A training-free predictor-corrector method that accelerates Diffusion Transformers by solving a feature-ODE, achieving large compute reductions with modest quality loss.
In 2019 IEEE/CVF International Confer- ence on Computer Vision Workshop (ICCVW), 512–520
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
A training-free predictor-corrector method that accelerates Diffusion Transformers by solving a feature-ODE, achieving large compute reductions with modest quality loss.