Media2Face: Text To Speech 3D Face
Media2Face is able to generate speech-synchronized, expressive 3D facial animations…
AI project
Robotics is about to have its ChatGPT moment
Robot startup @Figure_robot released a video Their Figure-01 robot can…
OpenAI and Microsoft are in talks to support humanoid robot company Figure
The report revealed that OpenAI and Microsoft are in financing…
Meta releases new programming aid model: CodeLlama70B
CodeLlama-70B-Instruct scored 67.8 on HumanEval, making it one of the…
Musk Human Interface Neuralink related videos
Imagine the joyous experience of being able to communicate with…
This year artificial intelligence infrastructure will be divided into two markets: LLM and diffusion models
Forecast: This year artificial intelligence infrastructure will be divided into…
TeslaRoadster Virtual Experience
Interesting to generate a title screen for the virtual #tesla…
Bard and GeminiPro surpass GPT-4 at Arena
Combine it with Google Sheets to automate data processing. Shows…
Artificial intelligence ads, they’re about to be big
A play, an action comedy, a documentary and a music…
Adept Fuyu-Heavy is a new multi-modality model designed for digital agents
Claimed to be the third most capable Multi-modality model in…
Japanese Generation Artist Liber @liberxx0
His works have a very strong personal character and aesthetic,…
Lumiere: Generate the entire video at once
Spatial-temporal text-to-video diffusion model developed by the Google Research team….