Divide & Bind technique for generative image models
Divide & Bind technique for generative image models
sites.google.com Divide & Bind
Our Divide & Bind can significantly improve a pretrained text-to-image model, faithfully generate multiple objects based on detailed textual description. Compared to prior state-of-the-art semantic nursing technique for text-to-image synthesis, Attend & Excite, our approach exhibits superior
![Divide & Bind](https://lemdro.id/pictrs/image/7c63c02f-2c6c-48e3-ab16-344fa0d5a9be.png?format=webp&thumbnail=256)
Greatly improves Stable Diffusion's issues of missing objects and mixing up attributes
0
comments