{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T08:55:40Z","timestamp":1770800140576,"version":"3.50.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02063-2","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T09:41:44Z","timestamp":1764754904000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TIPDF-DWSF: a task-oriented two-stage optimization framework for diffusion model LoRA fine-tuning"],"prefix":"10.1007","volume":"32","author":[{"given":"BaiHao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"2063_CR1","doi-asserted-by":"crossref","unstructured":"Sun, W., Li, X., Li, M., Xu, K., Meng, X., Meng, L.: Hierarchically-structured open-vocabulary indoor scene synthesis with pre-trained large language model. In: AAAI Conference on Artificial Intelligence (2025). https:\/\/api.semanticscholar.org\/CorpusID:276409105","DOI":"10.1609\/aaai.v39i7.32765"},{"key":"2063_CR2","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"F-A Croitoru","year":"2022","unstructured":"Croitoru, F.-A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10850\u201310869 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2063_CR3","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2020). arXiv:2010.02502"},{"key":"2063_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: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2063_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505243","volume":"56","author":"L Yang","year":"2022","unstructured":"Yang, L., Zhang, Z., Hong, S., Xu, R., Zhao, Y., Shao, Y., Zhang, W., Yang, M.-H., Cui, B.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56, 1\u201339 (2022)","journal-title":"ACM Comput. Surv."},{"key":"2063_CR6","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., Chen, M.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: International conference on machine learning (ICML) (2021). https:\/\/api.semanticscholar.org\/CorpusID:245335086"},{"key":"2063_CR7","unstructured":"Sun, X., Ji, Y., Ma, B., Li, X.: A comparative study between full-parameter and lora-based fine-tuning on chinese instruction data for instruction following large language model (2023). arXiv: 2304.08109"},{"key":"2063_CR8","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Muller, J., Penna, J., Rombach, R.: Sdxl: improving latent diffusion models for high-resolution image synthesis (2023). arXiv: 2307.01952"},{"key":"2063_CR9","unstructured":"Hu, J.E., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Chen, W.: Lora: low-rank adaptation of large language models (2021). arXiv:2106.09685"},{"key":"2063_CR10","unstructured":"kohya-ss: sd-scripts. https:\/\/github.com\/kohya-ss\/sd-scripts. GitHub repository (2025)"},{"key":"2063_CR11","unstructured":"Hayou, S., Ghosh, N., Yu, B.: Lora+: efficient low rank adaptation of large models (2024). arXiv:2402.12354"},{"key":"2063_CR12","unstructured":"Kopiczko, D.J., Blankevoort, T., Asano, Y.M.: Vera: vector-based random matrix adaptation (2023).arXiv:2310.11454"},{"key":"2063_CR13","doi-asserted-by":"crossref","unstructured":"Ren, P., Shi, C., Wu, S., Zhang, M., Ren, Z., Rijke, M., Chen, Z., Pei, J.: Mini-ensemble low-rank adapters for parameter-efficient fine-tuning (2024). arXiv: 2402.17263","DOI":"10.18653\/v1\/2024.acl-long.168"},{"key":"2063_CR14","unstructured":"Zhang, L., Zhang, L., Shi, S., Chu, X., Li, B.: Lora-fa: memory-efficient low-rank adaptation for large language models fine-tuning (2023). arXiv:2308.03303"},{"key":"2063_CR15","unstructured":"Huang, L., Wang, W., Wu, Z., Shi, Y., Dou, H., Liang, C., Feng, Y., Liu, Y., Zhou, J.: In-context lora for diffusion transformers (2024). arXiv:2410.23775"},{"key":"2063_CR16","unstructured":"Kasymov, A., Sendera, M., Stypulkowski, M., Zieba, M., Spurek, P.: Autolora: autoguidance meets low-rank adaptation for diffusion models (2024). arXiv: 2410.03941"},{"key":"2063_CR17","unstructured":"Zhuang, Z., Zhang, Y., Wang, X., Lu, J., Wei, Y., Zhang, Y.: Time-varying loRA: towards effective cross-domain fine-tuning of diffusion models. In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems (2024). https:\/\/openreview.net\/forum?id=SgODU2mx9T"},{"key":"2063_CR18","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1109\/TIP.2025.3553024","volume":"34","author":"C Liu","year":"2025","unstructured":"Liu, C., Sun, G., Liang, W., Dong, J., Qin, C., Cong, Y.: Museummaker: continual style customization without catastrophic forgetting. IEEE Trans. Image Process. 34, 2499\u20132512 (2025). https:\/\/doi.org\/10.1109\/TIP.2025.3553024","journal-title":"IEEE Trans. Image Process."},{"key":"2063_CR19","doi-asserted-by":"crossref","unstructured":"Ouyang, Z.-J., Li, Z., Hou, Q.: K-lora: unlocking training-free fusion of any subject and style loras. (2025). arXiv: 2502.18461","DOI":"10.1109\/CVPR52734.2025.01217"},{"key":"2063_CR20","unstructured":"Zhuang, S., Guo, Y., Ding, Y., Li, K., Chen, X., Wang, Y., Wang, F., Zhang, Y., Li, C., Wang, Y.: Timestep master: asymmetrical mixture of timestep lora experts for versatile and efficient diffusion models in vision (2025). arXiv: 2503.07416"},{"key":"2063_CR21","unstructured":"Kim, M., Ki, D., Shim, S.-W., Lee, B.-J.: Adaptive non-uniform timestep sampling for diffusion model training (2024). arXiv: 2411.09998"},{"key":"2063_CR22","unstructured":"Sohl-Dickstein, J.N., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics (2015). arXiv:1503.03585"},{"key":"2063_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020). arXiv:2006.11239"},{"key":"2063_CR24","unstructured":"Song, Y., Sohl-Dickstein, J.N., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations (2020). arXiv: 2011.13456"},{"key":"2063_CR25","unstructured":"Kingma, D.P., Salimans, T., Poole, B., Ho, J.: Variational diffusion models (2021)"},{"key":"2063_CR26","unstructured":"Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., Parikh, D., Gupta, S., Taigman, Y.: Make-a-video: text-to-video generation without text-video data (2022). arXiv:2209.14792"},{"key":"2063_CR27","doi-asserted-by":"crossref","unstructured":"Zhuang, S., Li, K., Chen, X., Wang, Y., Liu, Z., Qiao, Y., Wang, Y.: Vlogger: make your dream a vlog. In: 2024 IEEE\/CVF Conference Computer Vision Pattern Recogition (CVPR), pp. 8806\u20138817 (2024)","DOI":"10.1109\/CVPR52733.2024.00841"},{"key":"2063_CR28","unstructured":"Labs, B.F.: FLUX. https:\/\/github.com\/black-forest-labs\/flux (2024)"},{"key":"2063_CR29","unstructured":"Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Density Estimation For Statistics And Data Analysis (1986)"},{"key":"2063_CR30","unstructured":"Zhang, H., Wu, Z., Xing, Z., Shao, J., Jiang, Y.-G.: Adadiff: adaptive step selection for fast diffusion. (2023). arXiv: 2311.14768"},{"key":"2063_CR31","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Confernce Computer Vision Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2063_CR32","unstructured":"Liu, S.-Y., Wang, C.-Y., Yin, H., Molchanov, P., Wang, Y.-C.F., Cheng, K.-T., Chen, M.-H.: Dora: weight-decomposed low-rank adaptation (2024). arXiv:2402.09353"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02063-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02063-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02063-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T04:17:46Z","timestamp":1770783466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02063-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2063"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02063-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"26 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain studies with human participants or animals. Statement of informed consent is not applicable since the manuscript does not contain any patient data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"2"}}