{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVJWM4GWYVQBRCNJWR5MKHBTAB","short_pith_number":"pith:MVJWM4GW","schema_version":"1.0","canonical_sha256":"65536670d6c5601889a9b47ac51c330075b1868dde9d899f7595e17172a74c27","source":{"kind":"arxiv","id":"2509.06068","version":1},"attestation_state":"computed","paper":{"title":"Home-made Diffusion Model from Scratch to Hatch","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shih-Ying Yeh","submitted_at":"2025-09-07T14:21:57Z","abstract_excerpt":"We introduce Home-made Diffusion Model (HDM), an efficient yet powerful text-to-image diffusion model optimized for training (and inferring) on consumer-grade hardware. HDM achieves competitive 1024x1024 generation quality while maintaining a remarkably low training cost of $535-620 using four RTX5090 GPUs, representing a significant reduction in computational requirements compared to traditional approaches. Our key contributions include: (1) Cross-U-Transformer (XUT), a novel U-shape transformer, Cross-U-Transformer (XUT), that employs cross-attention for skip connections, providing superior "},"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":"2509.06068","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T14:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"e4bf54f1f2be8b221c4824f2f2f2e8ee5c18b8d2eeed2ea9ca9bbf279ebc640a","abstract_canon_sha256":"09d68e6e51151f19422974fe6dda37b1a463d3010ba7096a77f681a642e88288"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:29.430965Z","signature_b64":"aaUNZmPtdbekFx8oDw5aY9gu0BfZYERD4PKmsips+/4bi8UX1cgKcH4vg3y3HRa1/JF/Z8Eao1sH0jfdxgkqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65536670d6c5601889a9b47ac51c330075b1868dde9d899f7595e17172a74c27","last_reissued_at":"2026-07-05T12:06:29.430490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:29.430490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Home-made Diffusion Model from Scratch to Hatch","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shih-Ying Yeh","submitted_at":"2025-09-07T14:21:57Z","abstract_excerpt":"We introduce Home-made Diffusion Model (HDM), an efficient yet powerful text-to-image diffusion model optimized for training (and inferring) on consumer-grade hardware. HDM achieves competitive 1024x1024 generation quality while maintaining a remarkably low training cost of $535-620 using four RTX5090 GPUs, representing a significant reduction in computational requirements compared to traditional approaches. Our key contributions include: (1) Cross-U-Transformer (XUT), a novel U-shape transformer, Cross-U-Transformer (XUT), that employs cross-attention for skip connections, providing superior "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06068","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/2509.06068/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":"2509.06068","created_at":"2026-07-05T12:06:29.430543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06068v1","created_at":"2026-07-05T12:06:29.430543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06068","created_at":"2026-07-05T12:06:29.430543+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVJWM4GWYVQB","created_at":"2026-07-05T12:06:29.430543+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVJWM4GWYVQBRCNJ","created_at":"2026-07-05T12:06:29.430543+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVJWM4GW","created_at":"2026-07-05T12:06:29.430543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB","json":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB.json","graph_json":"https://pith.science/api/pith-number/MVJWM4GWYVQBRCNJWR5MKHBTAB/graph.json","events_json":"https://pith.science/api/pith-number/MVJWM4GWYVQBRCNJWR5MKHBTAB/events.json","paper":"https://pith.science/paper/MVJWM4GW"},"agent_actions":{"view_html":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB","download_json":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB.json","view_paper":"https://pith.science/paper/MVJWM4GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06068&json=true","fetch_graph":"https://pith.science/api/pith-number/MVJWM4GWYVQBRCNJWR5MKHBTAB/graph.json","fetch_events":"https://pith.science/api/pith-number/MVJWM4GWYVQBRCNJWR5MKHBTAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB/action/storage_attestation","attest_author":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB/action/author_attestation","sign_citation":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB/action/citation_signature","submit_replication":"https://pith.science/pith/MVJWM4GWYVQBRCNJWR5MKHBTAB/action/replication_record"}},"created_at":"2026-07-05T12:06:29.430543+00:00","updated_at":"2026-07-05T12:06:29.430543+00:00"}