A unified framework and targeted changes to parameterization, architecture, and objectives stabilize continuous-time consistency models, achieving FID scores of 2.06 on CIFAR-10 and 1.88 on ImageNet 512x512 with two-step sampling at 1.5B scale.
Then the objective becomes min θ,ϕ Et ewϕ(t) D ∥Fθ − Fθ− + λ(t)y∥2 2 − wϕ(t)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
A unified framework and targeted changes to parameterization, architecture, and objectives stabilize continuous-time consistency models, achieving FID scores of 2.06 on CIFAR-10 and 1.88 on ImageNet 512x512 with two-step sampling at 1.5B scale.