SUGAR combines a 2.5 million synthetic image-video-text dataset, selective attention, and two-stage training to generate videos of a subject from one image and a text prompt without per-subject fine-tuning.
Align your latents: High-resolution video synthesis with la- tent diffusion models
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner
SUGAR combines a 2.5 million synthetic image-video-text dataset, selective attention, and two-stage training to generate videos of a subject from one image and a text prompt without per-subject fine-tuning.