註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Taesung Park
@Taesung
training visual generative models @reve. ex-@AdobeResearch. Ph.D. @berkeley_ai, BS @Stanford
加入 March 2009
178 正在關注    1.4K 粉絲
Competing with model giants with 10x more resources, how did we do it? Introducing Unified Layout Models. We designed a new structured data format for images, based on hierarchical region conditioning. We call this "layouts". Think of it as SVG for pixels.
顯示更多
0
12
338
33
轉發到社區