Global radar

A full-scale college management portal with an integrated AI assistant (AIRA) and automated WhatsApp parent notifications.

MiniMax H3 video studio with a local NVIDIA CUDA backend or a managed Runpod cloud GPU.

X-Voice is a multilingual text-to-speech system that enables one speaker to speak 27 languages.

Pixel-space PRX text-to-image pipeline (~7B params, Qwen3-VL text encoder, no VAE)

Imposing Consistent Light - Control lighting of images

Clone de voz multilíngue usando Coqui TTS

Bulk image resizer for Stable Diffusion training datasets with JoyCaption AI captioning.

Generating Consistent Long Depth Sequences for Open-world Videos

[NVIDIA ONLY] End-to-end multimodal SVG generator capable of generating complex and detailed SVGs, from simple icons to intricate anime characters. (Minimum Requirements 12GB VRAM / 32GB RAM, Recommended Requirements 24GB VRAM / 24GB RAM)

[NVIDIA GPU required] Unified S^3 fields for animatable 3D asset generation from a single image. 6GB VRAM needed (Low VRAM option)

[NVIDIA Only] Dead simple web UI for training FLUX LoRA with LOW VRAM support (From 12GB)

Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

Automatically remove watermarks from videos generated by Sora AI.

Pinned, privacy-conscious Pinokio launcher for SUPIR photo restoration.

AI-powered speech denoising + enhancement (Gradio web demo + CLI).

One-click 3D Gaussian Splatting generation from a single image.

Self-hosted AI assistant with task-scoped approvals and a deterministic permission kernel. Bring your own model. macOS and Linux. Alpha.

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

A live 3D intelligence console for planet Earth.