Setup and customize deep learning environment in seconds.
- deep-learning
- jupyter
- lasagne
- caffe
Repository Index
83,087 visible repositories in the index
1,729–1,752 of 11,565 · Most stars
Taming Stable Diffusion for Lip Sync!
- research
- diffusion-models
- lipsync
- video-gen
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
- deep-neural-networks
- deep-learning
- object-detection
- anchor-free
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
- audio
- machine-learning
- signal-processing
- audio-data
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Ready-to-use and customizable users management for FastAPI
- python
- starlette
- fastapi
- async
An Efficient ProxyPool with Getter, Tester and Server
TranslatedExtremely lightweight | Stops defensive writing in papers | Anti-defensive writing for academic papers — 学术写作原则 Skill + prompt pack (CN/EN)
- academic-writing
- ai-writing
- claude-skill
- paper-writing
a script to run docker-compose.yml using podman
- podman
- docker-compose
- linux-containers
- rootless-containers
Main reference implementation for NLWeb, implemented in Python.
Fara1.5 – A family of frontier computer use agent models
- agent
- browser-use
- computer-use
- computer-use-agent
Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations
TranslatedAutomatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. Integration for connecting Xiaomi Mijia smart home devices to Hass
- xiaomi
- miio
- miot
- home-assistant
DFlash: Block Diffusion for Flash Speculative Decoding
SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
- dreambooth
- finetune
- lora
- stable-diffusion
Generate audiobooks from EPUBs, PDFs and text with synchronized captions.
- audiobook
- audiobooks
- content-creation
- content-creator
curl statistics made simple
Open-source unified multimodal model
TranslatedMusic tag editor that can edit the metadata of local music files, and scrape music information. (Editable local music file metadata.)
- music-tag
- navidrome
- mp3tag
- music
an ambient intelligence library
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.
- agent
- agentic-ai
- agentic-framework
- agentic-rag
XLNet: Generalized Autoregressive Pretraining for Language Understanding