News for hackers. Stuff that matters.
Re:MIT Unveils Gen AI Tool That Generates High Res Images 30... by samus on Wednesday March 27, 2024 @07:18AM (#39837652)
A lot of the problems of Stable Diffusion arise because of using a text encoder that isn't up to the task to encode the meaning sufficiently precise. For example, if you mention the word "green" in the prompt, it often carries over to the whole image instead of the object that is being described. Numbers suffer from a similar problem. Rendering text is compromised by tokenization.

One problem with hands might be that they are comparatively small. The model easily gets the big picture right (head, arms, legs), but hands are so-called high-frequency details and are additionally featured in lots of different positions, which are seldom sufficiently described in the captions of the training data.

There are no comments on this comment yet.