9 repositorios
Diffusion architectures that use flow-matching for more efficient noise-to-image transformation.
Distinct from Image Diffusion Models: Specifically focuses on flow-matching as an alternative to standard iterative denoising diffusion.
Explore 9 awesome GitHub repositories matching artificial intelligence & ml · Flow-Matching Frameworks. Refine with filters or upvote what's useful.
Flux is a diffusion model inference engine designed for text-to-image generation and image-to-image manipulation. It provides a system for executing open-weight models to transform natural language descriptions into visual imagery or to modify existing images. The project distinguishes itself through a flow-matching framework for image generation and a structural image controller. This controller allows for guided synthesis by using depth maps and Canny edge detection to constrain the geometry and composition of the output. The toolkit covers a broad range of image editing capabilities, incl
Utilizes a flow-matching framework to generate high-quality images more efficiently than standard diffusion.
Audiocraft is a deep learning audio library and machine learning framework designed for training, fine-tuning, and evaluating generative models for music and sound effects. It functions as a text-to-music generative model and a neural audio codec, providing the tools necessary to compress audio signals into discrete representations and synthesize high-fidelity waveforms from textual descriptions. The framework is distinguished by its ability to combine multiple conditioning signals, allowing for the generation of audio based on text prompts, melodic excerpts, or style-based audio clips. It al
Implements a flow matching objective to train models on continuous latents extracted from audio compressors.
F5-TTS is a text-to-speech system that utilizes a flow matching engine and diffusion transformers to generate fluent synthetic speech. It functions as a multilingual speech synthesizer and neural training framework, providing tools for voice cloning and high-performance inference serving. The project distinguishes itself through a voice cloning toolkit capable of mimicking specific speaker characteristics and tones from reference audio clips. It supports cross-lingual generation, allowing for the synthesis of audio across various global languages or the mixing of multiple languages within a s
Uses a flow matching engine and diffusion transformers to generate fluent synthetic speech.
This project is a machine learning research automation system designed to manage the full research lifecycle, from idea discovery to final paper submission. It utilizes markdown-based skill templates to execute autonomous research tasks and manage iterative loops of deep review and experimentation. The system distinguishes itself through integrated capabilities for academic communication and integrity auditing. It can automate the generation of LaTeX papers, conference slide decks, and evidence-grounded peer review rebuttals. To ensure rigor, it employs cross-model review routing and adversar
Transforms noise into clean embeddings using flow matching for continuous text generation.
AI NovelGenerator es una herramienta para generar ficción de formato largo utilizando modelos de lenguaje extensos. Funciona como un arquitecto narrativo y asistente de escritura, automatizando la creación de novelas de múltiples capítulos mientras gestiona la estructura general de la historia y el seguimiento de personajes. El proyecto se distingue por un sistema de recuperación de contexto semántico y un verificador de consistencia de historia por IA. Estas herramientas utilizan búsqueda semántica para recordar detalles específicos de la historia de capítulos anteriores y escanear el texto generado en busca de contradicciones en la trama o inconsistencias de comportamiento. El sistema cubre un ciclo de vida narrativo completo, incluyendo el diseño de la base de la historia, la construcción del mundo y la planificación de la estructura de la novela. Utiliza una canalización de múltiples etapas para redactar capítulos coherentes e incorpora un banco de trabajo de flujo de trabajo creativo para gestionar configuraciones y corrección de pruebas.
Provides automated scanning of generated text to identify logical plot contradictions and character inconsistencies.
Este proyecto es un framework de texto a voz neuronal y modelo de PyTorch diseñado para sintetizar voz humana. Convierte texto escrito en audio sintético prediciendo espectrogramas de mel, que sirven como una representación intermedia para la generación de voz. El sistema incluye un modelo de acondicionamiento para WaveNet para asegurar una salida de audio de sonido natural. Proporciona un framework de entrenamiento distribuido que utiliza procesamiento multi-GPU y precisión mixta automática para optimizar la velocidad de entrenamiento y reducir el uso de memoria. El proyecto cubre todo el pipeline de síntesis de voz neuronal, desde el entrenamiento del modelo utilizando conjuntos de datos de texto y audio hasta la generación de voces artificiales. Emplea un codificador-decodificador convolucional y atención de secuencia a secuencia para mapear características lingüísticas a marcos acústicos.
Provides a comprehensive neural engine for training speech models and generating synthetic audio.
Este proyecto es un framework de modelos generativos basado en PyTorch, diseñado para transformar ruido en distribuciones de datos complejas mediante el aprendizaje de campos vectoriales y trayectorias de probabilidad. Funciona como un kit de herramientas generativo multimodal para producir texto e imágenes sintéticas a través de flujos de probabilidad aprendidos. La librería se distingue por su soporte para integraciones en variedades continuas, discretas y de Riemann. Esto permite que el framework maneje una variedad de tipos de datos, incluyendo datos categóricos mediante el emparejamiento de flujos de estado discreto y espacios no euclidianos mediante la integración en variedades de Riemann. El kit de herramientas cubre todo el pipeline generativo, incluyendo la definición de trayectorias de probabilidad, regresión de campos vectoriales y el uso de solvers de ecuaciones diferenciales para el muestreo de datos. Estas capacidades permiten el entrenamiento e inferencia de modelos generativos capaces de crear contenido sintético en múltiples modalidades.
Provides a PyTorch-based library for implementing continuous and discrete flow matching algorithms to train generative models.
ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,
ExecuTorch continues text generation from a specific point in the cache, enabling stateful continuation.
Hunyuan3D-2.1 is a generative 3D framework and image-to-3D pipeline that transforms single 2D images into textured 3D geometries. It functions as an asset generator that produces high-quality 3D meshes and textures using a flow-matching system. The project includes a specialized synthesizer for creating photorealistic textures with physically based rendering properties. These tools allow for the simulation of metallic reflections and light interactions on generated models. The system covers 3D asset pipeline automation through a sequence of shape generation and mesh refinement. It also provi
Utilizes a flow-matching pipeline to transform Gaussian noise into initial 3D asset shapes.