{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5OXVYGBAKN5QLB34FBHCYOJU7Z","short_pith_number":"pith:5OXVYGBA","schema_version":"1.0","canonical_sha256":"ebaf5c1820537b05877c284e2c3934fe4cd16595cb55027efc87b9ce093e06a4","source":{"kind":"arxiv","id":"2505.23758","version":1},"attestation_state":"computed","paper":{"title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hidir Yesiltepe, Pinar Yanardag, Yusuf Dalva","submitted_at":"2025-05-29T17:59:46Z","abstract_excerpt":"We introduce LoRAShop, the first framework for multi-concept image editing with LoRA models. LoRAShop builds on a key observation about the feature interaction patterns inside Flux-style diffusion transformers: concept-specific transformer features activate spatially coherent regions early in the denoising process. We harness this observation to derive a disentangled latent mask for each concept in a prior forward pass and blend the corresponding LoRA weights only within regions bounding the concepts to be personalized. The resulting edits seamlessly integrate multiple subjects or styles into "},"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":"2505.23758","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"ac5c7a8067e3eefc0ff77c2392d3fe96909609d0842d8f3d77c35b42dc750834","abstract_canon_sha256":"c062a814cddd8178c37890cbfc27b63d363f173957ae1fb60b5f47f1f0fd74be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:13.783737Z","signature_b64":"84dJ6Qochk68Wj9u0PSEmKgUMlYR6a8hfoPrfApCPoJ583UzAPpUzayAFft9FKkSej+GNN8xvSd/b0f2LILiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebaf5c1820537b05877c284e2c3934fe4cd16595cb55027efc87b9ce093e06a4","last_reissued_at":"2026-07-05T11:12:13.783201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:13.783201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hidir Yesiltepe, Pinar Yanardag, Yusuf Dalva","submitted_at":"2025-05-29T17:59:46Z","abstract_excerpt":"We introduce LoRAShop, the first framework for multi-concept image editing with LoRA models. LoRAShop builds on a key observation about the feature interaction patterns inside Flux-style diffusion transformers: concept-specific transformer features activate spatially coherent regions early in the denoising process. We harness this observation to derive a disentangled latent mask for each concept in a prior forward pass and blend the corresponding LoRA weights only within regions bounding the concepts to be personalized. The resulting edits seamlessly integrate multiple subjects or styles into "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23758","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/2505.23758/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":"2505.23758","created_at":"2026-07-05T11:12:13.783271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23758v1","created_at":"2026-07-05T11:12:13.783271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23758","created_at":"2026-07-05T11:12:13.783271+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OXVYGBAKN5Q","created_at":"2026-07-05T11:12:13.783271+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OXVYGBAKN5QLB34","created_at":"2026-07-05T11:12:13.783271+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OXVYGBA","created_at":"2026-07-05T11:12:13.783271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03792","citing_title":"Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30431","citing_title":"DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07561","citing_title":"PureCC: Pure Learning for Text-to-Image Concept Customization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10032","citing_title":"Closed-Form Concept Erasure via Double Projections","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z","json":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z.json","graph_json":"https://pith.science/api/pith-number/5OXVYGBAKN5QLB34FBHCYOJU7Z/graph.json","events_json":"https://pith.science/api/pith-number/5OXVYGBAKN5QLB34FBHCYOJU7Z/events.json","paper":"https://pith.science/paper/5OXVYGBA"},"agent_actions":{"view_html":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z","download_json":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z.json","view_paper":"https://pith.science/paper/5OXVYGBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23758&json=true","fetch_graph":"https://pith.science/api/pith-number/5OXVYGBAKN5QLB34FBHCYOJU7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/5OXVYGBAKN5QLB34FBHCYOJU7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z/action/storage_attestation","attest_author":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z/action/author_attestation","sign_citation":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z/action/citation_signature","submit_replication":"https://pith.science/pith/5OXVYGBAKN5QLB34FBHCYOJU7Z/action/replication_record"}},"created_at":"2026-07-05T11:12:13.783271+00:00","updated_at":"2026-07-05T11:12:13.783271+00:00"}