HRDiT enables off-the-shelf diffusion transformer text-to-image models to produce coherent high-resolution images with far less computation, without any retraining.
In: Forty-second International Conference on Machine Learning (2025),https://openreview.net/forum?id=U74MOXPEJd
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
HRDiT enables off-the-shelf diffusion transformer text-to-image models to produce coherent high-resolution images with far less computation, without any retraining.