A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputatio…

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Reference implementation for DPO (Direct Preference Optimization)

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

A generative speech model for daily dialogue.

中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

AnimateDiff for AUTOMATIC1111 Stable Diffusion WebUI

Real time streaming talking head

IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …

so-vits-svc fork with realtime support, improved interface and more features.

A repository of models, textual inversions, and more

Real time interactive streaming digital human

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

WebUI extension for ControlNet

Fast Example-based Image Synthesis and Style Transfer

Open-Sora: Democratizing Efficient Video Production for All

Labeling extension for Automatic1111's Web UI

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

Stable Diffusion web UI

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

AI chat for every model.

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Bark Voice Cloning and Voice Cloning for Chinese Speech

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Vocal Remover using Deep Neural Networks

GUI for a Vocal Remover that uses Deep Neural Networks.

an extremely simple tool for separating vocals and background music, completely localized for web operation, using 2stems/4stems/5stems models 这是一个极简的人声和背景音乐分离工具，本地化网页操作，无需连接外网

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions