{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G77R5TIK4J7C2IBA4DYJSOCYG2","short_pith_number":"pith:G77R5TIK","schema_version":"1.0","canonical_sha256":"37ff1ecd0ae27e2d2020e0f09938583689c91567fa24dc4c474764d043019243","source":{"kind":"arxiv","id":"2308.01655","version":1},"attestation_state":"computed","paper":{"title":"DiffColor: Toward High Fidelity Text-Guided Image Colorization with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianxin Lin, Peng Xiao, Rongju Zhang, Xiangxiang Zeng, Yijun Wang","submitted_at":"2023-08-03T09:38:35Z","abstract_excerpt":"Recent data-driven image colorization methods have enabled automatic or reference-based colorization, while still suffering from unsatisfactory and inaccurate object-level color control. To address these issues, we propose a new method called DiffColor that leverages the power of pre-trained diffusion models to recover vivid colors conditioned on a prompt text, without any additional inputs. DiffColor mainly contains two stages: colorization with generative color prior and in-context controllable colorization. Specifically, we first fine-tune a pre-trained text-to-image model to generate color"},"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":"2308.01655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T09:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"5a773a9da578ed35b2110c1051f614d97f7c785e43362a38fa462b3c6348d1db","abstract_canon_sha256":"886348b8d4f0f05b515a9c2e990f088262b61831aef3172e4b435035994577ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:21.548929Z","signature_b64":"jD0eXvBOBQLlzUJfFl92euKdDq3IJdhbAuv4D5BBq9cz0SU74CPgbUl8SxXLvGXxQzBoxj5o3z4tVybkFEbUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ff1ecd0ae27e2d2020e0f09938583689c91567fa24dc4c474764d043019243","last_reissued_at":"2026-07-05T06:37:21.548398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:21.548398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffColor: Toward High Fidelity Text-Guided Image Colorization with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianxin Lin, Peng Xiao, Rongju Zhang, Xiangxiang Zeng, Yijun Wang","submitted_at":"2023-08-03T09:38:35Z","abstract_excerpt":"Recent data-driven image colorization methods have enabled automatic or reference-based colorization, while still suffering from unsatisfactory and inaccurate object-level color control. To address these issues, we propose a new method called DiffColor that leverages the power of pre-trained diffusion models to recover vivid colors conditioned on a prompt text, without any additional inputs. DiffColor mainly contains two stages: colorization with generative color prior and in-context controllable colorization. Specifically, we first fine-tune a pre-trained text-to-image model to generate color"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01655","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/2308.01655/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":"2308.01655","created_at":"2026-07-05T06:37:21.548465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01655v1","created_at":"2026-07-05T06:37:21.548465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01655","created_at":"2026-07-05T06:37:21.548465+00:00"},{"alias_kind":"pith_short_12","alias_value":"G77R5TIK4J7C","created_at":"2026-07-05T06:37:21.548465+00:00"},{"alias_kind":"pith_short_16","alias_value":"G77R5TIK4J7C2IBA","created_at":"2026-07-05T06:37:21.548465+00:00"},{"alias_kind":"pith_short_8","alias_value":"G77R5TIK","created_at":"2026-07-05T06:37:21.548465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20722","citing_title":"Multimodal Image Colorization: Quantifying the Impact of Text-Conditioned Guidance on Grayscale-to-Color Translation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2","json":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2.json","graph_json":"https://pith.science/api/pith-number/G77R5TIK4J7C2IBA4DYJSOCYG2/graph.json","events_json":"https://pith.science/api/pith-number/G77R5TIK4J7C2IBA4DYJSOCYG2/events.json","paper":"https://pith.science/paper/G77R5TIK"},"agent_actions":{"view_html":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2","download_json":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2.json","view_paper":"https://pith.science/paper/G77R5TIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01655&json=true","fetch_graph":"https://pith.science/api/pith-number/G77R5TIK4J7C2IBA4DYJSOCYG2/graph.json","fetch_events":"https://pith.science/api/pith-number/G77R5TIK4J7C2IBA4DYJSOCYG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2/action/storage_attestation","attest_author":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2/action/author_attestation","sign_citation":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2/action/citation_signature","submit_replication":"https://pith.science/pith/G77R5TIK4J7C2IBA4DYJSOCYG2/action/replication_record"}},"created_at":"2026-07-05T06:37:21.548465+00:00","updated_at":"2026-07-05T06:37:21.548465+00:00"}