{"work":{"id":"acf2c588-c088-4a6c-938e-150ad7c666d7","openalex_id":"https://openalex.org/W4402778507","doi":"10.1109/cvpr52733.2024.02494","arxiv_id":"2207.12598","raw_key":null,"title":"Classifier-Free Diffusion Guidance","authors":null,"authors_text":"Jonathan Ho, Tim Salimans","year":2022,"venue":"cs.LG","abstract":"Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model without such a classifier: in what we call classifier-free guidance, we jointly train a conditional and an unconditional diffusion model, and we combine the resulting conditional and unconditional score estimates to attain a trade-off between sample quality and diversity similar to that obtained using classifier guidance.","external_url":"https://arxiv.org/abs/2207.12598","cited_by_count":19,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2207.12598","created_at":"2026-05-08T18:44:00.061546+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Classifier-Free Diffusion Guidance","render_title":"Classifier-Free Diffusion Guidance"},"hub":{"state":{"work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":604,"external_cited_by_count":19,"distinct_field_count":32,"first_pith_cited_at":"2022-09-29T16:27:53+00:00","last_pith_cited_at":"2026-07-09T10:21:06+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":"2026-08-22T20:39:17.395982+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"method","n":53},{"context_role":"background","n":49},{"context_role":"baseline","n":5},{"context_role":"extension","n":1},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"use_method","n":53},{"context_polarity":"background","n":45},{"context_polarity":"baseline","n":5},{"context_polarity":"unclear","n":5},{"context_polarity":"extend","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Classifier-Free Diffusion Guidance","claims":[{"claim_text":"Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model w","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Classifier-Free Diffusion Guidance because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:13:36.024501+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"c91ab32b-1b57-42d9-ae75-38fd5dc6cd26","orcid":null,"display_name":"Jonathan Ho"},{"id":"94c5dbc0-da43-4fd4-abc6-96347f32f39c","orcid":null,"display_name":"Tim Salimans"}]},"error":null,"updated_at":"2026-05-13T20:13:36.407441+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T20:03:35.672688+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":45},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":42},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":34},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":30},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":29},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":24},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":22},{"title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","work_id":"0c6a768b-70b8-4242-bb0e-459f1008c9fc","shared_citers":21},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":21},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":20},{"title":"Progressive Distillation for Fast Sampling of Diffusion Models","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","shared_citers":18},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":14},{"title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","shared_citers":13},{"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","shared_citers":13},{"title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","work_id":"f38fc088-12aa-4bf4-9ecd-08d3e797ccb7","shared_citers":12},{"title":"High-Resolution Image Synthesis with Latent Diffusion Models","work_id":"f0270d36-2952-47fb-84c1-95e3ec341126","shared_citers":12},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":12},{"title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","work_id":"0a105815-ff2e-43ce-8566-966cdcae1af4","shared_citers":12},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":11},{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","work_id":"34430d19-7919-48ce-88a5-17b3bfe2192e","shared_citers":11},{"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":11},{"title":"Imagen Video: High Definition Video Generation with Diffusion Models","work_id":"bb20d241-dc6f-4b0a-b071-fd43a2cbd57f","shared_citers":11},{"title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","work_id":"98e51b10-54bd-4251-8a2d-f79bd6215c19","shared_citers":11},{"title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","work_id":"52a801fc-a707-45a1-a8cd-0d6702f124ab","shared_citers":11}],"time_series":[{"n":1,"year":2022},{"n":6,"year":2023},{"n":10,"year":2024},{"n":5,"year":2025},{"n":164,"year":2026}]},"error":null,"updated_at":"2026-05-13T20:13:36.019430+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":"2026-05-13T20:03:34.692611+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Classifier-Free Diffusion Guidance","claims":[{"claim_text":"Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model w","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Classifier-Free Diffusion Guidance because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:13:37.139179+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Classifier-Free Diffusion Guidance","claims":[{"claim_text":"Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model w","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Classifier-Free Diffusion Guidance because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:13:36.412889+00:00"}},"summary":{"title":"Classifier-Free Diffusion Guidance","claims":[{"claim_text":"Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model w","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Classifier-Free Diffusion Guidance because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":45},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":42},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":34},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":30},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":29},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":24},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":22},{"title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","work_id":"0c6a768b-70b8-4242-bb0e-459f1008c9fc","shared_citers":21},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":21},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":20},{"title":"Progressive Distillation for Fast Sampling of Diffusion Models","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","shared_citers":18},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":14},{"title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","shared_citers":13},{"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","shared_citers":13},{"title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","work_id":"f38fc088-12aa-4bf4-9ecd-08d3e797ccb7","shared_citers":12},{"title":"High-Resolution Image Synthesis with Latent Diffusion Models","work_id":"f0270d36-2952-47fb-84c1-95e3ec341126","shared_citers":12},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":12},{"title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","work_id":"0a105815-ff2e-43ce-8566-966cdcae1af4","shared_citers":12},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":11},{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","work_id":"34430d19-7919-48ce-88a5-17b3bfe2192e","shared_citers":11},{"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":11},{"title":"Imagen Video: High Definition Video Generation with Diffusion Models","work_id":"bb20d241-dc6f-4b0a-b071-fd43a2cbd57f","shared_citers":11},{"title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","work_id":"98e51b10-54bd-4251-8a2d-f79bd6215c19","shared_citers":11},{"title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","work_id":"52a801fc-a707-45a1-a8cd-0d6702f124ab","shared_citers":11}],"time_series":[{"n":1,"year":2022},{"n":6,"year":2023},{"n":10,"year":2024},{"n":5,"year":2025},{"n":164,"year":2026}]},"authors":[{"id":"c91ab32b-1b57-42d9-ae75-38fd5dc6cd26","orcid":null,"display_name":"Jonathan Ho","source":"manual","import_confidence":0.72},{"id":"94c5dbc0-da43-4fd4-abc6-96347f32f39c","orcid":null,"display_name":"Tim Salimans","source":"manual","import_confidence":0.72}]}}