Добрый день, друзья! Новое соревнование:

https://www.kaggle.com/competitions/stable-diffusion-image-to-prompts

The goal of this competition is to reverse the typical direction of a generative text-to-image model: instead of generating an image from a text prompt, can you create a model which can predict the text prompt given a generated image? You will make predictions on a dataset containing a wide variety of (prompt, image) pairs generated by Stable Diffusion 2.0, in order to understand how reversible the latent relationship is.