Awesome GitHub RepositoriesDiffusion Model Frameworks

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

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

Instruct-pix2pix is an instruction-based image model and PyTorch library designed to modify visual content by following natural language directions. It functions as a diffusion model image editor that applies human-written instructions to existing pictures rather than using traditional text-to-image prompts. The project provides a fine-tunable diffusion framework for adapting pre-trained checkpoints to specific image editing datasets. It includes a synthetic dataset generator that creates paired images and text triplets to train models on various image editing tasks. The system covers a rang

Diffusion Policy is a robot learning framework that uses diffusion models to map visual observations to precise action trajectories. It functions as an imitation learning toolkit and visuomotor policy learner, providing a system to train neural networks that replicate human behavior by generating robotic movements based on image and sensor data. The framework employs a conditional denoising process to sample sequences of robotic movements, allowing it to handle multimodal action distributions where multiple valid trajectories may exist for a single state. It utilizes score-based action modeli

Este es un framework de aprendizaje profundo de PyTorch y una herramienta para la síntesis de movimiento humano que genera animaciones de personajes en 3D a partir de prompts de texto o descripciones de acciones. Funciona como un generador de texto a movimiento que convierte lenguaje natural y etiquetas categóricas en secuencias de movimiento esquelético en 3D temporalmente consistentes. El sistema utiliza un modelo de difusión basado en transformadores para eliminar el ruido de los datos de movimiento de forma iterativa. Incluye capacidades para la generación condicionada por acciones, levantamiento de movimiento monocular a 3D y edición de secuencias de movimiento utilizando restricciones de texto. El framework incorpora la aplicación de restricciones de movimiento geométricas para garantizar la plausibilidad física a través de pérdidas de ubicación de articulaciones y velocidad. Además, cubre todo el pipeline de animación, incluyendo el entrenamiento del modelo de movimiento, la evaluación del rendimiento frente a datasets de referencia, el renderizado de mallas 3D y el control de simulación basado en física para la interacción ambiental.

This project is a diffusion model framework for training and sampling from denoising probabilistic models to generate images from noise. It functions as a generative image model that creates visual content by iteratively refining random noise into coherent images. The system includes a distributed GPU trainer designed to scale complex neural network architectures across multiple graphics processing units. It also provides an image dataset preprocessor to prepare, scale, and standardize raw image collections for training. The framework covers model training and image generation, utilizing noi

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

FastVideo is a comprehensive system for accelerated video generation, serving as a video generation inference engine, a video diffusion training framework, and a modular pipeline orchestrator. It provides a distributed transformer optimizer and a distillation toolkit designed to reduce denoising steps and model complexity to increase frame rates. The project distinguishes itself through specialized acceleration techniques, including joint distillation and sparse attention training. It implements low-step video generation and weight quantization to FP8 or FP4 precision to increase throughput a

Este repositorio sirve como recurso educativo estructurado para aprender a construir, entrenar y desplegar redes neuronales utilizando el framework PyTorch. Proporciona una colección de ejemplos de código prácticos y tutoriales diseñados para guiar a los profesionales a través de la implementación de modelos de deep learning. El proyecto cubre una amplia gama de dominios de machine learning, incluyendo visión artificial, procesamiento de lenguaje natural, modelado generativo y aprendizaje por refuerzo. Al utilizar componentes modulares y computación de gradiente automatizada, los materiales demuestran cómo construir arquitecturas complejas y optimizar los procesos de entrenamiento mediante algoritmos especializados y técnicas de aumento de datos. El contenido está organizado en una serie de ejercicios prácticos que abordan el ciclo de vida completo del desarrollo de modelos. Esto incluye la configuración de bucles de entrenamiento, la gestión de parámetros del modelo y la integración de modelos entrenados en entornos de producción.

Multimodal is a machine learning library built on PyTorch for training large-scale models that combine text, image, audio, and video data streams. It functions as a deep learning framework dedicated to generative diffusion models, multi-task training, and vision-language tasks. The library supplies modular building blocks, discrete latent codebook quantization, shared-space embeddings, and stackable adapter layers to handle diverse conditional inputs during training and inference. The framework supports specific architectures for diffusion models, text-to-video generation, image-text retrieva