Awesome GitHub RepositoriesGenerative AI Training

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

This project is a framework for training and sampling generative models designed to produce high-quality images in few steps. It provides implementations for image generation models that transform random noise into structured visual data through an optimized sampling process. The system specializes in accelerating image generation through consistency distillation and consistency training. It includes tools to transform pre-trained diffusion models into faster versions by distilling knowledge from a teacher model into a student model, as well as methods to train consistency models from scratch

Este proyecto es una extensión de Stable Diffusion WebUI que proporciona una interfaz gráfica para la generación de retratos personalizados y edición de fotos con IA. Permite a los usuarios entrenar modelos de identidad personalizados a partir de un pequeño conjunto de imágenes subidas para crear versiones digitales consistentes de personas específicas. La extensión incluye un sistema de prueba virtual que reemplaza la ropa en las imágenes alineando prendas de referencia con cuerpos de plantilla. También cuenta con herramientas para el intercambio de rostros (face swapping) tanto en imágenes estáticas como en videos, así como un animador de retratos que transforma imágenes estáticas en videos dinámicos utilizando movimiento guiado por referencia y descripciones de texto. Las capacidades adicionales cubren la manipulación de atributos faciales para ajustar la edad y la expresión, la síntesis de imágenes de múltiples personas y la generación de transiciones suaves entre imágenes mediante interpolación en el espacio latente.

Este proyecto es un generador de retratos con IA y un boilerplate SaaS diseñado para entrenar modelos personalizados a partir de fotos subidas para producir retratos profesionales de alta resolución. Funciona como un pipeline de generación de imágenes y orquestador de entrenamiento de modelos que gestiona el flujo de trabajo integral de procesamiento de imágenes de usuario para crear avatares estilizados. El sistema incluye un framework de monetización basado en créditos que gestiona pagos mediante webhooks automatizados. Proporciona una infraestructura completa para servicios impulsados por IA, incorporando gestión de cuentas de usuario y notificaciones automáticas por correo electrónico para alertar a los usuarios cuando sus imágenes generadas están listas para descargar. La plataforma cubre la recopilación de fotos de entrenamiento, la selección de estilos de retratos profesionales y la producción de imágenes en resolución 4K. También incluye capacidades para mejorar la calidad de la imagen y asegurar que los retratos finales mantengan una estética natural y realista.

This project is an educational course and collection of training materials focused on generative diffusion models. It provides a curriculum and practical guides for training, fine-tuning, and deploying models capable of synthesizing images, audio, and video. The material covers specific implementation strategies including noise-based synthesis, iterative refinement, and latent space compression. It provides instruction on guiding generative outputs through conditional synthesis and prompt adherence optimization, as well as techniques for image inpainting and text-based editing. The project i

Photoshot is a commercial SaaS image platform and web application used for creating personalized AI avatars and portraits. It functions as an AI avatar creator that trains custom machine learning models on user-uploaded photos to produce consistent digital personas. The platform includes an LLM prompt generator that uses large language models to craft detailed text descriptions for image generation engines. It integrates a secure third-party payment gateway to manage user access to these creative tools and services. The system architecture handles asynchronous task queueing for machine learn

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

This project is a generative AI educational resource and natural language processing course. It serves as a technical implementation guide for building, pre-training, and fine-tuning a large language model from scratch using PyTorch. The curriculum provides a step-by-step tutorial on large language model development, focusing specifically on the design of transformer-based text generation models. It includes dedicated instruction on parameter-efficient fine-tuning to optimize training by updating only a small subset of model weights. The material covers the end-to-end generative AI training