{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T23:07:43Z","timestamp":1779923263192,"version":"3.53.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T00:00:00Z","timestamp":1775347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":53,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-46445-6","type":"journal-article","created":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T11:25:58Z","timestamp":1775388358000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Identity-consistent and high-fidelity audio-driven portrait animation with enhanced latent diffusion"],"prefix":"10.1038","volume":"16","author":[{"given":"Xiangwen","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"San","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junping","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,5]]},"reference":[{"key":"46445_CR1","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P. & Nichol, A. Diffusion models beat GANs on image synthesis. Adv. Neural Inf. Process. Syst. 34, 8780\u20138794 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"46445_CR2","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A. & Abbeel, P. Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"46445_CR3","doi-asserted-by":"crossref","unstructured":"Peebles, W. & Xie, S. Scalable diffusion models with transformers. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4195\u20134205 (2023).","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"46445_CR4","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10684\u201310695 (2022).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"46445_CR5","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N. & Ganguli, S. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning. 2256\u20132265 (2015)."},{"key":"46445_CR6","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I. et al. Generative adversarial networks. Commun. ACM 63, 139\u2013144 (2020).","journal-title":"Commun. ACM"},{"key":"46445_CR7","doi-asserted-by":"publisher","first-page":"7519","DOI":"10.1038\/s41598-025-92225-z","volume":"15","author":"Y Zhou","year":"2025","unstructured":"Zhou, Y., Liu, Y., Shao, Y. & Chen, J. Fine-tuning diffusion model to generate new kite designs for the revitalization and innovation of intangible cultural heritage. Sci. Rep. 15, 7519 (2025).","journal-title":"Sci. Rep."},{"key":"46445_CR8","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TPAMI.2024.3461721","volume":"47","author":"Z Yue","year":"2024","unstructured":"Yue, Z., Wang, J. & Loy, C. C. Efficient diffusion model for image restoration by residual shifting. IEEE Trans. Pattern Anal. Mach. Intell. 47, 116\u2013130 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"46445_CR9","doi-asserted-by":"crossref","unstructured":"Loc, I. & Unlu, M.\u00a0B. Accelerating photoacoustic microscopy by reconstructing undersampled images using diffusion models. Sci. Rep. 14 (2024).","DOI":"10.1038\/s41598-024-67957-z"},{"key":"46445_CR10","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, O. & Jiang, Y. Multimodal diffusion framework for collaborative text image audio generation and applications. Sci. Rep. 15 (2025).","DOI":"10.1038\/s41598-025-05794-4"},{"key":"46445_CR11","unstructured":"Guo, Y. et al. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv:2307.04725 (2023)."},{"key":"46445_CR12","doi-asserted-by":"crossref","unstructured":"Hu, L. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153\u20138163 (2024).","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"46445_CR13","doi-asserted-by":"crossref","unstructured":"Tian, L., Wang, Q., Zhang, B. & Bo, L. Emo: Emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions. In European Conference on Computer Vision. 244\u2013260 (2024).","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"46445_CR14","unstructured":"Xu, M. et al. Hallo: Hierarchical audio-driven visual synthesis for portrait image animation. arXiv:2406.08801 (2024)."},{"key":"46445_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, Y. et al. Meta talk: Learning to data-efficiently generate audio-driven lip-synchronized talking face with high definition. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing. 4848\u20134852 (2022).","DOI":"10.1109\/ICASSP43922.2022.9747284"},{"key":"46445_CR16","unstructured":"Yao, S., Zhong, R., Yan, Y., Zhai, G. & Yang, X. Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering. arXiv:2201.00791 (2022)."},{"key":"46445_CR17","doi-asserted-by":"crossref","unstructured":"Yu, Z. et al. Talking head generation with probabilistic audio-to-visual diffusion priors. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7645\u20137655 (2023).","DOI":"10.1109\/ICCV51070.2023.00703"},{"key":"46445_CR18","doi-asserted-by":"crossref","unstructured":"Wang, D., Deng, Y., Yin, Z., Shum, H.-Y. & Wang, B. Progressive disentangled representation learning for fine-grained controllable talking head synthesis. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17979\u201317989 (2023).","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"46445_CR19","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.\u00a0K., Duan, Z. & Xu, C. Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7832\u20137841 (2019).","DOI":"10.1109\/CVPR.2019.00802"},{"key":"46445_CR20","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/TPAMI.2003.1227983","volume":"25","author":"V Blanz","year":"2003","unstructured":"Blanz, V. & Vetter, T. Face recognition based on fitting a 3D morphable model. IEEE Trans. Pattern Anal. Mach. Intell. 25, 1063\u20131074 (2003).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"46445_CR21","doi-asserted-by":"crossref","unstructured":"Blattmann, A. et al. Align your latents: High-resolution video synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 22563\u201322575 (2023).","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"46445_CR22","unstructured":"Chang, D. et al. Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion. In International Conference on Machine Learning (2024)."},{"key":"46445_CR23","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liang, Y., Zhu, L. & Yang, Y. Freelong: Training-free long video generation with spectral blend temporal attention. In Advances in Neural Information Processing Systems (2024).","DOI":"10.52202\/079017-4177"},{"key":"46445_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A. & Agrawala, M. Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3836\u20133847 (2023).","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"46445_CR25","unstructured":"Gu, J. et al. Reuse and diffuse: Iterative denoising for text-to-video generation. arXiv:2309.03549 (2023)."},{"key":"46445_CR26","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.\u00a0P. & Jawahar, C. A lip sync expert is all you need for speech to lip generation in the wild. In Proceedings of the 28th ACM International Conference on Multimedia. 484\u2013492 (2020).","DOI":"10.1145\/3394171.3413532"},{"key":"46445_CR27","doi-asserted-by":"publisher","first-page":"3457","DOI":"10.1109\/TVCG.2020.3023573","volume":"26","author":"X Wen","year":"2020","unstructured":"Wen, X., Wang, M., Richardt, C., Chen, Z.-Y. & Hu, S.-M. Photorealistic audio-driven video portraits. IEEE Trans. Vis. Comput. Graph. 26, 3457\u20133466 (2020).","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"46445_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, C. et al. Facial: Synthesizing dynamic talking face with implicit attribute learning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3867\u20133876 (2021).","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"46445_CR29","first-page":"157","volume":"2","author":"V Blanz","year":"2023","unstructured":"Blanz, V. & Vetter, T. A morphable model for the synthesis of 3D faces. Semin. Graph. Pap. Push. Bound. 2, 157\u2013164 (2023).","journal-title":"Semin. Graph. Pap. Push. Bound."},{"key":"46445_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, W. et al. Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8652\u20138661 (2023).","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"46445_CR31","unstructured":"Sun, X. et al. Vividtalk: One-shot audio-driven talking head generation based on 3D hybrid prior. arXiv:2312.01841 (2023)."},{"key":"46445_CR32","unstructured":"Ma, Y. et al. Dreamtalk: When expressive talking head generation meets diffusion probabilistic models. Vol. 2. arXiv:2312.09767 (2023)."},{"key":"46445_CR33","doi-asserted-by":"crossref","unstructured":"Shen, S. et al. Difftalk: Crafting diffusion models for generalized audio-driven portraits animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1982\u20131991 (2023).","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"46445_CR34","unstructured":"Wang, C. et al. V-express: Conditional dropout for progressive training of portrait video generation. arXiv:2406.02511 (2024)."},{"key":"46445_CR35","unstructured":"Van Den Oord, A., Vinyals, O. et al. Neural discrete representation learning. In Advances in Neural Information Processing Systems. Vol. 30 (2017)."},{"key":"46445_CR36","unstructured":"Song, J., Meng, C. & Ermon, S. Denoising diffusion implicit models. arXiv:2010.02502 (2020)."},{"key":"46445_CR37","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748\u20138763 (2021)."},{"key":"46445_CR38","doi-asserted-by":"crossref","unstructured":"Cao, M. et al. Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 22560\u201322570 (2023).","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"46445_CR39","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R. & Auli, M. wav2vec: Unsupervised pre-training for speech recognition. arXiv:1904.05862 (2019).","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"46445_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y. & Fan, C. Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3661\u20133670 (2021).","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"46445_CR41","unstructured":"Lugaresi, C. et al. Mediapipe: A framework for building perception pipelines. arXiv:1906.08172 (2019)."},{"key":"46445_CR42","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B. & Hochreiter, S. Gans trained by a two time-scale update rule converge to a local Nash equilibrium. In Advances in Neural Information Processing Systems. Vol. 30 (2017)."},{"key":"46445_CR43","unstructured":"Unterthiner, T. et al. Fvd: A new metric for video generation. In International Conference on Learning Representations (2019)."},{"key":"46445_CR44","doi-asserted-by":"crossref","unstructured":"Chung, J.\u00a0S. & Zisserman, A. Out of time: automated lip sync in the wild. In Computer Vision\u2013ACCV 2016 Workshops: ACCV 2016 International Workshops. 251\u2013263 (Springer, 2017).","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"46445_CR45","doi-asserted-by":"crossref","unstructured":"Kim, M., Jain, A.\u00a0K. & Liu, X. Adaface: Quality adaptive margin for face recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18750\u201318759 (2022).","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"46445_CR46","unstructured":"Wei, H., Yang, Z. & Wang, Z. Aniportrait: Audio-driven synthesis of photorealistic portrait animation. arXiv:2403.17694 (2024)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46445-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46445-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46445-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:43:25Z","timestamp":1779921805000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46445-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,5]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["46445"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-46445-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6850056\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,5]]},"assertion":[{"value":"9 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"16475"}}