Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

0

近日,有媒体报道称,字节跳动已推出一款名为Boximator的颠覆性视频模型,该模型能通过文本精准控制生成视频中的人物或物体动作,引发业界广泛关注。然而,针对这一消息,字节跳动官方迅速辟谣,表示Boximator目前仅是一个视频生成领域的技术研究项目,尚未达到完善的产品形态。

据字节跳动相关人士透露,Boximator确实在探索如何更精确地控制视频内容中对象的运动,但这一技术目前仍处于研发阶段,存在诸多技术挑战。他们指出,与市面上的Gen-2、Pink1.0等视频模型相比,Boximator在画面质量、保真度以及视频时长等方面还存在显著差距,因此,目前无法将其作为成熟产品推向市场。

字节跳动的这一回应,明确了Boximator的技术现状,同时也显示出公司在视频生成技术领域的谨慎态度。尽管如此,Boximator的技术理念,即通过文本指令控制视频内容,无疑预示着未来视频创作可能迎来的革新。字节跳动将继续致力于此类前沿技术的研发,以期在未来能推出更先进的产品,满足用户在视频创作和消费上的新需求。

来源:新浪科技

英语如下:

News Title: “ByteDance Denies Launch of Chinese Version of Sora: Boximator Remains in R&D Stage, Not a Mature Product”

Keywords: ByteDance, Boximator, Video Generation

News Content:

Title: ByteDance Addresses Boximator Development: Currently in Technological Research, Not a Fully-Fledged Product

Recently, reports emerged that ByteDance had introduced a groundbreaking video model named Boximator, capable of precisely controlling the actions of characters or objects in videos through text input, drawing extensive attention from the industry. However, the company promptly debunked these claims, stating that Boximator is currently an ongoing research project in the field of video generation and has not yet matured into a complete product.

According to sources within ByteDance, Boximator is indeed exploring more accurate control over object motion in video content. Nevertheless, the technology is still in the developmental stage, with numerous technical challenges yet to be overcome. They highlighted that compared to existing video models such as Gen-2 and Pink1.0, Boximator lags behind in terms of image quality, fidelity, and video duration, rendering it unsuitable for commercial release at this time.

ByteDance’s clarification on Boximator’s current status underscores the company’s cautious approach in the video generation technology domain. Despite this, the concept behind Boximator—controlling video content via text instructions—foreshadows potential innovations in future video creation. The company remains committed to advancing such cutting-edge technologies, aiming to introduce more advanced products in the future to cater to evolving user demands in video creation and consumption.

Source: Sina Tech

【来源】https://finance.sina.com.cn/tech/shenji/2024-02-20/doc-inairynk7158099.shtml

Views: 1

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注