Re-Imagen: Retrieval-Augmented Text-to-Image Generator. (arXiv:2209.14491v3 [cs.CV] UPDATED)

Research on text-to-image generation has witnessed significant progress in
generating diverse and photo-realistic images, driven by diffusion and
auto-regressive models trained on large-scale image-text data. Though
state-of-the-art models can generate high-quality images of common entities,
they often have difficulty generating images of uncommon entities, such as
`Chortai (dog)' or `Picarones (food)'. To tackle this issue, we present the
Retrieval-Augmented Text-to-Image Generator (Re-Imagen), a generative model
that uses retrieved information to produce high-fidelity and faithful images,
even for rare or unseen …

arxiv generator image image generator imagen retrieval text text-to-image text-to-image generator