{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:31:30Z","timestamp":1778081490345,"version":"3.51.4"},"reference-count":65,"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"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council, Taiwan","doi-asserted-by":"publisher","award":["NSTC-112-2221-E-A49-059MY3,NSTC-112-2221-E-A49-094-MY3"],"award-info":[{"award-number":["NSTC-112-2221-E-A49-059MY3,NSTC-112-2221-E-A49-094-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01708","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18377-18387","source":"Crossref","is-referenced-by-count":1,"title":["TF-TI2I: Training-Free Text-And-Image-To-Image Generation via Multi-Modal Implicit-Context Learning in Text-To-Image Models"],"prefix":"10.1109","author":[{"given":"Teng-Fang","family":"Hsiao","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo-Kai","family":"Ruan","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Lun","family":"Wu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Ling","family":"Lin","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","first-page":"3","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref7","first-page":"3","article-title":"Pixart-delta: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32210"},{"key":"ref9","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02078"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref14","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Z-star: Zero-shot style transfer via attention rearrangement","author":"Deng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"2","author":"Du","year":"2025","journal-title":"Generative models: What do they know? do they know things? let\u2019s find out!"},{"key":"ref17","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref18","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00206"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0363"},{"key":"ref21","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32368"},{"key":"ref24","first-page":"2","article-title":"Freecond: Free lunch in the input conditions of text-guided inpainting","author":"Hsiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref27","volume-title":"Flux","year":"2024"},{"key":"ref28","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref30","first-page":"3","article-title":"Sdxllightning: Progressive adversarial diffusion distillation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681506"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00725"},{"key":"ref37","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Meng"},{"key":"ref38","first-page":"6","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"ref40","article-title":"Kosmos-g: Generating images in context with multimodal large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Pan","year":"2024"},{"key":"ref41","first-page":"3","article-title":"lambda-eclipse: Multi-concept personalized text-toimage diffusion models by leveraging clip latent space","author":"Patel","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref47","first-page":"3","article-title":"Lightning-fast image inversion and editing for text-to-image diffusion models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Samuel","year":"2025"},{"key":"ref48","first-page":"3","article-title":"Knndiffusion: Image generation via large-scale retrieval","author":"Sheynin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref55","first-page":"2","article-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"6","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"CoRR"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref58","first-page":"2","article-title":"SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xie","year":"2025"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref61","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref64","first-page":"2","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/11444708.pdf?arnumber=11444708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:50Z","timestamp":1777612010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01708","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}