English

Emojich -- zero-shot emoji generation using Russian language: a technical report

Computation and Language 2022-01-14 v2 Artificial Intelligence Machine Learning

Abstract

This technical report presents a text-to-image neural network "Emojich" that generates emojis using captions in Russian language as a condition. We aim to keep the generalization ability of a pretrained big model ruDALL-E Malevich (XL) 1.3B parameters at the fine-tuning stage, while giving special style to the images generated. Here are presented some engineering methods, code realization, all hyper-parameters for reproducing results and a Telegram bot where everyone can create their own customized sets of stickers. Also, some newly generated emojis obtained by "Emojich" model are demonstrated.

Cite

@article{arxiv.2112.02448,
  title  = {Emojich -- zero-shot emoji generation using Russian language: a technical report},
  author = {Alex Shonenkov and Daria Bakshandaeva and Denis Dimitrov and Aleksandr Nikolich},
  journal= {arXiv preprint arXiv:2112.02448},
  year   = {2022}
}

Comments

5 pages, 4 figures and big figure at appendix, technical report

R2 v1 2026-06-24T08:04:31.148Z