A single diffusion transformer with a spatial-temporal VAE and in-context example pairs unifies over 20 vision tasks, with strong scores on several image benchmarks and uneven evidence on video tasks.
Visual prompting via image inpaint- ing
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
-
LaVin-DiT: Large Vision Diffusion Transformer
A single diffusion transformer with a spatial-temporal VAE and in-context example pairs unifies over 20 vision tasks, with strong scores on several image benchmarks and uneven evidence on video tasks.