Self-Swap Guidance steers diffusion sampling by swapping dissimilar token latents to enable CFG-like improvements for both conditional and unconditional generation.
Eliminating oversaturation and artifacts of high guid- ance scales in diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Guiding a Diffusion Model by Swapping Its Tokens
Self-Swap Guidance steers diffusion sampling by swapping dissimilar token latents to enable CFG-like improvements for both conditional and unconditional generation.