paper-with-me

홈 › Papers

UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization

2024-08-12 · Junjie He, Yifeng Geng, Liefeng Bo

This paper presents UniPortrait, an innovative human image personalization framework that unifies single- and multi-ID customization with high face fidelity, extensive facial editability, free-form input description, and diverse layout generation. UniPortrait consists of only two plug-and-play modules: an ID embedding module and an ID routing module. The ID embedding module extracts versatile editable facial features with a decoupling strategy for each ID and embeds them into the context space of diffusion models. The ID routing module then combines and distributes these embeddings adaptively to their respective regions within the synthesized image, achieving the customization of single and multiple IDs. With a carefully designed two-stage training scheme, UniPortrait achieves superior performance in both single- and multi-ID customization. Quantitative and qualitative experiments demonstrate the advantages of our method over existing approaches as well as its good scalability, e.g., the universal compatibility with existing generative control tools. The project page is at https://aigcdesigngroup.github.io/UniPortrait-Page/ .

📄 PDF Abstract BibTeX arXiv:2408.05939

Code (1)

junjiehe96/UniPortrait 공식 구현 pytorch

Tasks

Layout Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Concat-ID: Towards Universal Identity-Preserving Video Synthesis

2025-03-18 · Yong Zhong, Zhuoyi Yang, Jiayan Teng, Xiaotao Gu 외

We present Concat-ID, a unified framework for identity-preserving video generation. Concat-ID employs Variational Autoencoders to extract image features, which are concatenated with video latents along the sequence dimen…

Human-Domain Subject-to-VideoVideo GenerationVirtual Try-on

SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation

2025-10-07 · Oindrila Saha, Vojtech Krs, Radomir Mech, Subhransu Maji 외 arxiv

We present SIGMA-GEN, a unified framework for multi-identity preserving image generation. Unlike prior approaches, SIGMA-GEN is the first to enable single-pass multi-subject identity-preserved generation guided by both s…

Image Generation

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

2026-04-06 · Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo arxiv

We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image…

Virtual Try-on

Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis

2025-04-19 · Zichuan Liu, Liming Jiang, Qing Yan, Yumin Jia 외

We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unifi…

Image Generation

Vera: Identity-Faithful Human Subject-to-Video Generation

2026-07-22 · Yulong Xu, Xinyue Liu, Shujuan Li, huafeng shi 외 arxiv

Subject-to-video (S2V) generation has made substantial progress in preserving reference subjects across diverse categories, yet generic subject consistency remains insufficient for human-centric generation. A video may a…

Video Generation