models, allowing for a wide

ComfyUI-LTXVideo is a generative framework and ComfyUI custom node extension for synthesizing high-fidelity video. It utilizes a latent diffusion and transformer-based system to create cinematic clips from text, image, and audio inputs, providing a modular interface for precise control over subject behavior and temporal consistency. The tool distinguishes itself with production-grade capabilities, including the generation of High Dynamic Range video in linear formats such as ARRI LogC3. It supports multimodal synchronization for audio-driven animation and lip-syncing, and allows for the creat

Open-Sora-Plan is a text-to-video framework and distributed video training system. It utilizes a diffusion transformer architecture and large language model components to transform written descriptions or image prompts into high-quality video sequences. The system features a distributed infrastructure designed for large-scale video training and inference. It employs sequence parallelism to split high-resolution or long-duration video samples across multiple GPUs and uses a sparse attention mechanism to increase processing speed. The project includes capabilities for both text-to-video and im

Oumi is a comprehensive large language model development platform designed for synthesizing data, fine-tuning models, and running performance evaluations. It serves as a unified environment for the entire model lifecycle, encompassing a training and fine-tuning suite, an evaluation framework, and tools for synthetic data generation and model distillation. The platform is distinguished by its iterative, failure-driven synthesis approach, which analyzes model weaknesses during evaluation to generate targeted training data. It utilizes an LLM-based judge framework to programmatically score respo

CogVideo is a generative video framework that uses diffusion models and transformer-based architectures to synthesize high-resolution video clips. It functions as both a text-to-video and image-to-video generator, converting textual descriptions or static images into temporal visual sequences. The system integrates large language model capabilities to expand short user prompts into detailed descriptions for better visual alignment. It supports the animation of static images through latent seeding and provides the ability to extend the length of existing video sequences. The project includes

Text2Video-Zero is a text-to-video diffusion model and framework designed to synthesize temporally consistent video sequences from textual prompts. It functions as a zero-shot video generator, repurposing pre-trained image diffusion models to create video content without requiring additional training on video datasets. The system includes a conditional video synthesizer that allows for guided generation using depth, edge, or pose maps to control structural layout and movement. It also provides text-based video editing capabilities to modify the style or content of existing video clips through

Wan2.1 is a generative video synthesis framework that provides foundation models for creating high-fidelity video sequences and static images from descriptive text prompts. The system utilizes a unified architecture trained on both static and dynamic datasets, allowing it to function as a comprehensive tool for visual media creation. The framework distinguishes itself through a transformer-based temporal modeling approach that ensures structural coherence and consistent motion across video frames. It supports multi-resolution latent scaling, enabling the generation of content in various aspec

LivePortrait is a computer vision framework designed for portrait animation and generative video synthesis. It functions as a deep learning system that transfers facial expressions and head movements from a driving video source onto a static image or an existing portrait video, effectively decoupling the subject's identity from the dynamic motion patterns. The framework utilizes keypoint-based motion retargeting and implicit 3D latent representations to map movements across different subjects, including both human and animal portraits. By employing canonical motion normalization and feature-s

SadTalker is an audio-driven talking head generator that produces synchronized speaking videos from a single source image and an input audio file. The system utilizes a deep learning framework to map speech signals to facial motion data, enabling the creation of lifelike digital avatars and animated characters. The project distinguishes itself by employing a three-dimensional morphable model to translate audio features into precise facial landmarks and head pose parameters. It integrates latent diffusion motion synthesis to generate naturalistic head movements and uses expression-aware textur

Puter is a browser-based desktop environment and cloud-native development platform that provides a virtualized graphical workspace. It enables developers to build and deploy full-stack web applications by integrating cloud storage, authentication, and serverless backend logic directly into the browser, eliminating the need for traditional server infrastructure. The platform distinguishes itself through a unified cloud storage layer and a distributed network runtime that facilitates peer-to-peer communication and cross-origin resource fetching. It features a sophisticated cross-window orchestr

SmolLM is a project dedicated to the development of small language models. It focuses on training and fine-tuning compact models that maintain high performance while utilizing fewer parameters. The project emphasizes efficient AI inference and on-device text generation, aiming to enable the deployment of lightweight models on edge devices with limited memory and processing power. It utilizes synthetic data generation to produce artificial datasets that improve the reasoning and training of these AI systems. The system supports a variety of optimization and training capabilities, including we