{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7YNSSFLK47DZGCRTP6TSGOLXL2","short_pith_number":"pith:7YNSSFLK","schema_version":"1.0","canonical_sha256":"fe1b29156ae7c7930a337fa72339775eb46fa6e9dec8071b397c6639092c899f","source":{"kind":"arxiv","id":"2405.04356","version":1},"attestation_state":"computed","paper":{"title":"Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjae Oh, Hoseok Do, JiHyun Kim, Kwanghoon Sohn, Soohyun Kim","submitted_at":"2024-05-07T14:33:40Z","abstract_excerpt":"We present a new multi-modal face image generation method that converts a text prompt and a visual input, such as a semantic mask or scribble map, into a photo-realistic face image. To do this, we combine the strengths of Generative Adversarial networks (GANs) and diffusion models (DMs) by employing the multi-modal features in the DM into the latent space of the pre-trained GANs. We present a simple mapping and a style modulation network to link two models and convert meaningful representations in feature maps and attention maps into latent codes. With GAN inversion, the estimated latent codes"},"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":"2405.04356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T14:33:40Z","cross_cats_sorted":[],"title_canon_sha256":"90f34c6fe49bf209cb49efdf61659c1ecd6cbde3fc9052368123fa7fd0dea7d5","abstract_canon_sha256":"59f8430ce6774d55982532faa388cba53a405dcace4264f43534687e66b48f73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:35.969906Z","signature_b64":"simVA5q6iidiecqCmbtmBmFD9SAZs89oN/4WxNTkakvcyDj1fszuljDL3N0JqwWCgM21D/MbAFW9IuVHeFUNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe1b29156ae7c7930a337fa72339775eb46fa6e9dec8071b397c6639092c899f","last_reissued_at":"2026-07-05T08:16:35.969463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:35.969463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjae Oh, Hoseok Do, JiHyun Kim, Kwanghoon Sohn, Soohyun Kim","submitted_at":"2024-05-07T14:33:40Z","abstract_excerpt":"We present a new multi-modal face image generation method that converts a text prompt and a visual input, such as a semantic mask or scribble map, into a photo-realistic face image. To do this, we combine the strengths of Generative Adversarial networks (GANs) and diffusion models (DMs) by employing the multi-modal features in the DM into the latent space of the pre-trained GANs. We present a simple mapping and a style modulation network to link two models and convert meaningful representations in feature maps and attention maps into latent codes. With GAN inversion, the estimated latent codes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04356","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/2405.04356/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":"2405.04356","created_at":"2026-07-05T08:16:35.969520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04356v1","created_at":"2026-07-05T08:16:35.969520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04356","created_at":"2026-07-05T08:16:35.969520+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YNSSFLK47DZ","created_at":"2026-07-05T08:16:35.969520+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YNSSFLK47DZGCRT","created_at":"2026-07-05T08:16:35.969520+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YNSSFLK","created_at":"2026-07-05T08:16:35.969520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2","json":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2.json","graph_json":"https://pith.science/api/pith-number/7YNSSFLK47DZGCRTP6TSGOLXL2/graph.json","events_json":"https://pith.science/api/pith-number/7YNSSFLK47DZGCRTP6TSGOLXL2/events.json","paper":"https://pith.science/paper/7YNSSFLK"},"agent_actions":{"view_html":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2","download_json":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2.json","view_paper":"https://pith.science/paper/7YNSSFLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04356&json=true","fetch_graph":"https://pith.science/api/pith-number/7YNSSFLK47DZGCRTP6TSGOLXL2/graph.json","fetch_events":"https://pith.science/api/pith-number/7YNSSFLK47DZGCRTP6TSGOLXL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2/action/storage_attestation","attest_author":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2/action/author_attestation","sign_citation":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2/action/citation_signature","submit_replication":"https://pith.science/pith/7YNSSFLK47DZGCRTP6TSGOLXL2/action/replication_record"}},"created_at":"2026-07-05T08:16:35.969520+00:00","updated_at":"2026-07-05T08:16:35.969520+00:00"}