A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale.
Our model uses 128 gradient scales, one for each of its resblocks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2021 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Zero-Shot Text-to-Image Generation
A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale.