DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Diffusion probabilistic models (DPMs) have achieved impressive success in high-resolution image synthesis, especially in recent large-scale text-to-image generation applications. An essential technique for improving the sample quality of DPMs is guided sampling, which usually needs a large guidance scale to obtain the best sample quality. The commonly-used fast sampler for guided sampling is denoising diffusion implicit models (DDIM), a first-order diffusion ordinary differential equation (ODE) solver that generally needs 100 to 250 steps for high-quality samples. Although recent works propose dedicated high-order solvers and achieve a further speedup for sampling without guidance, their effectiveness for guided sampling has not been well-tested before. In this work, we demonstrate that previous high-order fast samplers suffer from instability issues, and they even become slower than DDIM when the guidance scale grows larger. To further speed up guided sampling, we propose DPM-Solver++, a high-order solver for the guided sampling of DPMs. DPM-Solver++ solves the diffusion ODE with the data prediction model and adopts thresholding methods to keep the solution matches training data distribution. We further propose a multistep variant of DPM-Solver++ to address the instability issue by reducing the effective step size. Experiments show that DPM-Solver++ can generate high-quality samples within only 15 to 20 steps for guided sampling by pixel-space and latent-space DPMs.
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
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
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712 · cited 13×
“We can rewrite DPM-Solver++(2S) by: and Discrete-time DPMs (Ho et al., 2020) train the noise prediction model (cid:15) θ at N fixed time steps { t n } Nn =1 and the noise prediction model is parameterized by ˜ (cid:15) θ ( x n , 1000 n N ) for n = 1 , . . . , N , where each x n is corresponding to…”
InfluentialGANs 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
Diffusion 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 · cited 4×
“1 INTRODUCTION Diffusion probabilistic models (DPMs) (Sohl-Dickstein et al., 2015; Ho et al., 2020; Song et al., 2021b) have achieved impressive success on various tasks, such as high-resolution image synthesis (Dhariwal & Nichol, 2021; Ho et al.”
InfluentialPhotorealistic 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 · cited 10×
“The second challenge is the “train-test mismatch” problem (Saharia et al., 2022b).”
InfluentialHierarchical 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 3×
“…& Nichol, 2021; Ho & Salimans, 2021) is a widely-used technique to apply DPMs for conditional sampling, which is useful in text-to-image, image-to-image, and class-to-image applications (Dhariwal & Nichol, 2021; Saharia et al., 2022b; Rombach et al., 2022; Nichol et al., 2021; Ramesh et al., 2022).”
Denoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507 · cited 6×
“A special case is k = 1 , where the solver is the same as DDIM (Song et al., 2021a), and we discuss in Sec.”
InfluentialScore-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 · cited 10×
“Specifically, sampling by diffusion ODEs need to discretize the following ODE (Song et al., 2021b) with t changing from T to 0 : and the equivalent diffusion ODE w.r.t. the data prediction model x θ is where the coefficients Kingma et al., 2021).”
InfluentialPalette: Image-to-Image Diffusion Models
Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., & Norouzi, M. (2022) · Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings · doi:10.1145/3528233.3530757 · Cited by 1,717
Improved Denoising Diffusion Probabilistic Models
Nichol, A., & Dhariwal, P. (2021) · arXiv · doi:10.48550/arxiv.2102.09672 · Cited by 1,550 · cited 2×
“Moreover, for the widely-used DDPM (Ho et al., 2020), we usually choose a sequence { β n } Nn =1 which is defined by either linear schedule (Ho et al., 2020) or cosine schedule (Nichol & Dhariwal, 2021).”
GLIDE: 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 · cited 6×
“…pairs from the MS-COCO2014 validation dataset and use the captions as conditions to draw 10K images from the pretrained “stable-diffusion” model, and we only draw a single image sample of each caption, following the standard evaluation procedures in (Nichol et al., 2021; Rombach et al., 2022).”
InfluentialClassifier-Free Diffusion Guidance
Ho, J., & Salimans, T. (2022) · arXiv · doi:10.48550/arxiv.2207.12598 · Cited by 1,126 · cited 3×
“Classifier-free guidance (Ho & Salimans, 2021) shares the same parameterized model (cid:15) θ ( x t , t, c ) for the unconditional and conditional noise prediction models, where the input c for the unconditional model is a special placeholder ∅ .”
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
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., & Guo, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01043 · Cited by 720 · cited 1×
“…et al., 2022a; Zhao et al., 2022), text-to-image generation (Nichol et al., 2021; Saharia et al., 2022b; Ramesh et al., 2022; Rombach et al., 2022; Gu et al., 2022), voice synthesis (Liu et al., 2022a; Chen et al., 2021a;b), molecule generation (Xu et al., 2022; Hoogeboom et al., 2022; Wu et al.,…”
Elucidating the Design Space of Diffusion-Based Generative Models
Karras, T., Aittala, M., Aila, T., & Laine, S. (2022) · arXiv · doi:10.48550/arxiv.2206.00364 · Cited by 702
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
Kingma, D. P., Salimans, T., Poole, B., & Ho, J. (2021) · arXiv · doi:10.48550/arxiv.2107.00630 · Cited by 374
Progressive Distillation for Fast Sampling of Diffusion Models
Salimans, T., & Ho, J. (2022) · arXiv · doi:10.48550/arxiv.2202.00512 · Cited by 287
Score-based Generative Modeling in Latent Space
Vahdat, A., Kreis, K., & Kautz, J. (2021) · arXiv · doi:10.48550/arxiv.2106.05931 · Cited by 224
Song, Y., Dhariwal, P., Chen, M., & Sutskever, I. (2023) · arXiv · doi:10.48550/arxiv.2303.01469 · Cited by 155
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
Blattmann, A., Dockhorn, T., Kulal, S., Mendelevitch, D., Kilian, M., Lorenz, D., Levi, Y., English, Z., Voleti, V., Letts, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.15127 · Cited by 105
On Fast Sampling of Diffusion Probabilistic Models
Kong, Z., & Ping, W. (2021) · arXiv · doi:10.48550/arxiv.2106.00132 · Cited by 79
Noise Estimation for Generative Diffusion Models
San-Roman, R., Nachmani, E., & Wolf, L. (2021) · arXiv · doi:10.48550/arxiv.2104.02600 · Cited by 44 · cited 2×
“Samplers based on extra training include model distillation (Salimans & Ho, 2022; Luhman & Luhman, 2021), learning reverse process variances (San-Roman et al., 2021; Nichol & Dhariwal, 2021; Bao et al., 2022a), and learning sampling steps (Lam et al.”
WorldSimBench: Towards Video Generation Models as World Simulators
Qin, Y., Shi, Z., Yu, J., Wang, X., Zhou, E., Li, L., Yin, Z., Liu, X., Sheng, L., Shao, J., et al. (2024) · arXiv · doi:10.48550/arxiv.2410.18072 · Cited by 3
Cited by
A 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
Probabilistic weather forecasting with machine learning
Price, I., Sanchez-Gonzalez, A., Alet, F., Andersson, T. R., El-Kadi, A., Masters, D., Ewalds, T., Stott, J., Mohamed, S., Battaglia, P., et al. (2025) · Nature · doi:10.1038/s41586-024-08252-9 · Cited by 434
“We use the second-order DPMSolver++2S solver 53 , augmented with the stochastic churn (again making use of P noise ) and noise inflation techniques used in ref.”
On Distillation of Guided Diffusion Models
Meng, C., Rombach, R., Gao, R., Kingma, D., Ermon, S., Ho, J., & Salimans, T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01374 · Cited by 308
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Höllein, L., Cao, A., Owens, A., Johnson, J., & Nießner, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00727 · Cited by 167
“We generate a single inpainting proposal and employ a state-of-the-art guided diffusion sampler [43].”
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
“In a later work, Lu et al. [94] introduced an improved version with DPM-solver ++ that essentially approximates the predicted image instead of the error.”
Metadata
- Authors
- Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., & Zhu, J.
- Venue
- Machine Intelligence Research
- Published
- 2025-06-23
- Volume
- 22
- Issue
- 4
- Pages
- 730-751
- ISSN
- 1476-8186 (ISSN-L)
- 2731-538X
- 2731-5398
- OpenAlex
- W4411528087
- Cited by
- 252
- References
- 26
- FWCI
- 63.30
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.