{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KY3UCKHSK75I2N5ZNERPIJ2NKQ","short_pith_number":"pith:KY3UCKHS","schema_version":"1.0","canonical_sha256":"56374128f257fa8d37b96922f4274d5418ee11eda9c98d0d7407d8e380b9c3fb","source":{"kind":"arxiv","id":"2301.07093","version":2},"attestation_state":"computed","paper":{"title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Fangzhou Mu, Haotian Liu, Jianfeng Gao, Jianwei Yang, Qingyang Wu, Yong Jae Lee, Yuheng Li","submitted_at":"2023-01-17T18:58:58Z","abstract_excerpt":"Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism. Our model a"},"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":"2301.07093","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T18:58:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.GR","cs.LG"],"title_canon_sha256":"4fbc736e730fba3020dfdfd3c5731787933fe1828fe35dc7309de57198e11a65","abstract_canon_sha256":"f9558edbf70034df0310b4be399e932f7f5999859a4fb77bbc2253daadf6c1c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:16.316353Z","signature_b64":"L8ACy8eq3ssiNRvuS0TM8qGX1/zOveNbF2ILjoknByAtdb646KT1gYe2Mu3wFu6uct2uVAPN8GI1LBGk5W1HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56374128f257fa8d37b96922f4274d5418ee11eda9c98d0d7407d8e380b9c3fb","last_reissued_at":"2026-07-05T06:01:16.315783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:16.315783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Fangzhou Mu, Haotian Liu, Jianfeng Gao, Jianwei Yang, Qingyang Wu, Yong Jae Lee, Yuheng Li","submitted_at":"2023-01-17T18:58:58Z","abstract_excerpt":"Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism. Our model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07093","kind":"arxiv","version":2},"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/2301.07093/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":"2301.07093","created_at":"2026-07-05T06:01:16.315869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07093v2","created_at":"2026-07-05T06:01:16.315869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07093","created_at":"2026-07-05T06:01:16.315869+00:00"},{"alias_kind":"pith_short_12","alias_value":"KY3UCKHSK75I","created_at":"2026-07-05T06:01:16.315869+00:00"},{"alias_kind":"pith_short_16","alias_value":"KY3UCKHSK75I2N5Z","created_at":"2026-07-05T06:01:16.315869+00:00"},{"alias_kind":"pith_short_8","alias_value":"KY3UCKHS","created_at":"2026-07-05T06:01:16.315869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30512","citing_title":"PhyDrawGen: Physically Grounded Diagram Generation from Natural Language","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15357","citing_title":"MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2304.08485","citing_title":"Visual Instruction Tuning","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ","json":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ.json","graph_json":"https://pith.science/api/pith-number/KY3UCKHSK75I2N5ZNERPIJ2NKQ/graph.json","events_json":"https://pith.science/api/pith-number/KY3UCKHSK75I2N5ZNERPIJ2NKQ/events.json","paper":"https://pith.science/paper/KY3UCKHS"},"agent_actions":{"view_html":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ","download_json":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ.json","view_paper":"https://pith.science/paper/KY3UCKHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07093&json=true","fetch_graph":"https://pith.science/api/pith-number/KY3UCKHSK75I2N5ZNERPIJ2NKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KY3UCKHSK75I2N5ZNERPIJ2NKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ/action/storage_attestation","attest_author":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ/action/author_attestation","sign_citation":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ/action/citation_signature","submit_replication":"https://pith.science/pith/KY3UCKHSK75I2N5ZNERPIJ2NKQ/action/replication_record"}},"created_at":"2026-07-05T06:01:16.315869+00:00","updated_at":"2026-07-05T06:01:16.315869+00:00"}