Probabilistically adding high-intensity noise to individual token embeddings during fine-tuning reduces replication in Stable Diffusion by up to 28.78% in the paper's experiments, with unchanged or improved FID.
Diffusion models beat GANs on image synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings
Probabilistically adding high-intensity noise to individual token embeddings during fine-tuning reduces replication in Stable Diffusion by up to 28.78% in the paper's experiments, with unchanged or improved FID.