👩🍳 How we use AI at Tech in Asia, thoughtfully and responsibly.
🧔♂️ A friendly human may check it before it goes live. More news here
🧔♂️ A friendly human may check it before it goes live. More news here
ByteDance unveils AI model OmniHuman-1 for lifelike videos
ByteDance has developed OmniHuman-1, an AI model that creates realistic videos of people speaking, singing, and moving from photos and sound.
A research paper revealed that OmniHuman-1 outperforms existing models in generating audio-conditioned human videos, often called “deepfakes.”
OmniHuman-1’s launch comes as AI competition intensifies, with OpenAI expanding its video tool, Sora, to more users.
These advancements unfold amid US efforts to limit China’s AI progress through ongoing restrictions.
Recent ByteDance developments
| Timeline |
|---|
26-Jan-2025 🎉 ByteDance ends Lunar New Year red packets, revamps benefits
|
25-Jan-2025 🧠 ByteDance joins artificial general intelligence race
|
24-Jan-2025 🇺🇸 ByteDance considers no-sale option for TikTok in US
|
24-Jan-2025 💰 ByteDance said to invest $20b in AI infrastructure globally
|
23-Jan-2025 🤖 ByteDance launches AI model Doubao 1.5 Pro
|
Stay updated on the go with our mobile app.
Get latest insights with smoother, more personalized experience through TIA mobile app.