By training appearance and motion LoRAs on separate layers and distilling from their single-LoRA teachers for 30 steps, the combined model produces videos with a custom subject and a custom motion.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1931–1941
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training
By training appearance and motion LoRAs on separate layers and distilling from their single-LoRA teachers for 30 steps, the combined model produces videos with a custom subject and a custom motion.