{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:24Z","timestamp":1777888704497,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01549","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16682-16691","source":"Crossref","is-referenced-by-count":0,"title":["CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation"],"prefix":"10.1109","author":[{"given":"Zixin","family":"Zhu","sequence":"first","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Duarte","sequence":"additional","affiliation":[{"name":"Adobe Inc. (ASML)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mamshad Nayeem","family":"Rizve","sequence":"additional","affiliation":[{"name":"Adobe Inc. (ASML)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Adobe Inc. (ASML)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ratheesh","family":"Kalarot","sequence":"additional","affiliation":[{"name":"Adobe Inc. (ASML)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref3","article-title":"Ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","volume-title":"Multidiffusion: Fusing diffusion paths for controlled image generation.","author":"Bar-Tal","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3370212"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref10","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume-title":"NeurIPS","volume":"36","author":"Epstein","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-025-01762-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327168"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref14","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_10"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","volume":"33","author":"Ho","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00787"},{"key":"ref23","article-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Region-aware diffusion for zero-shot text-driven image editing","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106777"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref27","first-page":"4328","article-title":"Diffusion-lm improves controllable text generation","volume-title":"NeurIPS","volume":"35","author":"Li","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref33","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref35","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Gpt-4o: Multimodal large language model by openai","volume-title":"Technical report","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref39","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"issue":"140","key":"ref42","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"JMLR"},{"issue":"2","key":"ref43","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref47","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref48","first-page":"1","article-title":"Serengil and Alper Ozpinar","volume-title":"ICEET","author":"Ilkin","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00092"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91672-4_2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref56","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref57","article-title":"Designing a better asymmetric vqgan for stablediffusion","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445268.pdf?arnumber=11445268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:54Z","timestamp":1777611354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01549","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}