{"work":{"id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","openalex_id":null,"doi":null,"arxiv_id":"2010.02502","raw_key":null,"title":"Denoising Diffusion Implicit Models","authors":null,"authors_text":"Jiaming Song, Chenlin Meng, and Stefano Ermon","year":2020,"venue":"cs.LG","abstract":"Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose reverse process can be much faster to sample from. We empirically demonstrate that DDIMs can produce high quality samples $10 \\times$ to $50 \\times$ faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample quality, and can perform semantically meaningful image interpolation directly in the latent space.","external_url":"https://arxiv.org/abs/2010.02502","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-06-29T12:03:24.089119+00:00","pith_arxiv_id":"2010.02502","created_at":"2026-05-08T19:34:04.654737+00:00","updated_at":"2026-06-29T12:03:24.089119+00:00","title_quality_ok":true,"display_title":"Denoising Diffusion Implicit Models","render_title":"Denoising Diffusion Implicit Models"},"hub":{"state":{"work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":446,"external_cited_by_count":null,"distinct_field_count":29,"first_pith_cited_at":"2021-01-07T06:12:28+00:00","last_pith_cited_at":"2026-06-25T03:32:12+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-29T11:58:41.924753+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":58},{"context_role":"method","n":23},{"context_role":"baseline","n":2}],"polarity_counts":[{"context_polarity":"background","n":56},{"context_polarity":"use_method","n":23},{"context_polarity":"baseline","n":2},{"context_polarity":"support","n":1},{"context_polarity":"unclear","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Denoising Diffusion Implicit Models","claims":[{"claim_text":"Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose revers","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Denoising Diffusion Implicit Models because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:13:36.410005+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"6dd1676b-37f2-42cc-8510-9bfad718704f","orcid":null,"display_name":"Jiaming Song"},{"id":"48c1f0f1-8929-45f0-822b-bc862d2f3803","orcid":null,"display_name":"Chenlin Meng"},{"id":"93b87436-13ba-4c7a-b6a6-4d8aae7fef7c","orcid":null,"display_name":"and Stefano Ermon"}]},"error":null,"updated_at":"2026-05-13T20:13:37.136467+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T20:13:42.018261+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":51},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":48},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":42},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":37},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":31},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":30},{"title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","work_id":"0c6a768b-70b8-4242-bb0e-459f1008c9fc","shared_citers":30},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":20},{"title":"Denoising Diffusion Probabilistic Models","work_id":"dc023f4e-7c79-471c-b713-deeb559ba010","shared_citers":19},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":17},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":16},{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","work_id":"34430d19-7919-48ce-88a5-17b3bfe2192e","shared_citers":15},{"title":"Progressive Distillation for Fast Sampling of Diffusion Models","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","shared_citers":15},{"title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","work_id":"98e51b10-54bd-4251-8a2d-f79bd6215c19","shared_citers":14},{"title":"Qwen-Image Technical Report","work_id":"d06d7ecc-7579-4f89-a60b-4278a0f3c562","shared_citers":14},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":12},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":12},{"title":"Training Diffusion Models with Reinforcement Learning","work_id":"67684dda-3930-452a-b91a-36cbb8e2e219","shared_citers":12},{"title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","work_id":"2dd7e0b7-c69c-4976-a406-12d4f5b18d14","shared_citers":11},{"title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","work_id":"f38fc088-12aa-4bf4-9ecd-08d3e797ccb7","shared_citers":11},{"title":"High-Resolution Image Synthesis with Latent Diffusion Models","work_id":"f0270d36-2952-47fb-84c1-95e3ec341126","shared_citers":11},{"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","shared_citers":11},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":10},{"title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","work_id":"40702548-f094-4c67-a5db-a62f426f852e","shared_citers":10}],"time_series":[{"n":3,"year":2021},{"n":5,"year":2022},{"n":6,"year":2023},{"n":4,"year":2024},{"n":5,"year":2025},{"n":163,"year":2026}]},"error":null,"updated_at":"2026-05-13T20:13:36.498505+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T20:13:40.409099+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Denoising Diffusion Implicit Models","claims":[{"claim_text":"Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose revers","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Denoising Diffusion Implicit Models because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:13:36.502595+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Denoising Diffusion Implicit Models","claims":[{"claim_text":"Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose revers","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Denoising Diffusion Implicit Models because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:13:40.414481+00:00"}},"summary":{"title":"Denoising Diffusion Implicit Models","claims":[{"claim_text":"Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose revers","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Denoising Diffusion Implicit Models because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":51},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":48},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":42},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":37},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":31},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":30},{"title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","work_id":"0c6a768b-70b8-4242-bb0e-459f1008c9fc","shared_citers":30},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":20},{"title":"Denoising Diffusion Probabilistic Models","work_id":"dc023f4e-7c79-471c-b713-deeb559ba010","shared_citers":19},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":17},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":16},{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","work_id":"34430d19-7919-48ce-88a5-17b3bfe2192e","shared_citers":15},{"title":"Progressive Distillation for Fast Sampling of Diffusion Models","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","shared_citers":15},{"title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","work_id":"98e51b10-54bd-4251-8a2d-f79bd6215c19","shared_citers":14},{"title":"Qwen-Image Technical Report","work_id":"d06d7ecc-7579-4f89-a60b-4278a0f3c562","shared_citers":14},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":12},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":12},{"title":"Training Diffusion Models with Reinforcement Learning","work_id":"67684dda-3930-452a-b91a-36cbb8e2e219","shared_citers":12},{"title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","work_id":"2dd7e0b7-c69c-4976-a406-12d4f5b18d14","shared_citers":11},{"title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","work_id":"f38fc088-12aa-4bf4-9ecd-08d3e797ccb7","shared_citers":11},{"title":"High-Resolution Image Synthesis with Latent Diffusion Models","work_id":"f0270d36-2952-47fb-84c1-95e3ec341126","shared_citers":11},{"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","shared_citers":11},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":10},{"title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","work_id":"40702548-f094-4c67-a5db-a62f426f852e","shared_citers":10}],"time_series":[{"n":3,"year":2021},{"n":5,"year":2022},{"n":6,"year":2023},{"n":4,"year":2024},{"n":5,"year":2025},{"n":163,"year":2026}]},"authors":[{"id":"93b87436-13ba-4c7a-b6a6-4d8aae7fef7c","orcid":null,"display_name":"and Stefano Ermon","source":"manual","import_confidence":0.72},{"id":"48c1f0f1-8929-45f0-822b-bc862d2f3803","orcid":null,"display_name":"Chenlin Meng","source":"manual","import_confidence":0.72},{"id":"6dd1676b-37f2-42cc-8510-9bfad718704f","orcid":null,"display_name":"Jiaming Song","source":"manual","import_confidence":0.72}]}}