3 datasets found

Text2Shape is a dataset of 8,447 table instances and 6,591 chair instances from the ShapeNet dataset, along with 75,344 natural language descriptions.

The dataset used in the paper is not explicitly described, but it is mentioned that it is a large-scale captioned image dataset (LAION) used to train the Stable Diffusion model.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...