The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
On Distillation of Guided Diffusion Models
Abstract
Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALL.E 2, Stable Diffusion and Imagen. However, a downside of classifier-free guided diffusion models is that they are computationally expensive at inference time since they require evaluating two diffusion models, a class-conditional model and an unconditional model, tens to hundreds of times. To deal with this limitation, we propose an approach to distilling classifier-free guided diffusion models into models that are fast to sample from: Given a pre-trained classifier-free guided model, we first learn a single model to match the output of the combined conditional and unconditional models, and then we progressively distill that model to a diffusion model that requires much fewer sampling steps. For standard diffusion models trained on the pixel-space, our approach is able to generate images visually comparable to that of the original model using as few as 4 sampling steps on ImageNet$64\times 64$and CIFAR-10, achieving FID/IS scores comparable to that of the original model while being up to 256 times faster to sample from. For diffusion models trained on the latent-space (e.g., Stable Diffusion), our approach is able to generate high-fidelity images using as few as 1 to 4 denoising steps, accelerating inference by at least 10-fold compared to existing methods on ImageNet$256\times 256$and LAION datasets. We further demonstrate the effectiveness of our approach on text-guided image editing and inpainting, where our distilled model is able to generate high-quality results using as few as 2–4 denoising steps.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Self-citationLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
Self-citationGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Self-citationDiffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528
Self-citationHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 2×
“, 2021), DALL·E 2 (Ramesh et al., 2022), and Imagen (Saharia et al.”
Denoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507
Self-citationZero-shot text-to-image generation
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021) · arXiv · doi:10.48550/arxiv.2102.12092 · Cited by 2,417
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953
Self-citationImproved Denoising Diffusion Probabilistic Models
Nichol, A., & Dhariwal, P. (2021) · arXiv · doi:10.48550/arxiv.2102.09672 · Cited by 1,550 · cited 1×
“[22] Alex Nichol and Prafulla Dhariwal.”
Generative Modeling by Estimating Gradients of the Data Distribution
Song, Y., & Ermon, S. (2019) · arXiv · doi:10.48550/arxiv.1907.05600 · Cited by 1,453
Self-citationGLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357
Classifier-Free Diffusion Guidance
Ho, J., & Salimans, T. (2022) · arXiv · doi:10.48550/arxiv.2207.12598 · Cited by 1,126
Self-citationResolution-robust Large Mask Inpainting with Fourier Convolutions
Suvorov, R., Logacheva, E., Mashikhin, A., Remizova, A., Ashukha, A., Silvestrov, A., Kong, N., Goka, H., Park, K., & Lempitsky, V. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv51458.2022.00323 · Cited by 1,123
LAION-5B: An open large-scale dataset for training next generation image-text models
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.08402 · Cited by 1,022
Pseudo Numerical Methods for Diffusion Models on ManifoldsPreprint
Liu, L., Ren, Y., Lin, Z., & Zhao, Z. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.09778 · Cited by 892
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
Self-citationElucidating the Design Space of Diffusion-Based Generative Models
Karras, T., Aittala, M., Aila, T., & Laine, S. (2022) · neural information processing systems · doi:10.52202/068431-1926 · Cited by 538
Cascaded Diffusion Models for High Fidelity Image Generation
Ho, J., Saharia, C., Chan, W., Fleet, D. J., Norouzi, M., & Salimans, T. (2021) · arXiv · doi:10.48550/arxiv.2106.15282 · Cited by 514
Self-citationDPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., & Zhu, J. (2022) · neural information processing systems · doi:10.52202/068431-0418 · Cited by 464
Knowledge Distillation in Iterative Generative Models for Improved Sampling SpeedPreprint
Luhman, E., & Luhman, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.02388 · Cited by 444
Improved Precision and Recall Metric for Assessing Generative Models
Kynkäänniemi, T., Karras, T., Laine, S., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1904.06991 · Cited by 379
Kingma, D. P., Salimans, T., Poole, B., & Ho, J. (2021) · arXiv · doi:10.48550/arxiv.2107.00630 · Cited by 374
Self-citationScaling Autoregressive Models for Content-Rich Text-to-Image Generation
Yu, J., Xu, Y., Koh, J. Y., Luong, T., Baid, G., Wang, Z., Vasudevan, V., Ku, A., Yang, Y., Ayan, B. K., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.10789 · Cited by 371
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
Preechakul, K., Chatthee, N., Wizadwongsa, S., & Suwajanakorn, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01036 · Cited by 338
Gotta Go Fast When Generating Data with Score-Based ModelsPreprint
Jolicoeur‐Martineau, A., Li, K., Piché-Taillefer, R., Kachman, T., & Mitliagkas, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14080 · Cited by 301
Progressive Distillation for Fast Sampling of Diffusion Models
Salimans, T., & Ho, J. (2022) · arXiv · doi:10.48550/arxiv.2202.00512 · Cited by 287
Self-citationDual Diffusion Implicit Bridges for Image-to-Image TranslationPreprint
Su, X., Song, J., Meng, C., & Ermon, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.08382 · Cited by 270
Self-citationDPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., & Zhu, J. (2025) · Machine Intelligence Research · doi:10.1007/s11633-025-1562-4 · Cited by 252
Learning Fast Samplers for Diffusion Models by Differentiating Through Sample QualityPreprint
Watson, D., Chan, W., Ho, J., & Norouzi, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.05830 · Cited by 202
Self-citationGENIE: Higher-Order Denoising Diffusion Solvers
Dockhorn, T., Vahdat, A., & Kreis, K. (2022) · neural information processing systems · doi:10.52202/068431-2186 · Cited by 177
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
Xu, M., Yu, L., Song, Y., Shi, C., Ermon, S., & Tang, J. G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.02923 · Cited by 164
Self-citationD2C: Diffusion-Decoding Models for Few-Shot Conditional Generation
Sinha, A., Song, J., Meng, C., & Ermon, S. (2021) · neural information processing systems · Cited by 131
Self-citationSDEdit: Image Synthesis and Editing with Stochastic Differential EquationsPreprint
Meng, C., Song, Y. S., Song, J., Wu, J., Zhu, J.-Y., & Ermon, S. (2021) · arXiv (Cornell University) · Cited by 103
Self-citation
Cited by
Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S. W., Fidler, S., & Kreis, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02161 · Cited by 724
Self-citationA Survey on Generative Diffusion Models
Cao, H., Tan, C., Gao, Z., Xu, Y., Chen, G., Heng, P.-A., & Li, S. Z. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3361474 · Cited by 538
Liu, Y., Yang, Z., Yu, Z., Liu, Z., Liu, D., Lin, H., Li, M., Ma, S., Avdeev, M., & Shi, S. (2023) · Journal of Materiomics · doi:10.1016/j.jmat.2023.05.001 · Cited by 294
SinSR: Diffusion-Based Image Super-Resolution in a Single Step
Wang, Y., Yang, W., Chen, X., Wang, Y., Guo, L., Chau, L.-P., Liu, Z., Qiao, Y., Kot, A. C., & Wen, B. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02437 · Cited by 196
“To alleviate the training overhead, progressive distillation strategies are usually adopted [25, 35].”
MethodDiffusion Models, Image Super-Resolution, and Everything: A Survey
Moser, B. B., Shanbhag, A. S., Raue, F., Frolov, S., Palacio, S., & Dengel, A. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3476671 · Cited by 117
Metadata
- Authors
- Meng, C., Rombach, R., Gao, R., Kingma, D., Ermon, S., Ho, J., & Salimans, T.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 14297-14306
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386071831
- Cited by
- 308
- References
- 41
- FWCI
- 34.91
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.