A stage-aware token merging scheme, SDTM, speeds up DiT text-to-image generation 1.55x without fine-tuning and with negligible FID change.
Ld-pruner: Efficient pruning of latent diffu- sion models using task-agnostic insights
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
A stage-aware token merging scheme, SDTM, speeds up DiT text-to-image generation 1.55x without fine-tuning and with negligible FID change.