Awesome GitHub RepositoriesDiffusion Sampling Methods

This is a framework for training and sampling diffusion models to generate high-fidelity images, video, and 4D assets. It provides a modular environment for managing generative AI training pipelines, including the handling of datasets, noise sampling, and loss weighting to stabilize the creation of synthetic content. The project features a modular model configuration system that uses YAML-based assembly to define network submodules and conditioners. It also includes a dedicated toolset for AI image watermarking, allowing for the embedding and detection of invisible markers to verify the origi

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

This project is a diffusion-based AI art generator and animation framework used to create digital images and motion graphics from text prompts. It functions as a system for producing stylized videos and AI art through iterative diffusion sampling and neural network models. The framework distinguishes itself through specialized tools for 3D depth animation, using depth-map transformations to create spatial movement. It also includes neural style transfer capabilities to apply specific artistic looks, such as watercolor or pixel art, and utilizes optical flow frame blending to reduce flickering

This is a classifier-guided diffusion framework for high-fidelity image generation. It implements a cascaded diffusion pipeline that chains a base diffusion model with a dedicated upsampler to progressively increase image resolution in stages, and uses classifier-guided diffusion sampling to steer the reverse diffusion process toward higher-quality outputs. The framework provides tools for training diffusion models from scratch using distributed processes with gradient accumulation, as well as training classifier models that provide gradient-based guidance during sampling. It supports both un

DiffSinger est un synthétiseur vocal IA et un générateur audio neuronal conçu pour produire du chant et de la parole haute fidélité. Il fonctionne comme un système de synthèse vocale (text-to-speech) et un outil de synthèse de voix chantée basé sur la diffusion qui transforme le texte et la hauteur (pitch) en audio audible. Le système utilise un mécanisme de diffusion superficielle et un raffinement itératif du bruit pour générer des performances vocales réalistes. Il incorpore des plugins d'échantillonnage spécialisés et des solveurs numériques pour accélérer l'inférence et réduire le temps requis pour générer des voix synthétiques. Le projet couvre la modélisation acoustique, la synthèse de mel-spectrogrammes et la reconstruction par vocodeur neuronal pour convertir le texte en formes d'onde audio dans le domaine temporel. Il inclut également des capacités d'amélioration vocale synthétique pour améliorer la qualité sonore des enregistrements.

GLIDE is a generative model designed for text-to-image synthesis, image editing, and the contextual filling of masked image regions. It uses a guided diffusion process to transform random noise into high-resolution imagery that aligns with descriptive text prompts. The system provides specialized capabilities for modifying existing visuals, including the ability to alter specific image elements and iteratively refine selected regions through text-driven guidance. It also functions as an inpainting tool, filling missing or masked sections of an image with new content that blends naturally with