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

deep learning for image processing including classification and object-detection etc.

DALL·E Mini - Generate images from a text prompt

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"

适用于 GPT-SoVITS 的api调用接口

Implementation of the D8 algorithm, a lake identification and flow algorithm with python and matplotlib

Image and text generation video（图文生成视频）

The mHM basin extractor.

The well-known D8 algorithm is the most commonly used method for approximating flow directions on a topographic surface, and this method tracks "flow" from each pixel to one of its eight neighbor p…

Clip video (and audio from video) by matching dialogue from a subtitle (SRT) file.