AI Agent Skills

[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

An unofficial PyTorch implementation of the audio LM VALL-E

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

React Native binding of whisper.cpp.

MARS5 speech model (TTS) from CAMB.AI

Audio Plugin for Audio to MIDI transcription using deep learning.

Video Processing in Python

Automatically remove the mosaics in images and videos, or add mosaics to them.

MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Golang framework to build an AI that can understand and speak back to you, and everything else you want