PQD calibrates diffusion-model quantization on time steps drawn from a tuned normal distribution, reporting competitive 8-bit FID on 64x64 ImageNet but much worse 4-bit FID and no quantitative text-to-image results.
Differentiable soft quantization: Bridging full-precision and low-bit neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
PQD: Post-training Quantization for Efficient Diffusion Models
PQD calibrates diffusion-model quantization on time steps drawn from a tuned normal distribution, reporting competitive 8-bit FID on 64x64 ImageNet but much worse 4-bit FID and no quantitative text-to-image results.