{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DESQCT66EMCTJS746HRPZAEGCL","short_pith_number":"pith:DESQCT66","schema_version":"1.0","canonical_sha256":"1925014fde230534cbfcf1e2fc808612f0d2ef4f698f1dae8bfce9ee80b15cf4","source":{"kind":"arxiv","id":"2401.01952","version":1},"attestation_state":"computed","paper":{"title":"Instruct-Imagen: Image Generation with Multi-modal Instruction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Hexiang Hu, Kelvin C.K. Chan, Kihyuk Sohn, Ming-Wei Chang, Wenhu Chen, William Cohen, Xue Ben, Xuhui Jia, Yandong Li, Yang Zhao, Yu-Chuan Su","submitted_at":"2024-01-03T19:31:58Z","abstract_excerpt":"This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format.\n  We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model "},"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":"2401.01952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T19:31:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"29923ab2748b2bb52d19119cfe339c3b9985b99b01d9ced5f470027fbb5aa5a0","abstract_canon_sha256":"18410990e69ba400af5e54fcf7c37fb3dc19cc6d0cf9f3c27e2f2a3ef0c1d2d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:08.622504Z","signature_b64":"3voO+4QLxNu5H0XGnf91AsWTJmHL8N5xhcuMBe+85Mv3Up6iEBqA5zBJCvRPKXok1pElVoX/XVMmM2+FGVlMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1925014fde230534cbfcf1e2fc808612f0d2ef4f698f1dae8bfce9ee80b15cf4","last_reissued_at":"2026-07-05T07:30:08.622008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:08.622008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruct-Imagen: Image Generation with Multi-modal Instruction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Hexiang Hu, Kelvin C.K. Chan, Kihyuk Sohn, Ming-Wei Chang, Wenhu Chen, William Cohen, Xue Ben, Xuhui Jia, Yandong Li, Yang Zhao, Yu-Chuan Su","submitted_at":"2024-01-03T19:31:58Z","abstract_excerpt":"This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format.\n  We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01952","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/2401.01952/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":"2401.01952","created_at":"2026-07-05T07:30:08.622064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01952v1","created_at":"2026-07-05T07:30:08.622064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01952","created_at":"2026-07-05T07:30:08.622064+00:00"},{"alias_kind":"pith_short_12","alias_value":"DESQCT66EMCT","created_at":"2026-07-05T07:30:08.622064+00:00"},{"alias_kind":"pith_short_16","alias_value":"DESQCT66EMCTJS74","created_at":"2026-07-05T07:30:08.622064+00:00"},{"alias_kind":"pith_short_8","alias_value":"DESQCT66","created_at":"2026-07-05T07:30:08.622064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08090","citing_title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL","json":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL.json","graph_json":"https://pith.science/api/pith-number/DESQCT66EMCTJS746HRPZAEGCL/graph.json","events_json":"https://pith.science/api/pith-number/DESQCT66EMCTJS746HRPZAEGCL/events.json","paper":"https://pith.science/paper/DESQCT66"},"agent_actions":{"view_html":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL","download_json":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL.json","view_paper":"https://pith.science/paper/DESQCT66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01952&json=true","fetch_graph":"https://pith.science/api/pith-number/DESQCT66EMCTJS746HRPZAEGCL/graph.json","fetch_events":"https://pith.science/api/pith-number/DESQCT66EMCTJS746HRPZAEGCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL/action/storage_attestation","attest_author":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL/action/author_attestation","sign_citation":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL/action/citation_signature","submit_replication":"https://pith.science/pith/DESQCT66EMCTJS746HRPZAEGCL/action/replication_record"}},"created_at":"2026-07-05T07:30:08.622064+00:00","updated_at":"2026-07-05T07:30:08.622064+00:00"}