Stable Diffusion web UI

Robust Speech Recognition via Large-Scale Weak Supervision

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Deezer source separation library including pretrained models.

We write your reusable computer vision tools. 💜

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

OCR, layout analysis, reading order, line detection in 90+ languages

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

DUSt3R: Geometric 3D Vision Made Easy

A tiny script to issue and renew TLS certs from Let's Encrypt

Handwriting Synthesis with RNNs ✏️

Access large language models from the command-line

DreamUV - 3D viewport UV editing tools for Blender

Print XML formated receipts on ESC/POS printers, in Python.

Codename generator using WordNet parts of speech database

Implementation of A. Efros and T. Leung, 'Texture Synthesis by Non-parametric Sampling' (1999)