LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913983364071424 |
|---|---|
| author | Song, Wenhui Li, Hanhui Huang, Jiehui Hu, Panwen Cheng, Yuhao Chen, Long Yan, Yiqiang Liang, Xiaodan |
| author_facet | Song, Wenhui Li, Hanhui Huang, Jiehui Hu, Panwen Cheng, Yuhao Chen, Long Yan, Yiqiang Liang, Xiaodan |
| contents | In this paper, we present LaVieID, a novel \underline{l}ocal \underline{a}utoregressive \underline{vi}d\underline{e}o diffusion framework designed to tackle the challenging \underline{id}entity-preserving text-to-video task. The key idea of LaVieID is to mitigate the loss of identity information inherent in the stochastic global generation process of diffusion transformers (DiTs) from both spatial and temporal perspectives. Specifically, unlike the global and unstructured modeling of facial latent states in existing DiTs, LaVieID introduces a local router to explicitly represent latent states by weighted combinations of fine-grained local facial structures. This alleviates undesirable feature interference and encourages DiTs to capture distinctive facial characteristics. Furthermore, a temporal autoregressive module is integrated into LaVieID to refine denoised latent tokens before video decoding. This module divides latent tokens temporally into chunks, exploiting their long-range temporal dependencies to predict biases for rectifying tokens, thereby significantly enhancing inter-frame identity consistency. Consequently, LaVieID can generate high-fidelity personalized videos and achieve state-of-the-art performance. Our code and models are available at https://github.com/ssugarwh/LaVieID. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07603 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation Song, Wenhui Li, Hanhui Huang, Jiehui Hu, Panwen Cheng, Yuhao Chen, Long Yan, Yiqiang Liang, Xiaodan Computer Vision and Pattern Recognition In this paper, we present LaVieID, a novel \underline{l}ocal \underline{a}utoregressive \underline{vi}d\underline{e}o diffusion framework designed to tackle the challenging \underline{id}entity-preserving text-to-video task. The key idea of LaVieID is to mitigate the loss of identity information inherent in the stochastic global generation process of diffusion transformers (DiTs) from both spatial and temporal perspectives. Specifically, unlike the global and unstructured modeling of facial latent states in existing DiTs, LaVieID introduces a local router to explicitly represent latent states by weighted combinations of fine-grained local facial structures. This alleviates undesirable feature interference and encourages DiTs to capture distinctive facial characteristics. Furthermore, a temporal autoregressive module is integrated into LaVieID to refine denoised latent tokens before video decoding. This module divides latent tokens temporally into chunks, exploiting their long-range temporal dependencies to predict biases for rectifying tokens, thereby significantly enhancing inter-frame identity consistency. Consequently, LaVieID can generate high-fidelity personalized videos and achieve state-of-the-art performance. Our code and models are available at https://github.com/ssugarwh/LaVieID. |
| title | LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.07603 |