Skip to content

ALADDIN: Adversarial Latent Diffusion Knowledge Distillation for One-Step Identity Replacement

ALADDIN: Adversarial Latent Diffusion Distillation for One-Step Identity Swapping

arXiv· arXiv:2610.37503· Ivan Shchekotov, Timofei Gritsaev, Viacheslav Pirogov, Dmitry Vetrov·Indexed by this site · 6 days ago· Originally publishedAI updates
AI summary

ALADDIN is a one-step face identity swapping method; the generator is initialized from a pretrained multi-step flow-matching model and trained adversarially. The authors find that standard evaluation favors methods trained and scored with the same identity encoder, and re-evaluate baselines using an independent encoder. With comparable identity transfer, ALADDIN's realism and target preservation are best among one-step methods, matching the best multi-step models with 28× fewer network evaluations and an order of magnitude fewer training pairs.

Related events and news

1 events · 1 news mentions

News that mentions this paper

Sumsub与高校发布单步换脸模型ALADDIN

Read originalarxiv.org