Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
- Linzhan Mou2.1k
UniMate
Text-driven motion generation model for characters with any skeleton
- 2.6k
Stable Video Infinity
Research code and weights for generating very long videos without drift
- 4.2k
MOSS-TTS
Open speech and sound model family for TTS, dialogue, and effects
6.2k
- 8.2k
TabPFN
Pretrained transformer for classification and regression on tables
pliny8.9k
- 8.4k
MiroThinker
Open-weight deep research agent models with a tool-using search framework
- 9.9k
Pocket TTS
Small CPU-only text-to-speech model with voice cloning and streaming
- 9.3k
MobileAgent
GUI agent models and frameworks that operate phones, desktops, and browsers
- 12.4k
YuE
Open music generation model that plans a score, then sings the song
- 12.5k
Chandra OCR
OCR model converting scanned pages and PDFs into layout-aware Markdown
- 14.1k
Needle
Tiny on-device model for tool calls, extraction and speech input
- 2.8k
LongLive
NVIDIA research code for long video generation and robot world models
- 18.2k
LingBot-Map
Feed-forward transformer that rebuilds 3D scenes from streaming video
- 7.7k
WeatherNext
Google DeepMind's AI models for global weather and cyclone forecasting
- 9.4k
Sana
Linear diffusion transformer models for fast image and video generation
39.6k
62.7k
- 91.4k
PaddleOCR
OCR toolkit that converts scanned pages and photos to Markdown or JSON
- 27.1k
Chatterbox TTS
Open text-to-speech models with zero-shot voice cloning in 23+ languages
- 26.9k
MiniCPM-V
Open multimodal models for images, video, documents and speech on-device
- 19.8k
olmOCR
PDF and image-to-Markdown converter built on a 7B vision-language model
ShiYu42.1k
- 12.3k
TRELLIS.2
4B-parameter model that turns a single image into a textured 3D asset