The Plug and Play of Language Models for Text-to-image Generation

Text-to-image (T2I) models enable controllable image generation through user-provided captions. A text encoder is typically used to map captions to a latent space, and it has been shown to be critical for model's performance. However, replacing or upgrading the text encoder in a T2I model is challenging due to the tight bond between the current encoder and the image decoder. It requires training the model from scratch, which can be prohibitively expensive. To address this problem, we introduce a more efficient approach to align a pre-trained language model with the latent space of an existing T2I model. We propose a Model Translation Network (MTN) and a new training objective to align the representation spaces of the two text encoders using only a corpus of unlabeled text. We empirically find that MTN can be trained efficiently and can boost the performance of existing T2I models by upgrading their text encoder. Moreover, we find that MTN can align multilingual language models such as XLM-Roberta, thus allowing existing T2I models to generate high-quality images from captions beyond English.