{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:08:12Z","timestamp":1776290892993,"version":"3.50.1"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733895","type":"print"},{"value":"9783031733901","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73390-1_25","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:24:01Z","timestamp":1730305441000},"page":"428-447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Distilling Diffusion Models Into Conditional GANs"],"prefix":"10.1007","author":[{"given":"Minguk","family":"Kang","sequence":"first","affiliation":[]},{"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Connelly","family":"Barnes","sequence":"additional","affiliation":[]},{"given":"Sylvain","family":"Paris","sequence":"additional","affiliation":[]},{"given":"Suha","family":"Kwak","sequence":"additional","affiliation":[]},{"given":"Jaesik","family":"Park","sequence":"additional","affiliation":[]},{"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[]},{"given":"Jun-Yan","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Taesung","family":"Park","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Ascher, U.M., Petzold, L.R.: Computer Methods for Ordinary Differential Equations and Differential-algebraic Equations. SIAM (1998)","DOI":"10.1137\/1.9781611971392"},{"key":"25_CR2","unstructured":"Atkinson, K.: An Introduction to Numerical Analysis. Wiley (1991)"},{"key":"25_CR3","unstructured":"Berthelot, D., et al.: TRACT: denoising diffusion models with transitive closure time-distillation. arXiv preprint arXiv:2303.04248 (2023)"},{"key":"25_CR4","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"25_CR5","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Pixart-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. In: International Conference on Learning Representations (ICLR) (2024)","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., et al.: Speed is all you need: on-device acceleration of large diffusion models via GPU-aware optimizations. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"25_CR10","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"25_CR11","unstructured":"Dosovitskiy, A., Brox, T.: Generating images with perceptual similarity metrics based on deep networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"25_CR12","unstructured":"Fu, S., et al.: DreamSim: learning new dimensions of human visual similarity using synthetic data. In: Conference on Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"25_CR13","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., Cohen-or, D.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"25_CR14","unstructured":"Goodfellow, I.: NIPS 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)"},{"key":"25_CR15","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Conference on Neural Information Processing Systems (NeurIPS) (2014)"},{"key":"25_CR16","unstructured":"Gu, J., Zhai, S., Zhang, Y., Liu, L., Susskind, J.M.: BOOT: data-free distillation of denoising diffusion models with bootstrapping. In: ICML 2023 Workshop on Structured Probabilistic Inference and Generative Modeling (2023)"},{"key":"25_CR17","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"25_CR18","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPscore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"25_CR20","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"25_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Advances in Neural Information Processing Systems Deep Learning and Representation Learning Workshop (2015)"},{"key":"25_CR22","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"25_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"25_CR24","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: Conference on Neural Information Processing Systems (NeurIPS) Workshop (2022)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Huber, P.J.: Robust estimation of a location parameter. In: Breakthroughs in Statistics: Methodology and distribution (1992)","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"25_CR26","unstructured":"Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"25_CR29","unstructured":"Kang, M., Shim, W., Cho, M., Park, J.: Rebooting ACGAN: auxiliary classifier GANs with stable training. In: Conference on Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"25_CR31","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"25_CR32","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"25_CR35","unstructured":"Kettunen, M., H\u00e4rk\u00f6nen, E., Lehtinen, J.: E-LPIPS: robust perceptual image similarity via random transformation ensembles. arXiv preprint arXiv:1906.03973 (2019)"},{"key":"25_CR36","unstructured":"Kim, D., et al.: Consistency trajectory models: learning probability flow ODE trajectory of diffusion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"25_CR37","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"25_CR38","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Ph.D. thesis, University of Toronto (2012)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"25_CR40","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"25_CR41","unstructured":"Li, M., Lin, J., Meng, C., Ermon, S., Han, S., Zhu, J.Y.: Efficient spatially sparse inference for conditional GANs and diffusion models. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"25_CR42","unstructured":"Li, Y., et al.: SnapFusion: text-to-image diffusion model on mobile devices within two seconds. In: Conference on Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3d content creation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"25_CR44","unstructured":"Lin, S., Wang, A., Yang, X.: SDXL-Lightning: progressive adversarial diffusion distillation. arXiv preprint arXiv:2402.13929 (2024)"},{"key":"25_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Liu, M.Y., et al.: Few-shot Unsupervised Image-to-Image Translation. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01065"},{"key":"25_CR47","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"25_CR48","unstructured":"Liu, X., Zhang, X., Ma, J., Peng, J., Liu, Q.: InstaFlow: one step is enough for high-quality diffusion-based text-to-image generation. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"25_CR49","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-Solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"25_CR50","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-Solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"25_CR51","unstructured":"Luhman, E., Luhman, T.: Knowledge distillation in iterative generative models for improved sampling speed. arXiv preprint arXiv:2101.02388 (2021)"},{"key":"25_CR52","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)"},{"key":"25_CR53","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"25_CR55","unstructured":"Mescheder, L., Nowozin, S., Geiger, A.: Which training methods for GANs do actually Converge? In: International Conference on Machine Learning (ICML) (2018)"},{"key":"25_CR56","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"25_CR57","unstructured":"Miyato, T., Koyama, M.: cGANs with projection discriminator. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"25_CR59","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.Y.: Contrastive learning for unpaired image-to-image translation. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"25_CR61","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"25_CR62","unstructured":"Park, T., et al.: Swapping autoencoder for deep image manipulation. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"25_CR63","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"25_CR64","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"25_CR65","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"25_CR66","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning (ICML) (2016)"},{"key":"25_CR67","unstructured":"Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: Conference on Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"25_CR68","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGAN encoder for image-to-image translation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"25_CR69","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"25_CR70","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: Stable diffusion. https:\/\/github.com\/CompVis\/stable-diffusion. Accessed 06 Nov 2022"},{"key":"25_CR71","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: Stable diffusion 1.5. https:\/\/github.com\/runwayml\/stable-diffusion. Accessed 06 Nov 2022"},{"key":"25_CR72","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"25_CR73","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"25_CR74","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"25_CR75","unstructured":"Sauer, A., Boesel, F., Dockhorn, T., Blattmann, A., Esser, P., Rombach, R.: Fast high-resolution image synthesis with latent adversarial diffusion distillation. arXiv preprint arXiv:2403.12015 (2024)"},{"key":"25_CR76","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., Aila, T.: StyleGAN-T: unlocking the power of GANs for fast large-scale text-to-image synthesis. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023)","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"25_CR78","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: StyleGAN-xl: Scaling StyleGAN to large diverse datasets. In: ACM SIGGRAPH 2022 Conference Proceedings (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"25_CR79","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"25_CR80","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR81","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"25_CR82","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"25_CR83","unstructured":"Song, Y., Dhariwal, P.: Improved techniques for training consistency models. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"25_CR84","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"25_CR85","unstructured":"Song, Y., Garg, S., Shi, J., Ermon, S.: Sliced score matching: A scalable approach to density and score estimation. In: Uncertainty in Artificial Intelligence. PMLR (2020)"},{"key":"25_CR86","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"25_CR87","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1162\/NECO_a_00142","volume":"23","author":"P Vincent","year":"2011","unstructured":"Vincent, P.: A connection between score matching and denoising autoencoders. Neural Comput. 23, 1661\u20131674 (2011)","journal-title":"Neural Comput."},{"key":"25_CR88","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"25_CR89","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"25_CR90","unstructured":"Wang, Z., Zheng, H., He, P., Chen, W., Zhou, M.: Diffusion-GAN: training GANs with Diffusion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"25_CR91","unstructured":"Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"25_CR92","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"25_CR93","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhao, Y., Xiao, Z., Hou, T.: UFOGen: you forward once large scale text-to-image generation via diffusion gans. arXiv preprint arXiv:2311.09257 (2023)","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"25_CR94","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: One-step diffusion with distribution matching distillation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"25_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"25_CR96","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"25_CR97","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"25_CR98","unstructured":"Zhao, S., et al.: Large scale image completion via co-modulated generative adversarial networks. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"25_CR99","unstructured":"Zhao, S., Liu, Z., Lin, J., Zhu, J.Y., Han, S.: Differentiable augmentation for data-efficient GAN training. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"25_CR100","unstructured":"Zheng, H., Nie, W., Vahdat, A., Azizzadenesheli, K., Anandkumar, A.: Fast sampling of diffusion models via operator learning. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"25_CR101","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73390-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:35:09Z","timestamp":1732977309000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73390-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733895","9783031733901"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73390-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}