Global radar

Enjoy the magic of Diffusion models!

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Optimized implementation of Qwen3-TTS for Apple Silicon (M1-M4)

Clawdbot完整配置指南：从安装到Claude Code中转

JJYB_AI 智剪 - 智能视频自动剪辑与AI解说工具（离线TTS、原创解说、混剪、AI配音）

✨ Open-source AI hackers for your apps 👨🏻‍💻

Search the web and your self-hosted apps using local AI agents.

Upload a low-resolution image, adjust the upscale factor and other settings, and get a high-resolution version of your image as output.

The official code of Yume

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

An open-source OpusClip alternative

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

generate a video from an image with a text prompt

The world’s fastest framework for building websites.

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025)

Aplikasi ini digunakan untuk menghasilkan suara berbasis teks dengan berbagai pilihan pembicara. Teknologi yang digunakan meliputi model text-to-speech (TTS) yang canggih dengan konversi teks ke fonem. Model yang dipakai dilatih khusus untuk bahasa Indonesia, Jawa dan Sunda.

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.