DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.
Taylor’s expansion yields xti − αti αti−1 xti−1 − αti(e−hi − 1)xθ(xti−1 , ti−1) − αti −e−hi − hi + 1 x(1) θ (xti−1 , ti−1) ≤ Ch 3 i , where C is a constant depends on x(2) θ
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2022 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.