Apps

Generating Consistent Long Depth Sequences for Open-world Videos

🔊 Generate high-quality, realistic speech with LuxTTS, a lightweight text-to-speech model for fast voice cloning and clear audio output.

Minecraft AI with LLMs+Mineflayer

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

Local AI Auto-Rigging for 3D Models

This Model Through Trip Generation uses socio-economic data to estimate zonal trip totals. Trip Distribution connects origins to destinations via a gravity model. Mode Choice splits person-trips into vehicle trips (PCE). Traffic Assignment loads these onto the network, iterating to equilibrium to yield link volumes and V/C ratios for design.

Contribute to JustinDoan/Ideogram-UI development by creating an account on GitHub.

Local AI Auto-Rigging

Ideogrammar — Ideogram 4 Prompt Editor A single-file, no-build web app for composing structured Ideogram 4 prompts.

A Git extension for tracking the AI-generated code in your repos

Upload an image and use a mask or click to specify areas to retain or change. Provide a prompt to generate new content for the edited areas. The application then outputs the modified images.

A fully self-contained, offline AI image generation studio for Windows. Runs Stable Diffusion (Safetensors/GGUF) locally with zero manual setup. Auto-configures CUDA for Nvidia GPUs and Vulkan for AMD/Intel Arc cards. Zero system-wide dependencies required.

Hermes Agent with modern WebUI (nesquena/hermes-webui). Persistent memory, multi-provider AI (OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter), scheduled cron jobs, skills, and sessions. Three-panel interface with chat, tasks, memory, and workspace browser. https://github.com/nesquena/hermes-webui

A Web UI for easy subtitle using whisperx model based on whisper-webui by jhj0517.

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Text-to-Speech for 16 Indian languages: Assamese, Bengali, Bodo, English (Indian accent), Hinglish, Gujarati, Hindi, Kannada, Malayalam, Manipuri, Marathi, Odia, Punjabi, Rajasthani, Tamil, and Telugu. SOTA models based on FastPitch and HiFi-GAN V1.

Contribute to TomClive/SeeDance2Stitcher development by creating an account on GitHub.

Platform otomasi video pendek berbasis AI untuk mengubah video YouTube panjang menjadi klip vertikal (9:16) maupun horizontal otomatis dengan fitur robust face tracking (MediaPipe/OpenCV) dan dynamic subtitle burn-in bergaya viral.

Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.