GMem conditions diffusion models on a fixed bank of DINOv2 features and reports much lower FID at far fewer epochs than SiT and REPA baselines on ImageNet.
We then create nine interpolated snippets ˆsi by linearly interpolating between s1 and s2 with interpolation coefficients αi ranging from 0.1 to 0.9 in increments of 0.1
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
-
GMem: A Modular Approach for Ultra-Efficient Generative Models
GMem conditions diffusion models on a fixed bank of DINOv2 features and reports much lower FID at far fewer epochs than SiT and REPA baselines on ImageNet.