🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

NextFlow🚀: Unified Sequential Modeling Activates Multimodal Understanding and Generation

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

The Context Graph Factory for AI. Build, manage, and deploy AI-optimized Context Graphs.

We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

手搓Agent系列，香蕉Pro邪修应用和gemini本地化部署

Learning on the Job: An Experience-Driven, Self-Evolving Agent for Long-Horizon Tasks

Official project page for "From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing" (X-Dub).

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation,…

HY-Motion model for 3D character animation generation.

Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.

Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.

AI Word协同文档SDK

SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.

BuildingAI is an enterprise-grade open-source intelligent agent platform designed for AI developers, AI entrepreneurs, and forward-thinking organizations. Through a visual configuration interface (…

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

PersonaLive! : Expressive Portrait Image Animation for Live Streaming

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

SDPose-OOD的comfyui节点。implementation of SDPose-OOD in ComfyUI

[AAAI 2026] Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback

MotionGPT3: Human Motion as a Second Modality, a MoT-based framework for unified motion understanding and generation

✨ WithAnyone is capable of generating high-quality, controllable, and ID consistent images

Lumos-Custom Project: research for customized video generation in the Lumos Project.

Diagram-as-code for AWS architecture.

Mixture-of-Groups Attention for End-to-End Long Video Generation