#generative-ai Repositories
791 repositories total
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
Large Model Fundamentals: Understand Large Model Fundamentals in One Article
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.
LLM-Driven Extraction of Unstructured Data โ Built for API Deployments & ETL Pipeline Workflows
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic ๐ช: Generative-AI (AIGC), easy-to-use APIs, awesome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
AI Agent Skill (Claude Code, Codex & more): Turn any script into animated stickman videos for faceless YouTube, Shorts & TikTok. 14+ styles with voiceover, captions & SFX. Free & open-source (MIT).
A general-purpose AIGC video engine: script to finished film in one pipeline โ dramas, ads, product videos, otome games, and more.
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.
[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"
Remove visible and invisible AI watermarks from images and video, and AI provenance metadata from images, video, and audio. Python library, CLI, and agent skill for SynthID, C2PA, EXIF, IPTC, XMP, and common generative-AI marks. By Victor Kuznetsov.
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person
An AI-powered data science team of agents to help you perform common data science tasks 10X faster.
Developed by Turing's Cat, the first generation of creative AI, based on open-source GPT2.0 | Scalable, evolvable
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
Curated list of the best truly open-source AI projects, models, tools, and infrastructure. Daily updated.
Open-source AI red teaming toolkit from Microsoft. Test generative AI systems with automated scans, adaptive multi-turn attacks, and a web UI.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
This is a step-by-step guide to getting started with AI/LLM large models, including tutorials and demo code. It takes you from APIs to local large model deployment and fine-tuning. The code files will be provided in online versions for Kaggle or Colab, allowing you to learn even without a graphics card. The project also features a small code playground ๐ก where you can experiment with interesting AI scripts. Simultaneously, it includes a complete Chinese mirrored version of the assignments from Hung-Yi Lee's (HUNG-YI LEE) 2024 Introduction to Generative AI course.
Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms โ from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems