Certain random seeds yield consistently more accurate compositional text-to-image outputs, and mining these seeds plus fine-tuning on the resulting self-generated images improves numerical and spatial composition accuracy.
Pixart- : Fast training of diffusion transformer for photorealistic text-to-image synthesis, 2023 a
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
-
All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
Certain random seeds yield consistently more accurate compositional text-to-image outputs, and mining these seeds plus fine-tuning on the resulting self-generated images improves numerical and spatial composition accuracy.