PixelPlayer: Project developed by the MIT research team
Different sound sources can be automatically identified and separated from…
Open source projects
UFO: UI agent developed by Microsoft focused on Windows operating system interaction
It can automatically perform a series of complex tasks by…
OS-Copilot: Ability to interact with the operating system (OS)
An intelligent agent framework that performs a wide range of…
YOLO-World: A real-time target Detection Tools developed by Tencent AI Laboratory
It can automatically identify and locate various objects in the…
Anything in Any Scene: Seamless insertion of any object into existing motion videos
1. Accurate placement of objects: Ensure that the position of…
MetaVoice-1B: A highly realistic and natural text-to-speech (TTS) conversion model
The model has 120 million parameters and has been trained…
ChatGPT shell open source program
Provide a one-stop guide covering FAQs and basic strategies to…
The concept of GEO: Generative engine optimization
Impression metrics specifically for the generation engine! Experiments have shown…
M2UGen: A multimodal music understanding and generation model
M2UGen can understand a variety of music, including styles, instruments…
Pile: An open-source AI diary software with a very clean and beautiful interface
It can help you write and save diary entries, record…
OpenVoice: Versatile instant voice cloning
Developed by MyShell TTS. It is capable of replicating the…
SSR-Encoder: Extracts key features from images to generate new images
SSR-Encoder is capable of extracting a variety of features from…