Jan 27, 2024 · ByteDance, the parent company of the popular social media platform TikTok, has discreetly unveiled four new AI applications designed for users outside of China.

Jan 29, 2025 · Bytedance * Equal contribution, † Project lead Paper Page TL;DR : We propose an end-to-end multimodality-conditioned human video generation framework named OmniHuman, which can generate human videos based on a single human image and motion signals (e.g., audio only, video only, or a combination of audio and video).

4 days ago · The Chinese tech giant behind TikTok has quietly unveiled an advanced AI model for generating video that raises new concerns about the threat of deepfake content. ... ByteDance's OmniHuman-1 model ...

Jan 22, 2025 · TikTok owner ByteDance on Wednesday released an update to its flagship AI model as a global race intensified to create AI models capable of tackling complex problems.

6 days ago · ByteDance researchers have developed an AI system that transforms single photographs into realistic videos of people speaking, singing and moving naturally — a breakthrough that could reshape...

Jan 22, 2025 · TikTok owner ByteDance on Wednesday released an update to its flagship AI model aimed at challenging Microsoft-backed OpenAI ’s latest reasoning model products, as a global race intensified to...

4 days ago · ByteDance, the parent company of TikTok, has introduced a new artificial intelligence model called OmniHuman-1. This model is designed to generate realistic videos using photos and sound clips. The development follows OpenAI's decision to expand access to its video-generation tool, Sora, for ChatGPT ...

Sep 30, 2024 · TikTok's Chinese parent ByteDance plans to develop an AI model trained primarily with chips from compatriot Huawei Technologies (HWT.UL), said three people familiar with the matter, as U.S....