Very very WIP implementation of "TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation"
https://arxiv.org/abs/2404.11824
There are some really interesting techniques that we can use to manipulate attention.
Results for a region mask that roughly covers the left half of the frame. Test with a prompt + seed that covers the whole left half of the image and low margin force.
Very very WIP implementation of "TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation" https://arxiv.org/abs/2404.11824
There are some really interesting techniques that we can use to manipulate attention.