TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.
TA V Text2video-zero Rerender-a-video fatezero PnP ours (preprocess) ours (sampling) ours (total) 2684 198 285 349 208 50 187 237 We provide additional implementation details below
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TokenFlow: Consistent Diffusion Features for Consistent Video Editing
TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.