Ingredients: Blending Custom Photos with Video Diffusion Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fei, Zhengcong, Li, Debang, Qiu, Di, Yu, Changqian, Fan, Mingyuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916654928101376
author Fei, Zhengcong
Li, Debang
Qiu, Di
Yu, Changqian
Fan, Mingyuan
author_facet Fei, Zhengcong
Li, Debang
Qiu, Di
Yu, Changqian
Fan, Mingyuan
contents This paper presents a powerful framework to customize video creations by incorporating multiple specific identity (ID) photos, with video diffusion Transformers, referred to as Ingredients. Generally, our method consists of three primary modules: (i) a facial extractor that captures versatile and precise facial features for each human ID from both global and local perspectives; (ii) a multi-scale projector that maps face embeddings into the contextual space of image query in video diffusion transformers; (iii) an ID router that dynamically combines and allocates multiple ID embedding to the corresponding space-time regions. Leveraging a meticulously curated text-video dataset and a multi-stage training protocol, Ingredients demonstrates superior performance in turning custom photos into dynamic and personalized video content. Qualitative evaluations highlight the advantages of proposed method, positioning it as a significant advancement toward more effective generative video control tools in Transformer-based architecture, compared to existing methods. The data, code, and model weights are publicly available at: https://github.com/feizc/Ingredients.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01790
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ingredients: Blending Custom Photos with Video Diffusion Transformers
Fei, Zhengcong
Li, Debang
Qiu, Di
Yu, Changqian
Fan, Mingyuan
Computer Vision and Pattern Recognition
This paper presents a powerful framework to customize video creations by incorporating multiple specific identity (ID) photos, with video diffusion Transformers, referred to as Ingredients. Generally, our method consists of three primary modules: (i) a facial extractor that captures versatile and precise facial features for each human ID from both global and local perspectives; (ii) a multi-scale projector that maps face embeddings into the contextual space of image query in video diffusion transformers; (iii) an ID router that dynamically combines and allocates multiple ID embedding to the corresponding space-time regions. Leveraging a meticulously curated text-video dataset and a multi-stage training protocol, Ingredients demonstrates superior performance in turning custom photos into dynamic and personalized video content. Qualitative evaluations highlight the advantages of proposed method, positioning it as a significant advancement toward more effective generative video control tools in Transformer-based architecture, compared to existing methods. The data, code, and model weights are publicly available at: https://github.com/feizc/Ingredients.
title Ingredients: Blending Custom Photos with Video Diffusion Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.01790