在全球人工智能技术的浪潮中，Adobe公司正积极投身于文生视频领域的竞争。据财联社报道，Adobe近期加快了构建其人工智能视频生成模型的步伐，以应对OpenAI的文生视频模型Sora所引发的市场热潮。该公司计划以每分钟3美元的价格购买大量的视频资源，旨在打造一款能够根据文本生成逼真视频的AI模型。
为了积累必要的训练素材，Adobe正向其广泛的摄影师和艺术家网络伸出橄榄枝。根据一份内部文件，Adobe将向每位参与者支付120美元，以换取他们拍摄的日常活动视频，如行走、表达各种情绪如喜悦和愤怒等。这些多样化的视频内容将为Adobe的AI模型提供丰富的学习样本，以提升其在生成人类行为和情感表现方面的准确性。
Adobe的这一举措展示了其在创意软件领域的持续创新力，也预示着未来文本到视频的转化技术可能迎来重大突破。随着AI技术的不断进步，此类模型有望在娱乐、教育、广告等多个领域产生深远影响，改变人们创造和消费多媒体内容的方式。
英语如下：
News Title: “Adobe Accelerates AI-Generated Video Push, Procuring Resources at $3/Minute to Rival OpenAI’s Sora Model”
Keywords: Adobe, generated video, AI model
News Content: Amid the global surge in artificial intelligence technology, Adobe is vigorously engaging in the competition within the AI-generated video domain. According to Cailian Press, the company has recently stepped up its efforts to develop its AI video generation model in response to the market buzz generated by OpenAI’s text-to-video model, Sora. Adobe intends to acquire a vast amount of video resources at a rate of $3 per minute to create an AI model capable of producing realistic videos based on text input.
To accumulate the necessary training materials, Adobe is reaching out to its extensive network of photographers and artists. An internal document reveals that Adobe will compensate each participant with $120 for their videos capturing everyday activities, such as walking, expressing various emotions like joy and anger. This diverse array of video content will provide ample learning samples for Adobe’s AI model, enhancing its accuracy in generating human behaviors and emotional expressions.
This move by Adobe underscores its ongoing innovation in the creative software arena and foreshadows significant breakthroughs in the future of text-to-video conversion technology. As AI advancements continue, such models are expected to have a profound impact on industries like entertainment, education, and advertising, transforming the way people create and consume multimedia content.
【来源】https://www.cls.cn/detail/1643286
Views: 1