Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
- controllable-generation
- foundation-models
- image-generation
- text-rendering
47,133 repositories indexed
1,561–1,584 of 5,590 · Most stars
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
Python library and CLI tool to interface with Google Translate's text-to-speech API
wxPython's Project Phoenix. A new implementation of wxPython, better, stronger, faster than he was before.
CodeChecker is an analyzer tooling, defect database and viewer extension for static and dynamic analyzer tools.
A package which efficiently applies any function to a pandas dataframe or series in the fastest available manner
A WeeChat script for Slack.com. Supports threads and reactions, synchronizes read markers, provides typing notification, etc..
A curated list of awesome MySQL software, libraries, tools and resources
Run MapReduce jobs on Hadoop or Amazon Web Services
Phishing Campaign Toolkit
Fava - web interface for Beancount
Version controlled file system
Load and performance benchmark tool
Python library for portfolio optimization, factor model construction, and risk management built on scikit-learn
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning
Rasterio reads and writes geospatial raster datasets
Bitcoin arbitrage - opportunity detector
git-cola: The highly caffeinated Git GUI
:bar_chart: Save matplotlib figures as TikZ/PGFplots for smooth integration into LaTeX.
Malcolm is a powerful, easily deployable network traffic analysis tool suite for full packet capture artifacts (PCAP files), Zeek logs and Suricata alerts.
PyGraphistry is a Python library to quickly load, shape, embed, and explore big graphs with the GPU-accelerated Graphistry visual graph analyzer
Please no pull requests for this repository. Thanks!
A cross platform Bluetooth Low Energy Client for Python using asyncio
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
High level asynchronous concurrency and networking framework that works on top of either Trio or asyncio