kynthesis
Follow
Stars
A professional video compression tool accessible to all, mostly based on FFmpeg.
A python module to repair invalid JSON, commonly used to parse the output of LLMs
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
🔥 A Complete List of GitHub Profile Badges and Achievements 🔥
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
A lightweight library that leverages Language Models (LLMs) to enable natural language interactions, allowing you to source and converse with data.
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.
Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Semantic-Aware Discriminator for Image Super-Resolution
Repository to demonstrate Chain of Table reasoning with multiple tables powered by LangGraph
Handy image viewer based on PyQt5. Convenient for viewing and comparing :-)
APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)
Official Implementation of VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data (WACV 2024)
neosr is a framework for training real-world single-image super-resolution networks.
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
My VitePress website I made to visually compare the output I created with over 600 different AI upscaling models. Running under https://phhofm.github.io/upscale/
PyTorch code for our ICLR 2024 paper "Recursive Generalization Transformer for Image Super-Resolution"
This is a simple text image blind super-resolution model, using BSRGAN
This is official implementtaion of "VmambaIR: Visual State Space Model for Image Restoration"
Learning Generative Structure Prior for Blind Text Image Super-resolution [CVPR 2023]
An unofficial C#/.NET SDK for accessing the Mistral AI API
MobiLlama : Small Language Model tailored for edge devices
Drag & drop UI to build your customized LLM flow
Codes for VPGTrans: Transfer Visual Prompt Generator across LLMs. VL-LLaMA, VL-Vicuna.