{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HWD5WEDMGTC2FAN62PQS5HHB6W","short_pith_number":"pith:HWD5WEDM","schema_version":"1.0","canonical_sha256":"3d87db106c34c5a281bed3e12e9ce1f59df8196163e7580c568e3b2d7ce7bd12","source":{"kind":"arxiv","id":"2401.02677","version":1},"attestation_state":"computed","paper":{"title":"Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Harish Prabhala, Patrick von Platen, Sayak Paul, Vishnu V. Jaddipal, Yatharth Gupta","submitted_at":"2024-01-05T07:21:46Z","abstract_excerpt":"Stable Diffusion XL (SDXL) has become the best open source text-to-image model (T2I) for its versatility and top-notch image quality. Efficiently addressing the computational demands of SDXL models is crucial for wider reach and applicability. In this work, we introduce two scaled-down variants, Segmind Stable Diffusion (SSD-1B) and Segmind-Vega, with 1.3B and 0.74B parameter UNets, respectively, achieved through progressive removal using layer-level losses focusing on reducing the model size while preserving generative quality. We release these models weights at https://hf.co/Segmind. Our met"},"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":"2401.02677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T07:21:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ed09178eb011ab3257a1d4e702f3ebc9c306e10ef3a950dbbe90a53b9a809c2","abstract_canon_sha256":"5d98ee81ea6ef775e0b7414efcf600ef259a129f8635cbc976eef047cc7dbdf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:29.652109Z","signature_b64":"pyjVBsTzols4mco9uI/3JLpMqu7HBq3kpW9Y/bR3hIKwnHToF8ML1rxxnSumZB38tk27jzZz7hueMlsKKW15Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d87db106c34c5a281bed3e12e9ce1f59df8196163e7580c568e3b2d7ce7bd12","last_reissued_at":"2026-07-05T07:30:29.651698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:29.651698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Harish Prabhala, Patrick von Platen, Sayak Paul, Vishnu V. Jaddipal, Yatharth Gupta","submitted_at":"2024-01-05T07:21:46Z","abstract_excerpt":"Stable Diffusion XL (SDXL) has become the best open source text-to-image model (T2I) for its versatility and top-notch image quality. Efficiently addressing the computational demands of SDXL models is crucial for wider reach and applicability. In this work, we introduce two scaled-down variants, Segmind Stable Diffusion (SSD-1B) and Segmind-Vega, with 1.3B and 0.74B parameter UNets, respectively, achieved through progressive removal using layer-level losses focusing on reducing the model size while preserving generative quality. We release these models weights at https://hf.co/Segmind. Our met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02677","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/2401.02677/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":"2401.02677","created_at":"2026-07-05T07:30:29.651753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02677v1","created_at":"2026-07-05T07:30:29.651753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02677","created_at":"2026-07-05T07:30:29.651753+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWD5WEDMGTC2","created_at":"2026-07-05T07:30:29.651753+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWD5WEDMGTC2FAN6","created_at":"2026-07-05T07:30:29.651753+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWD5WEDM","created_at":"2026-07-05T07:30:29.651753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17378","citing_title":"RISE: Relay Inference and Online Scheduling for Efficient Edge-Device Collaborative Diffusion Model Services","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19729","citing_title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19729","citing_title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19729","citing_title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12966","citing_title":"Boosting Visual Instruction Tuning with Self-Supervised Guidance","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16879","citing_title":"Adaptive Forensic Feature Refinement via Intrinsic Importance Perception","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17736","citing_title":"IncreFA: Breaking the Static Wall of Generative Model Attribution","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W","json":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W.json","graph_json":"https://pith.science/api/pith-number/HWD5WEDMGTC2FAN62PQS5HHB6W/graph.json","events_json":"https://pith.science/api/pith-number/HWD5WEDMGTC2FAN62PQS5HHB6W/events.json","paper":"https://pith.science/paper/HWD5WEDM"},"agent_actions":{"view_html":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W","download_json":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W.json","view_paper":"https://pith.science/paper/HWD5WEDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02677&json=true","fetch_graph":"https://pith.science/api/pith-number/HWD5WEDMGTC2FAN62PQS5HHB6W/graph.json","fetch_events":"https://pith.science/api/pith-number/HWD5WEDMGTC2FAN62PQS5HHB6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W/action/storage_attestation","attest_author":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W/action/author_attestation","sign_citation":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W/action/citation_signature","submit_replication":"https://pith.science/pith/HWD5WEDMGTC2FAN62PQS5HHB6W/action/replication_record"}},"created_at":"2026-07-05T07:30:29.651753+00:00","updated_at":"2026-07-05T07:30:29.651753+00:00"}