我個人認爲谷歌Veo3視頻模型是I/O大會中最大亮點，有當初OpenAI Sora亮相時的震撼。此前只開放給超貴的Ultra會員，本週末Gemini Pro會員也可以用了，好像一週限制10次，每次視頻長度是8秒，不支持上傳圖片輔助。隨便嘗試了幾個案例給大家分享，prompt是問Gemini 2.5Pro生成的。
以下是幾個案例（主要還是自己想象力不夠）：
雖然現階段追求效果的話還是需要抽卡，但通過簡單prompt one shot效果來看，谷歌Veo3模型要比快手可靈、字節即夢要好不少，尤其是配音、對口型這些稱得上SOTA，大家有機會可以多試試。OpenAI的Sora需要加把勁了，希望視頻模型繼續捲起來。
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.
Comments