HyperDreamBooth
First page
Paper summary
A smaller, faster, and more efficient version of DreamBooth for personalizing text-to-image models.
Ask this paper
01
HyperNetwork design: Uses a HyperNetwork to predict LoRA weights from a single input image, bypassing per-subject optimization.
02
25x speedup: Achieves ~25x faster personalization than DreamBooth while maintaining visual fidelity to the subject.
03
Single-image input: Requires only one input image of the subject - a major UX improvement over prior methods needing 3-5 images.
04
On-device personalization: Compact adapter footprint makes HyperDreamBooth-style techniques attractive for on-device personalization in consumer apps.