{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T04:09:56Z","timestamp":1746850196411,"version":"3.40.5"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,6]]},"DOI":"10.1109\/smc54092.2024.10831577","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:20Z","timestamp":1737398360000},"page":"148-154","source":"Crossref","is-referenced-by-count":0,"title":["Faster and More Efficient Subject Image Generation for Text-to-Image Diffusion Models"],"prefix":"10.1109","author":[{"given":"Bihui","family":"Yu","sequence":"first","affiliation":[{"name":"Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang,China,110168"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengbing","family":"Yao","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang,China,110168"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingxuan","family":"Wei","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang,China,110168"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linzhuang","family":"Sun","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang,China,110168"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sibo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang,China,110168"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liping","family":"Bu","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang,China,110168"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref3","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref8","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref11","article-title":"P+ p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"29","article-title":"The neural autoregressive distribution estimator","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Larochelle","year":"2011"},{"key":"ref13","first-page":"881","article-title":"Made: Masked autoencoder for distribution estimation","volume-title":"International conference on machine learning","author":"Germain","year":"2015"},{"key":"ref14","article-title":"Learning in implicit generative models","author":"Mohamed","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref18","article-title":"Density estimation using real nvp","author":"Dinh","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Glow: Generative flow with invertible $1\\times 1$ convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207181"},{"key":"ref23","article-title":"Banach wasserstein gan","volume":"31","author":"Adler","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"International conference on machine learning","author":"Larsen","year":"2016"},{"issue":"3","key":"ref25","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref26","article-title":"Pixart-: Weak-to-strong training of diffusion transformer for 4k text-to-image generation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"arXiv preprint"},{"volume-title":"Video generation models as world simulators","year":"2024","author":"Brooks","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref30","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Prompt-free diffusion: Taking\u201ctext\u201d out of text-to-image diffusion models","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Photoverse: Tuning-free image customization with text-to-image diffusion models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref39","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2024,10,6]]},"location":"Kuching, Malaysia","end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830919\/10830920\/10831577.pdf?arnumber=10831577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:52:13Z","timestamp":1746813133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10831577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/smc54092.2024.10831577","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}