linzai1992

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

llama3

The official Meta Llama 3 GitHub site

reflex

🕸️ Web apps in pure Python 🐍

bilibili-API-collect

哔哩哔哩-API收集整理【不断更新中....】

VoiceCraft

Zero-Shot Speech Editing and Text-to-Speech in the Wild

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

img2dataset

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

torchtune

A Native-PyTorch Library for LLM Fine-tuning

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

aiXcoder-7B

official repository of aiXcoder-7B Code Large Language Model

StableSR

Exploiting Diffusion Prior for Real-World Image Super-Resolution

XNNPACK

High-efficiency floating-point neural network inference operators for mobile, server, and Web

Realtime_PyAudio_FFT

Realtime audio analysis in Python, using PyAudio and Numpy to extract and visualize FFT features from streaming audio.

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Matcha-TTS

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

scrapetube

A YouTube scraper for scraping channels, playlists, and searching 🔎

StableTTS

Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3

VoiceFlow-TTS

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

dataspeech

Awesome-LLM-related-Papers-Comprehensive-Topics

Awesome LLM-related papers and repos on very comprehensive topics.

shutterscrape

Web scrapper for Shutterstock

VideoRecap

EnCLAP

Official Implementation of EnCLAP

ppgs

High-Fidelity Neural Phonetic Posteriorgrams

Open-Sora-Dataset

HQ-Edit

HQ-Edit: A High-Quality and High-Coverage Dataset for General Image Editing

audio-pipeline

Defuzers

Image generation UI for diffusers.