{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JFKSGOQ2Q5VVCNJKDXSR7R3AD3","short_pith_number":"pith:JFKSGOQ2","schema_version":"1.0","canonical_sha256":"4955233a1a876b51352a1de51fc7601ecf63abf6e6a45c09d5819b1e5ab00915","source":{"kind":"arxiv","id":"2304.03411","version":1},"attestation_state":"computed","paper":{"title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyun Joon Jung, Jing Shi, Wei Xiong, Zhe Lin","submitted_at":"2023-04-06T23:26:38Z","abstract_excerpt":"Recent advances in personalized image generation allow a pre-trained text-to-image model to learn a new concept from a set of images. However, existing personalization approaches usually require heavy test-time finetuning for each concept, which is time-consuming and difficult to scale. We propose InstantBooth, a novel approach built upon pre-trained text-to-image models that enables instant text-guided image personalization without any test-time finetuning. We achieve this with several major components. First, we learn the general concept of the input images by converting them to a textual to"},"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":"2304.03411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T23:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"035ef613b02440b41e362fd7370b6fe048ece83d6fcfea05add60d08dc43aec2","abstract_canon_sha256":"f85851f9e77258ad97551b499f653f131f895ac979748dc1cea3d64e0b583664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:55.593660Z","signature_b64":"N+Lg+4cwGVJhGCUbqwYYlAF3IrZmiffx9iJOLwGDVcDWAzJZNFCS7Zh54VJmg2L26IoKJpzRnORqY4eq/K9NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4955233a1a876b51352a1de51fc7601ecf63abf6e6a45c09d5819b1e5ab00915","last_reissued_at":"2026-07-05T05:58:55.593245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:55.593245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyun Joon Jung, Jing Shi, Wei Xiong, Zhe Lin","submitted_at":"2023-04-06T23:26:38Z","abstract_excerpt":"Recent advances in personalized image generation allow a pre-trained text-to-image model to learn a new concept from a set of images. However, existing personalization approaches usually require heavy test-time finetuning for each concept, which is time-consuming and difficult to scale. We propose InstantBooth, a novel approach built upon pre-trained text-to-image models that enables instant text-guided image personalization without any test-time finetuning. We achieve this with several major components. First, we learn the general concept of the input images by converting them to a textual to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03411","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/2304.03411/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":"2304.03411","created_at":"2026-07-05T05:58:55.593301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03411v1","created_at":"2026-07-05T05:58:55.593301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03411","created_at":"2026-07-05T05:58:55.593301+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFKSGOQ2Q5VV","created_at":"2026-07-05T05:58:55.593301+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFKSGOQ2Q5VVCNJK","created_at":"2026-07-05T05:58:55.593301+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFKSGOQ2","created_at":"2026-07-05T05:58:55.593301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02129","citing_title":"Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19182","citing_title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2310.19512","citing_title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2307.04725","citing_title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3","json":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3.json","graph_json":"https://pith.science/api/pith-number/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/graph.json","events_json":"https://pith.science/api/pith-number/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/events.json","paper":"https://pith.science/paper/JFKSGOQ2"},"agent_actions":{"view_html":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3","download_json":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3.json","view_paper":"https://pith.science/paper/JFKSGOQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03411&json=true","fetch_graph":"https://pith.science/api/pith-number/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/graph.json","fetch_events":"https://pith.science/api/pith-number/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/action/storage_attestation","attest_author":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/action/author_attestation","sign_citation":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/action/citation_signature","submit_replication":"https://pith.science/pith/JFKSGOQ2Q5VVCNJKDXSR7R3AD3/action/replication_record"}},"created_at":"2026-07-05T05:58:55.593301+00:00","updated_at":"2026-07-05T05:58:55.593301+00:00"}