{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EAFCO5DO2DR57QEBMSDITZJ6HO","short_pith_number":"pith:EAFCO5DO","schema_version":"1.0","canonical_sha256":"200a27746ed0e3dfc081648689e53e3bafd7270b462b20ea2ef31d117b88ba78","source":{"kind":"arxiv","id":"2501.14046","version":1},"attestation_state":"computed","paper":{"title":"LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adil Khan, Andrey Palaev, Syed M. Ahsan Kazmi","submitted_at":"2025-01-23T19:26:14Z","abstract_excerpt":"The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance level. While existing methods offer some control through fine-tuning or auxiliary information, they often face limitations in flexibility and accuracy. To address these challenges, we propose a pipeline leveraging Large Language Models (LLMs), open-vocabulary detectors, cross-attention maps and intermediate activations of diffusion U-Net for instance-level im"},"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":"2501.14046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T19:26:14Z","cross_cats_sorted":[],"title_canon_sha256":"30a974a31a1213dcee1f9bb7cd12732321d6dbdb8529fe12df87227dc4d660ed","abstract_canon_sha256":"8508fcb1e112303dae7a93dbd9cdb2283ec44a6508e7b5c62abef7bbf0f7e210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:44.554811Z","signature_b64":"aDAPHgS4w0dkeV1iPPquaHqtkIWB//dgFxqBB1PAI/lQW6jUydLv9EN7SNjaxpH5ob8+X98YwfSvwGVa+HhtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"200a27746ed0e3dfc081648689e53e3bafd7270b462b20ea2ef31d117b88ba78","last_reissued_at":"2026-07-05T10:04:44.554402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:44.554402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adil Khan, Andrey Palaev, Syed M. Ahsan Kazmi","submitted_at":"2025-01-23T19:26:14Z","abstract_excerpt":"The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance level. While existing methods offer some control through fine-tuning or auxiliary information, they often face limitations in flexibility and accuracy. To address these challenges, we propose a pipeline leveraging Large Language Models (LLMs), open-vocabulary detectors, cross-attention maps and intermediate activations of diffusion U-Net for instance-level im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14046","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/2501.14046/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":"2501.14046","created_at":"2026-07-05T10:04:44.554458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14046v1","created_at":"2026-07-05T10:04:44.554458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14046","created_at":"2026-07-05T10:04:44.554458+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAFCO5DO2DR5","created_at":"2026-07-05T10:04:44.554458+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAFCO5DO2DR57QEB","created_at":"2026-07-05T10:04:44.554458+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAFCO5DO","created_at":"2026-07-05T10:04:44.554458+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/EAFCO5DO2DR57QEBMSDITZJ6HO","json":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO.json","graph_json":"https://pith.science/api/pith-number/EAFCO5DO2DR57QEBMSDITZJ6HO/graph.json","events_json":"https://pith.science/api/pith-number/EAFCO5DO2DR57QEBMSDITZJ6HO/events.json","paper":"https://pith.science/paper/EAFCO5DO"},"agent_actions":{"view_html":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO","download_json":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO.json","view_paper":"https://pith.science/paper/EAFCO5DO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14046&json=true","fetch_graph":"https://pith.science/api/pith-number/EAFCO5DO2DR57QEBMSDITZJ6HO/graph.json","fetch_events":"https://pith.science/api/pith-number/EAFCO5DO2DR57QEBMSDITZJ6HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO/action/storage_attestation","attest_author":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO/action/author_attestation","sign_citation":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO/action/citation_signature","submit_replication":"https://pith.science/pith/EAFCO5DO2DR57QEBMSDITZJ6HO/action/replication_record"}},"created_at":"2026-07-05T10:04:44.554458+00:00","updated_at":"2026-07-05T10:04:44.554458+00:00"}