{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4NPFM3BCTFGQ73TF4HU4Z7QWW","short_pith_number":"pith:V4NPFM3B","schema_version":"1.0","canonical_sha256":"af1af2b36114ca687f732f0f4e67f0b587973cd5ac1edddcb048ef364a32705c","source":{"kind":"arxiv","id":"2311.17042","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Diffusion Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Blattmann, Axel Sauer, Dominik Lorenz, Robin Rombach","submitted_at":"2023-11-28T18:53:24Z","abstract_excerpt":"We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal in combination with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps. Our analyses show that our model clearly outperforms existing few-step methods (GANs, Latent Consistency Models) in a single step and reaches the performan"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.17042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:24Z","cross_cats_sorted":[],"title_canon_sha256":"0195b51d71db112bf60308503f16edf9ba79a67984e900d7e6970d3b833613e3","abstract_canon_sha256":"2e31a8ceb383ad1d26bfdfe002153b334f13bcb29f128e0175bb6d444b349a53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:49.936332Z","signature_b64":"O8hYe6u6RAT3cMhsWXfZF2UrqmV1/7B34FR2pC9179imbuOHFTak918FsPwnQBwWgOvVz3yJEjugG/13ZgTtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1af2b36114ca687f732f0f4e67f0b587973cd5ac1edddcb048ef364a32705c","last_reissued_at":"2026-07-05T07:17:49.935849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:49.935849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Diffusion Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Blattmann, Axel Sauer, Dominik Lorenz, Robin Rombach","submitted_at":"2023-11-28T18:53:24Z","abstract_excerpt":"We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal in combination with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps. Our analyses show that our model clearly outperforms existing few-step methods (GANs, Latent Consistency Models) in a single step and reaches the performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17042","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.17042/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.17042","created_at":"2026-07-05T07:17:49.935907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17042v1","created_at":"2026-07-05T07:17:49.935907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17042","created_at":"2026-07-05T07:17:49.935907+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4NPFM3BCTFG","created_at":"2026-07-05T07:17:49.935907+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4NPFM3BCTFGQ73T","created_at":"2026-07-05T07:17:49.935907+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4NPFM3B","created_at":"2026-07-05T07:17:49.935907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22394","citing_title":"Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20416","citing_title":"On the Redundancy of Timestep Embeddings in Diffusion Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19961","citing_title":"Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02317","citing_title":"NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13247","citing_title":"EPIG: Emotion-Based Prompting for Personalised Image Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06901","citing_title":"LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31340","citing_title":"Scenario-conditioned flow matching for probabilistic generation of three-component ground-motion waveforms","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23996","citing_title":"Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2304.09479","citing_title":"DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21573","citing_title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16259","citing_title":"Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21272","citing_title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14876","citing_title":"Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00090","citing_title":"It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2405.08748","citing_title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12557","citing_title":"One Step Diffusion via Shortcut Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06061","citing_title":"PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06940","citing_title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26244","citing_title":"MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW","json":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW.json","graph_json":"https://pith.science/api/pith-number/V4NPFM3BCTFGQ73TF4HU4Z7QWW/graph.json","events_json":"https://pith.science/api/pith-number/V4NPFM3BCTFGQ73TF4HU4Z7QWW/events.json","paper":"https://pith.science/paper/V4NPFM3B"},"agent_actions":{"view_html":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW","download_json":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW.json","view_paper":"https://pith.science/paper/V4NPFM3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17042&json=true","fetch_graph":"https://pith.science/api/pith-number/V4NPFM3BCTFGQ73TF4HU4Z7QWW/graph.json","fetch_events":"https://pith.science/api/pith-number/V4NPFM3BCTFGQ73TF4HU4Z7QWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW/action/storage_attestation","attest_author":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW/action/author_attestation","sign_citation":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW/action/citation_signature","submit_replication":"https://pith.science/pith/V4NPFM3BCTFGQ73TF4HU4Z7QWW/action/replication_record"}},"created_at":"2026-07-05T07:17:49.935907+00:00","updated_at":"2026-07-05T07:17:49.935907+00:00"}