{"work":{"id":"a7e16614-fbfc-45d6-8fb6-714035cb707c","openalex_id":null,"doi":null,"arxiv_id":"2211.01095","raw_key":null,"title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","authors":null,"authors_text":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu","year":2022,"venue":"cs.LG","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 DDIM, a first-order diffusion 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 large. 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.","external_url":"https://arxiv.org/abs/2211.01095","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-24T08:44:14.093462+00:00","pith_arxiv_id":"2211.01095","created_at":"2026-05-10T23:57:09.070459+00:00","updated_at":"2026-05-24T08:44:14.093462+00:00","title_quality_ok":true,"display_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","render_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models"},"hub":{"state":{"work_id":"a7e16614-fbfc-45d6-8fb6-714035cb707c","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":39,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2022-11-28T06:08:54+00:00","last_pith_cited_at":"2026-05-21T14:59:12+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-05T19:19:29.824167+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"method","n":3}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"use_method","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}