Radar

Convert 2D videos to 3D VR format using AI depth estimation.

A live 3D intelligence console for planet Earth.

HWIDGEN

generate a video from an image with a text prompt

generate a video from an image with a text prompt

Penpot: The open-source design platform for Product teams that need scalable collaboration.

A coding agent for open models like Kimi K3

Flask-based web UI for AI image/video generation, chat, and text-to-speech with queue management and multi-theme system

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

[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

A tool that takes a text document containing a book or a novel, ingests it with an LLM to produce an annotated script, and then uses a TTS API to generate the voice lines, finally stitching them together into an audiobook in MP3 format.

Run FP8 models on Apple Silicon / MPS in ComfyUI. Compatibility layer for ComfyUI on Apple Silicon.

Playground Web UI using segment-anything-2 models from the Meta.

Automapper for Beat Saber songs, using Python, Machine Learning and hundreds of user-created maps from the past years.

Fast stable diffusion on CPU and AI PC

llama.cpp with BakLLaVA model describes what does it see (https://github.com/Fuzzy-Search/realtime-bakllava)

Real-time space launch tracker with live countdown, mission details, rocket information and launch updates.

QualityScaler - image/video AI upscaler app

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

MiniCPM5: SOTA on-device LLMs, small yet powerful.