{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2IVZ7NDVJ5EXQRLLSRAUUZX4OE","short_pith_number":"pith:2IVZ7NDV","schema_version":"1.0","canonical_sha256":"d22b9fb4754f4978456b94414a66fc710931a188e7d046c6dab3a0866941ca34","source":{"kind":"arxiv","id":"2505.10743","version":1},"attestation_state":"computed","paper":{"title":"IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amritanshu Tiwari, Cherish Puniani, Kaustubh Sharma, Ojasva Nema","submitted_at":"2025-05-15T23:08:52Z","abstract_excerpt":"Recent advances in text-to-image diffusion models, particularly Stable Diffusion, have enabled the generation of highly detailed and semantically rich images. However, personalizing these models to represent novel subjects based on a few reference images remains challenging. This often leads to catastrophic forgetting, overfitting, or large computational overhead.We propose a two-stage pipeline that addresses these limitations by leveraging LoRA-based fine-tuning on the attention weights within the U-Net of the Stable Diffusion XL (SDXL) model. First, we use the unmodified SDXL to generate a g"},"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":"2505.10743","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T23:08:52Z","cross_cats_sorted":[],"title_canon_sha256":"eb8048e35dcece31f7c664abb53f0957bc4ffbd23c5004fd2ea2a86464f8ab84","abstract_canon_sha256":"e77b5a9cce567dec827c96549a5843c7f4872b9c86c866bd52e1f47c370043aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:04.736485Z","signature_b64":"PG6zzEkciFhkfknAkD9taQ2NRZaKK1TLC9PuEackGwcdaNNZjmwn6NW/wQJMLnapIi6MzQqnDNxQjIkUCQLXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22b9fb4754f4978456b94414a66fc710931a188e7d046c6dab3a0866941ca34","last_reissued_at":"2026-07-05T11:04:04.736028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:04.736028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amritanshu Tiwari, Cherish Puniani, Kaustubh Sharma, Ojasva Nema","submitted_at":"2025-05-15T23:08:52Z","abstract_excerpt":"Recent advances in text-to-image diffusion models, particularly Stable Diffusion, have enabled the generation of highly detailed and semantically rich images. However, personalizing these models to represent novel subjects based on a few reference images remains challenging. This often leads to catastrophic forgetting, overfitting, or large computational overhead.We propose a two-stage pipeline that addresses these limitations by leveraging LoRA-based fine-tuning on the attention weights within the U-Net of the Stable Diffusion XL (SDXL) model. First, we use the unmodified SDXL to generate a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10743","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/2505.10743/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":"2505.10743","created_at":"2026-07-05T11:04:04.736083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10743v1","created_at":"2026-07-05T11:04:04.736083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10743","created_at":"2026-07-05T11:04:04.736083+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IVZ7NDVJ5EX","created_at":"2026-07-05T11:04:04.736083+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IVZ7NDVJ5EXQRLL","created_at":"2026-07-05T11:04:04.736083+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IVZ7NDV","created_at":"2026-07-05T11:04:04.736083+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/2IVZ7NDVJ5EXQRLLSRAUUZX4OE","json":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE.json","graph_json":"https://pith.science/api/pith-number/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/graph.json","events_json":"https://pith.science/api/pith-number/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/events.json","paper":"https://pith.science/paper/2IVZ7NDV"},"agent_actions":{"view_html":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE","download_json":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE.json","view_paper":"https://pith.science/paper/2IVZ7NDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10743&json=true","fetch_graph":"https://pith.science/api/pith-number/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/graph.json","fetch_events":"https://pith.science/api/pith-number/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/action/storage_attestation","attest_author":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/action/author_attestation","sign_citation":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/action/citation_signature","submit_replication":"https://pith.science/pith/2IVZ7NDVJ5EXQRLLSRAUUZX4OE/action/replication_record"}},"created_at":"2026-07-05T11:04:04.736083+00:00","updated_at":"2026-07-05T11:04:04.736083+00:00"}