Vidu: A model that can generate 16-second, 1080P video
This model is regarded as the first video model in…
Multimedia processing
SpeechAlign: Use human feedback to change Text To Speech to enhance the naturalness and expressiveness of technical interactions
A research team at Fudan University has developed SpeechAlign, an…
The Open Sora team has released another video generation project, MagicTime
A set of technology called MagicAdapter has been developed that…
SAM Model Video Segmentation Project
The goal of this project is motion segmentation-discovering and segmenting…
NoLang: Enter any theme or web link to directly generate a video
It supports direct conversion of text, web links, PDFs, questions,…
VoiceCraft: A voice model that outpaces XTTS
Supports cloning audio and editing audio by modifying the text…
FRESCO is a video transfer project
The code for FRESCO, a video rendering project, has been…
Gatekeep: A new type of text-to-video AI that focuses on teaching
It can convert mathematics and physics problems into video content…
Google has also created a project where a photo + audio can generate a talking and singing video
Google has also created a project where a photo +…
Optimizer AI: An AI tool specifically designed to automatically generate sound effects for videos can automatically dub AI videos
Ability to create sounds and sound effects that are suitable…
ChatGPT voice reading function starts gray scale testing
Set up the voice and click the Play button to…
![Pika launches LipSync [lip sync] function](https://raw.githubusercontent.com/tarogoing/tarogo-image-galaxy/master/2024/03/Pika-Lip-Syncing.png)
Pika launches LipSync [lip sync] function
Lip Sync can synchronize the mouth animation and audio of…