Explore projects

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

SkyReels-A2: Compose anything in video diffusion transformers

The best OSS video generation models

Specify what you want it to build, the AI asks for clarification, and then builds it.

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.

A pattern for an always on AI Assistant powered by Deepseek-V3, RealtimeSTT, and Typer for engineering

⛴️ Docker image of Nextcloud

Python notebook to generate QR codes with LinkedIn and GitHub logos

24/7 Customer Service for your website

🎧☁️ Your Personal Streaming Service

Jarvis is a voice-activated, conversational AI assistant powered by a local LLM (Qwen via Ollama). It listens for a wake word, processes spoken commands using a local language model with LangChain, and responds out loud via TTS. It supports tool-calling for dynamic functions like checking the current time.

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Foundational model for human-like, expressive TTS

A simple, modular seedbox solution

Home of the DSub Android client fork