每日读则推(十四)——Meta Movie Gen: the most advanced media foundation models to-date

                       premiere n.首映,首次公演 v.首次公演(戏剧、音乐、电影) a.首要的,最早的
  Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. 
迄今,到现在为止
                                                                                        a.先进的;高级的,高等的;晚期的,状况不佳的;高龄的  advance v.(使)前进,(使)向前移动;发展,进步;预付;提前,提早;促进,推动;提出(想法或理论);上涨,增加;提拔,晋升 n.前进;进步,进展;改善;预付款;勾引,追求;(价格、价值的)上涨;贷款 a.预先的,事先的;先行的,先遣的

  v.开发;发展                                                                        v.投递,运送;接生,分娩;发表,宣布(这里是提供)
  Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results
                                                                                                          a.最先进的;已经发展的;达到最高水准的                capability n.能力,才能;功能,计算机性能
across a range of capabilities. We’re excited for the potential of this line of research to
ad.从一边到另一边;在……对面 prep.从一边到另一边;横过,穿过,跨越(政治、宗教、社会隔阂等)
               n.(变动或浮动的)范围,界限;视觉(或听觉)范围;一系列 v.(在一定的范围内)变化,变动;(按一定位置或顺序)排列,排序                          a.(这里是 业余的)休闲的;非正式的;马虎的
usher in entirely new possibilities for casual creators and creative professionals alike.
n.引座员,迎宾员 v.引导,引领,开创(usher sth. in)                       创意专业人士
               全新的可能性

More details and examples of what Movie Gen can do：
https://ai.meta.com/research/movie-gen/?utm_source=twitter&utm_medium=organic_social&utm_content=video&utm_campaign=moviegen

Movie Gen models and capabilities：
Movie Gen Video: 30B parameter transformer model(30B 参数转换器模型) that can generate high-quality and high-definition images and videos from a single text prompt.
                                                                                                                       v.促使,导致;鼓励;提示(说话者);(计算机上;提示;(给演员)提词,提白 n.(给演员的)提词;(计算机屏幕上显示准备接受指令的)提示;鼓励 a.迅速的,立刻的 ad.准时地

                                                                                                                                              以及
  Movie Gen Audio: A 13B parameter transformer model that can take a video input along
                                                                                                         n.保真   a.声音的,音频的 n.声音,音频                                                                                                                     n/v.同时,同步 
with optional text prompts for controllability to generate high-fidelity audio synced to the
        a.可选择的,选修的               n.可控性;可控制性(controllable a.可控制的;可管理的;能操纵的)                                        a.环境的,周围的                     
video. It can generate ambient sound, instrumental background music and foley sound—
                                                                 a.与乐器有关的;有作用的                       拟音
v.投递,运送;接生,分娩;发表,宣布(这里是提供)
delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-
                                                                                      视频到音频       n.对齐;结盟
audio alignment.                     

  Precise video editing: Using a generated or existing video and accompanying text
  a.精确的,准确的;(人)严格的,一丝不苟的                                             v.陪伴,陪同;伴随,与……一起发生;为……伴奏(或伴唱);附带,补充
instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes.

  Personalized videos: Using an image of a person and a text prompt, the model can
  vt.使个性化;把……拟人化
generate a video with state-of-the-art results on character preservation and natural
                                                                                                    n.保护,维护;保留,维持
movement in video.
n.移动,转移

  We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to
                         n.反馈意见
sharing more on this work and the creative possibilities it will enable in the future.

Article-link：
https://x.com/AIatMeta/status/1842188252541043075