请问HN：哪些突破性进展解决了AI生成的手部和文本问题？
图像生成模型有所改进，但我对其“如何”实现这一点感到困惑。请帮我理清思路。有没有相关的出版物或文章介绍这两个曾经困难的问题是如何解决的？
查看原文
Image generation models improved, but I missed the boat on <i>how</i>. Help me connect the dots. Any relevant publications or writeups on how these two former difficult problems were solved?