Make It Count: Text-to-Image Generation with an Accurate Number of Objects

arXiv:2406.10210v1 Announce Type: new
Abstract: Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications from technical documents, to children's books to illustrating cooking recipes. Generating object-correct counts is fundamentally challenging because the generative model needs to keep a sense of separate identity for every instance of the object, even if several objects look identical or overlap, and then carry out a global computation implicitly …

abstract applications arxiv books children children's books cooking count cs.ai cs.cv cs.gr diffusion diffusion models documents generative image image diffusion image generation important object objects recipes success technical text text-to-image type