26 dépôts
Defined sequences of automated steps for creating and refining generative content through iterative processing.
Explore 26 awesome GitHub repositories matching artificial intelligence & ml · Generative AI Workflows. Refine with filters or upvote what's useful.
ComfyUI is a node-based generative AI orchestration engine designed for constructing, testing, and executing complex image and video synthesis pipelines. By utilizing a directed acyclic graph execution model, the platform allows users to build reproducible workflows through modular, interconnected processing blocks without requiring manual code implementation. It serves as both a local environment for high-performance model inference and a production-ready server for deploying generative capabilities. The platform distinguishes itself through its focus on workflow portability and extensibilit
Synthesizes video sequences from textual prompts by executing complex, multi-stage generative workflows.
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,
Provides workflows for generating modified or extended versions of existing images via text instructions.
TaskMatrix is a multimodal AI chat interface and visual task orchestrator. It combines language models with visual recognition to enable the exchange, analysis, and modification of images within a conversational environment. The system coordinates multiple foundation models through orchestration pipelines that chain language, detection, and segmentation models. This allows for complex visual operations, such as using text instructions to guide image masking and executing modular inpainting workflows to edit specific image regions. The project includes a computer vision toolset for object det
Provides a modular workflow for modifying image regions using segmentation masks and diffusion models.
Open-Higgsfield-AI is a generative AI content studio and visual workflow orchestrator. It provides a unified interface for creating photorealistic images and videos, utilizing a node-based editor to chain multiple image, video, and audio models into automated content pipelines. The system functions as an AI video animation tool and local GPU inference engine, allowing users to run generative models on local hardware or remote servers. It includes specialized capabilities for audio-driven lip synchronization and cinematic camera controls to adjust virtual lens and focal settings. The platform
Designs automated sequences of image, video, and audio models to create generative content.
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
Integrates a large language model to expand short user prompts into detailed descriptions to improve video generation quality.
StableStudio is a generative AI frontend and image interface designed for creating and editing visual content. It provides a web-based graphical interface that connects to generative AI models via API connections to facilitate image synthesis and modification. The project functions as a pluggable AI backend manager, using a modular system to standardize diverse AI provider APIs into a unified format. This architecture allows users to swap between different generative AI backends and providers to compare outputs and optimize production. The system manages long-running generation tasks through
Provides specialized workflows for image-to-image manipulation and AI-driven artistic refinement.
jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti
Builds retrieval-augmented generation pipelines and agentic AI applications using hosted API endpoints.
This repository provides a collection of reference implementations and code examples for training and deploying machine learning models using the MLX framework. It serves as a practical guide for executing distributed training, fine-tuning large language models, converting model weights, and implementing multimodal generative workflows. The project distinguishes itself through specialized examples for local hardware execution, featuring weight quantization to reduce memory usage and low-rank adaptation for parameter-efficient fine-tuning. It also includes scripts for transforming external mod
Provides sequences of automated steps for creating images, video, music, and text using diffusion models and transformers.
StabilityMatrix is a centralized installer and orchestrator for Stable Diffusion web interfaces and their dependencies. It functions as a generative AI workspace and portable runtime, providing a unified interface to install and update AI image generation packages within isolated environments to prevent global system conflicts. The project distinguishes itself through a shared model manager that imports, organizes, and shares checkpoints across different installations. It utilizes a central model repository and filesystem mapping to allow multiple packages to access the same large binary asse
Provides a workflow for creating visual assets via a dedicated interface and managed workspaces.
Rig is a framework for building large language model applications, featuring a multi-provider client and a workflow builder for retrieval-augmented generation systems. It serves as an orchestrator for creating autonomous agents that can maintain conversation state and execute complex tasks through custom prompting and plugins. The project provides standardized interfaces for both completion and embedding model providers, allowing for unified request and response patterns across different engines. It also includes a vector database integration layer that defines a common interface for indexing
Enables the design of automated sequences that produce multimedia content using various generative AI model capabilities.
This project is a containerized deployment for running Stable Diffusion web interfaces. It provides a portable runtime for generative AI that manages dependencies and hardware acceleration to enable text-to-image generation and image-to-image transformations via a browser-based interface. The system uses hardware-specific image tags to support both GPU-accelerated synthesis and CPU-only execution. It ensures environment isolation across different operating systems while utilizing bind-mount data persistence to keep heavy model weights and generated outputs on the host machine. The deployment
Implements a portable container setup for executing automated sequences of generative image refinement.
Civitai is a platform for generative media creation and AI model distribution. It provides a centralized service for producing images, videos, audio, and music, while serving as a repository where users can share, discover, and browse custom model weights and fine-tuned adaptations. The platform distinguishes itself through a provider-agnostic orchestration layer that manages multi-step generation pipelines and complex workflows across different backends. It integrates with autonomous AI agents and editors via the Model Context Protocol, allowing external tools to access generation pipelines
Manages complex generation pipelines by submitting and controlling raw configurations.
SkyReels-V2 is a video generation system that creates, extends, and refines video clips from text descriptions, images, or both. It operates as a diffusion-based video generation model that can produce videos of any duration by denoising frames sequentially, with each new frame conditioned on the ones that came before it. The system supports generating videos from scratch using text prompts, starting from a single image and producing subsequent frames, or constraining both the first and last frames to match user-provided images. What distinguishes SkyReels-V2 is its combination of infinite-le
Expands brief text descriptions into detailed prompts using a language model for better video alignment.
PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo
Expands a brief input into a comprehensive, structured prompt using one of several expansion strategies.
Baserow est une base de données relationnelle no-code et un constructeur d'applications qui permet aux utilisateurs de créer des tables de données structurées et des outils métier via une interface visuelle. Il fonctionne comme un backend de données API REST headless et un espace de travail de données auto-hébergé, fournissant une plateforme pour gérer des bases de données collaboratives tout en conservant un contrôle total sur la résidence des données. La plateforme intègre des modèles de langage étendus pour servir de plateforme de données alimentée par LLM, capable de générer des structures de base de données, du contenu d'enregistrement et des flux de travail techniques à partir du langage naturel. Elle agit également comme un serveur de protocole de contexte de modèle (Model Context Protocol), permettant aux agents IA distants d'interagir avec des enregistrements de base de données structurés par programmation. Au-delà de ses capacités fondamentales de base de données, le projet fournit des outils pour construire des portails externes de marque, des applications métier internes et des tableaux de bord interactifs. Il inclut un moteur d'automatisation piloté par les événements pour l'automatisation des processus métier et prend en charge une large gamme d'intégrations API, incluant les webhooks, le streaming d'événements WebSocket et la synchronisation de données tierces. Le logiciel est conçu pour l'hébergement sur infrastructure privée et le déploiement conteneurisé afin d'assurer la souveraineté et la sécurité des données.
Creates complete technical workflows and database architectures using natural language processing.
Ce projet est un générateur vidéo Stable Diffusion qui crée des images en mouvement en interpolant entre des prompts textuels au sein de l'espace latent d'un modèle génératif. Il fonctionne comme un outil pour la génération vidéo par IA et l'interpolation d'espace latent, transformant du texte descriptif en séquences visuelles. Le système permet spécifiquement des visuels audio-réactifs en synchronisant le taux d'interpolation d'image sur le rythme et la cadence d'un fichier audio. Il produit ces séquences via une génération vidéo par morphing, qui effectue une transition fluide entre différents prompts textuels. Le projet inclut une interface utilisateur graphique qui fournit une interface de contrôle basée sur le web pour gérer le workflow texte-vers-vidéo. Cela permet l'orchestration du processus génératif sans écrire de code de pipeline manuel.
Provides a text-to-video generation workflow that transforms descriptive prompts into moving imagery.
ComfyUI-Copilot is an AI-powered assistant and design tool for creating, optimizing, and automating node-based generative AI workflows within ComfyUI. It functions as an LLM workflow orchestrator that provides natural language guidance to help design and refine complex image and video generation pipelines. The system uses large language models to translate natural language prompts into structured node-based graph configurations. It incorporates state-aware prompt engineering and dynamic node mapping to ensure generated sequences match the specific requirements of the target AI nodes. The too
Creates and optimizes complex node-based sequences for automating generative image and video production.
HunyuanVideo-1.5 is a video generation foundation model and text-to-video diffusion framework. It utilizes a latent video diffusion model and a spatio-temporal transformer architecture to generate high-definition video sequences from text descriptions and images. The project enables cinematic camera control for directing pans and tilts and provides image-to-video animation capabilities. It supports visual style adaptation through low-rank adaptation tuning and uses a language model for prompt refinement to improve visual alignment. The model covers high-resolution video upscaling via a super
Enriches short user prompts into detailed descriptions using a large language model for better visual alignment.
Tune-A-Video est un framework de diffusion texte-à-vidéo conçu pour convertir des modèles de diffusion texte-à-image pré-entraînés en générateurs vidéo. Il utilise un mécanisme d'attention spatio-temporelle et un entraînement sur paire texte-vidéo unique pour permettre la synthèse de séquences en mouvement à partir d'invites textuelles. Le projet fournit des outils pour la personnalisation vidéo one-shot, permettant à un modèle d'être réglé sur une seule vidéo de référence pour préserver des personnages ou des styles artistiques spécifiques à travers de nouvelles générations. Il fonctionne également comme un éditeur vidéo qui modifie les sujets, les arrière-plans et les styles via le guidage par invite d'échantillonnage de bruit et l'inversion. Le framework couvre plusieurs domaines de capacité principaux, y compris l'extraction de guidage structurel pour préserver la mise en page et le mouvement des vidéos sources et la cohérence du contenu spatio-temporel pour garder les éléments visuels stables à travers les images. Ces processus permettent la synthèse vidéo personnalisée et la modification du contenu visuel via un échantillonnage guidé.
Synthesizes moving video sequences from textual prompts by repurposing image diffusion models.
OpenGpt est une plateforme d'orchestration d'agents et une interface multimodale conçue pour construire et déployer des personas IA spécialisés. Elle permet aux utilisateurs de créer des agents orientés vers des tâches avec des invites système personnalisées et des contraintes comportementales pour automatiser les flux de travail professionnels, créatifs et techniques. Le projet propose un flux de travail d'ingénierie de prompt qui transforme les entrées utilisateur simples en instructions structurées pour améliorer la précision du modèle. Il intègre la génération augmentée par récupération (RAG) en connectant des bases de données vectorielles à l'interface de chat, permettant des réponses contextuelles à partir de jeux de données privés. La plateforme couvre un large éventail de capacités, y compris l'analyse de données multimodales pour les PDF et l'audio, la gestion d'API multi-fournisseurs via des clés personnelles, et la génération de divers types de contenu tels que des documents professionnels, du code fonctionnel et des invites visuelles. Elle inclut également des outils pour l'analyse de contenu, les services de traduction et la gestion d'identité via Google OAuth.
Rewrites basic text descriptions into detailed prompt ideas for better visual alignment in image generators.