{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T12:13:35Z","timestamp":1788783215660,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376565","type":"print"},{"value":"9783032376572","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-37657-2_22","type":"book-chapter","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T11:58:51Z","timestamp":1788782331000},"page":"392-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Conditioning Matters: Stabilizing Inversion and\u00a0Attention in\u00a0Diffusion Image Editing"],"prefix":"10.1007","author":[{"given":"Zheyuan","family":"Zhan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinfei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoshi","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Defang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"22_CR1","unstructured":"Black-Forest: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Brack, M., et al.: Limitless image editing using text-to-image models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: Masactrl: tuning-free mutual self-attention control for consistent image synthesis and editing. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"22_CR4","unstructured":"Chen, D., Zhou, Z., Wang, C., Shen, C., Lyu, S.: On the trajectory regularity of ode-based diffusion sampling. In: ICML (2024)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Datta, S., Ku, A., Ramachandran, D., Anderson, P.: Prompt expansion for adaptive text-to-image generation. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-long.189"},{"key":"22_CR6","unstructured":"Deng, Y., He, X., Mei, C., Wang, P., Tang, F.: Fireflow: fast inversion of rectified flow for image semantic editing. In: ICML (2025)"},{"key":"22_CR7","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: ICML (2024)"},{"key":"22_CR8","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross-attention control. In: ICLR (2023)"},{"key":"22_CR9","unstructured":"Jiao, G., Huang, B., Wang, K.C., Liao, R.: Uniedit-flow: unleashing inversion and editing in the era of flow models (2025). arXiv:2504.13109"},{"key":"22_CR10","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: Direct inversion: boosting diffusion-based editing with 3 lines of code (2023). arXiv:2310.01506"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Zero-shot medical image translation via frequency-guided diffusion models. IEEE Trans. Med. Imaging (2023)","DOI":"10.1109\/TMI.2023.3325703"},{"key":"22_CR13","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: ICLR (2023)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lu, S., Liu, Y., Kong, A.W.K.: TF-icon: diffusion-based training-free cross-domain image composition. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"22_CR15","unstructured":"Meiri, B., Samuel, D., Darshan, N., Chechik, G., Avidan, S., Ben-Ari, R.: Fixed-point inversion for text-to-image diffusion models (2023). arXiv:2312.12540"},{"key":"22_CR16","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"22_CR18","unstructured":"Nie, S., Guo, H.A., Lu, C., Zhou, Y., Zheng, C., Li, C.: The blessing of randomness: SDE beats ode in general diffusion-based image editing. In: ICLR (2023)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: ACM SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Garibi, D., Azuri, I., Averbuch-Elor, H., Cohen-Or, D.: Localizing object-level shape variations with text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR23","unstructured":"Rout, L., Chen, Y., Ruiz, N., Caramanis, C., Shakkottai, S., Chu, W.S.: Semantic image inversion and editing using rectified stochastic differential equations. In: ICLR (2025)"},{"key":"22_CR24","unstructured":"Stanczuk, J.P., Batzolis, G., Deveney, T., Sch\u00f6nlieb, C.B.: Diffusion models encode the intrinsic dimension of data manifolds. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"22_CR25","unstructured":"Su, X., Song, J., Meng, C., Ermon, S.: Dual diffusion implicit bridges for image-to-image translation. In: ICLR (2023)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Tang, R., et al.: What the DAAM: interpreting stable diffusion using cross attention. In: ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"22_CR27","unstructured":"Tewel, Y., Gal, R., Samuel, D., Atzmon, Y., Wolf, L., Chechik, G.: Training-free object insertion in images with pretrained diffusion models (2024). arXiv:2411.07232"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"22_CR29","unstructured":"Wang, J., et al.: Taming rectified flow for inversion and editing. In: ICML (2025)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Wu, C.H., De\u00a0la Torre, F.: A latent space of stochastic diffusion models for zero-shot image editing and guidance. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: Unveil inversion and invariance in flow transformer for versatile image editing. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02652"},{"key":"22_CR32","unstructured":"Zhan, Z., et al.: Conditional image synthesis with diffusion models: a survey. TMLR (2025)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, T., Zhang, S., Shao, J., Tang, Y.: KV-edit: training-free image editing for precise background preservation (2025). arXiv:2502.17363","DOI":"10.1109\/ICCV51701.2025.01542"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37657-2_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T11:59:03Z","timestamp":1788782343000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37657-2_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"ISBN":["9783032376565","9783032376572"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37657-2_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"assertion":[{"value":"8 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}