RandAR shows a decoder-only transformer can generate images in arbitrary token orders with quality close to raster order, using position instruction tokens, while unlocking parallel decoding and zero-shot editing.
In- structPix2Pix: Learning to follow image editing instructions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
RandAR shows a decoder-only transformer can generate images in arbitrary token orders with quality close to raster order, using position instruction tokens, while unlocking parallel decoding and zero-shot editing.