{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MFY5ZWIYVVJHU6CWKFJGRL2CHD","short_pith_number":"pith:MFY5ZWIY","canonical_record":{"source":{"id":"2401.07519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T07:50:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d6ea9a5cfb31dd659312284b07e1456c05cee79909eb5f36658bebbd67e5318","abstract_canon_sha256":"1453585afe60e10c953c7cf24965f2a5e62be976a2aca5a311124f3eb83bf0e6"},"schema_version":"1.0"},"canonical_sha256":"6171dcd918ad527a7856515268af4238ee61806a698f4fccb46dc582f104ca30","source":{"kind":"arxiv","id":"2401.07519","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07519","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07519v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07519","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"MFY5ZWIYVVJH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MFY5ZWIYVVJHU6CW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MFY5ZWIY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MFY5ZWIYVVJHU6CWKFJGRL2CHD","target":"record","payload":{"canonical_record":{"source":{"id":"2401.07519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T07:50:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d6ea9a5cfb31dd659312284b07e1456c05cee79909eb5f36658bebbd67e5318","abstract_canon_sha256":"1453585afe60e10c953c7cf24965f2a5e62be976a2aca5a311124f3eb83bf0e6"},"schema_version":"1.0"},"canonical_sha256":"6171dcd918ad527a7856515268af4238ee61806a698f4fccb46dc582f104ca30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.088365Z","signature_b64":"ZhGoLdyq1Q6NcguQ7CUVt+wtz2rHf2SEReQ+CznklMrF5aqV2kMGXGbM6X3NM38rnZC9/VvyHNQS9Xq918GGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6171dcd918ad527a7856515268af4238ee61806a698f4fccb46dc582f104ca30","last_reissued_at":"2026-05-17T23:38:13.087758Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.087758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.07519","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kMg4OHmXWRZMC1mn6iJV/UQYwioABc4wfcC1HeMWO628jPBIFDcFgawm2zB1Y2C61MtdBBTO+H3Www8ilJQVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:51:26.742753Z"},"content_sha256":"5fca6546f56e068b907066de1798b2efbaac0078d8e61cd21012e5c24e22c7e4","schema_version":"1.0","event_id":"sha256:5fca6546f56e068b907066de1798b2efbaac0078d8e61cd21012e5c24e22c7e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MFY5ZWIYVVJHU6CWKFJGRL2CHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"InstantID generates high-fidelity personalized images from one face photo in seconds without fine-tuning.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anthony Chen, Haofan Wang, Huaxia Li, Qixun Wang, Xu Bai, Xu Tang, Yao Hu, Zekui Qin","submitted_at":"2024-01-15T07:50:18Z","abstract_excerpt":"There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world applicability is hindered by high storage demands, lengthy fine-tuning processes, and the need for multiple reference images. Conversely, existing ID embedding-based methods, while requiring only a single forward inference, face challenges: they either necessitate extensive fine-tuning across numerous model parameters, lack compatibility with community pre-trained models, or fail to maintain high face fidelity. Addressing these limitations, we "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our plug-and-play module adeptly handles image personalization in various styles using just a single facial image, while ensuring high fidelity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the IdentityNet design, by imposing strong semantic and weak spatial conditions on facial and landmark images integrated with textual prompts, will deliver high face fidelity across styles without fine-tuning or multiple references.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"InstantID enables zero-shot identity-preserving image generation from one facial image via a novel IdentityNet that combines strong semantic and weak spatial conditioning with text prompts in diffusion models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"InstantID generates high-fidelity personalized images from one face photo in seconds without fine-tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c7c55b2b29e48134074dbb9842a109140b90530e246b06d2351cf5ae3084f219"},"source":{"id":"2401.07519","kind":"arxiv","version":2},"verdict":{"id":"ece50b4f-89f0-4340-beb7-5021bdf36772","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:57:42.525913Z","strongest_claim":"Our plug-and-play module adeptly handles image personalization in various styles using just a single facial image, while ensuring high fidelity.","one_line_summary":"InstantID enables zero-shot identity-preserving image generation from one facial image via a novel IdentityNet that combines strong semantic and weak spatial conditioning with text prompts in diffusion models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the IdentityNet design, by imposing strong semantic and weak spatial conditions on facial and landmark images integrated with textual prompts, will deliver high face fidelity across styles without fine-tuning or multiple references.","pith_extraction_headline":"InstantID generates high-fidelity personalized images from one face photo in seconds without fine-tuning."},"references":{"count":28,"sample":[{"doi":"","year":2022,"title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","work_id":"2cd7b629-ab37-4ce5-b51e-aa4d99547468","ref_index":1,"cited_arxiv_id":"2211.01324","is_internal_anchor":true},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2307.09481 (2023)","work_id":"b5906af7-b3b8-4517-a1d2-9687f00960ea","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","work_id":"8e700a39-a905-4502-b336-4e1a69b5bf6a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48550/arxiv.2208.01618","year":2022,"title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","work_id":"ca618c21-3ba6-448e-bd86-bcecff3cdeb5","ref_index":4,"cited_arxiv_id":"2208.01618","is_internal_anchor":true},{"doi":"","year":2023,"title":"Designing an encoder for fast personalization of text-to-image models","work_id":"38db57b1-fb65-4b24-9152-ee4147c37fb4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":28,"snapshot_sha256":"d825eb2dc763f997431cb7886d5e136835bba665b743088a5786fdf3f3995597","internal_anchors":7},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b3b5502522b8ff5bf8e0b933470cd7db20d5632d257acc3bd0214da84b616474"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ece50b4f-89f0-4340-beb7-5021bdf36772"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIK4TaRJRdVi9laiBIGUeCHgmLdgg+/npQVndkQZS8ykVH6dSWUSpz+nUDNFZHgkHvQfjqylZRzBNuh7Bgs+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:51:26.743286Z"},"content_sha256":"962cd1d93c7f3b3fd584eae98178de5afb60f4bcba641491622b9f86336d8449","schema_version":"1.0","event_id":"sha256:962cd1d93c7f3b3fd584eae98178de5afb60f4bcba641491622b9f86336d8449"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD/bundle.json","state_url":"https://pith.science/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-20T05:51:26Z","links":{"resolver":"https://pith.science/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD","bundle":"https://pith.science/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD/bundle.json","state":"https://pith.science/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFY5ZWIYVVJHU6CWKFJGRL2CHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MFY5ZWIYVVJHU6CWKFJGRL2CHD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1453585afe60e10c953c7cf24965f2a5e62be976a2aca5a311124f3eb83bf0e6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T07:50:18Z","title_canon_sha256":"8d6ea9a5cfb31dd659312284b07e1456c05cee79909eb5f36658bebbd67e5318"},"schema_version":"1.0","source":{"id":"2401.07519","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07519","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07519v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07519","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"MFY5ZWIYVVJH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MFY5ZWIYVVJHU6CW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MFY5ZWIY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:962cd1d93c7f3b3fd584eae98178de5afb60f4bcba641491622b9f86336d8449","target":"graph","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our plug-and-play module adeptly handles image personalization in various styles using just a single facial image, while ensuring high fidelity."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the IdentityNet design, by imposing strong semantic and weak spatial conditions on facial and landmark images integrated with textual prompts, will deliver high face fidelity across styles without fine-tuning or multiple references."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"InstantID enables zero-shot identity-preserving image generation from one facial image via a novel IdentityNet that combines strong semantic and weak spatial conditioning with text prompts in diffusion models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"InstantID generates high-fidelity personalized images from one face photo in seconds without fine-tuning."}],"snapshot_sha256":"c7c55b2b29e48134074dbb9842a109140b90530e246b06d2351cf5ae3084f219"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b3b5502522b8ff5bf8e0b933470cd7db20d5632d257acc3bd0214da84b616474"},"paper":{"abstract_excerpt":"There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world applicability is hindered by high storage demands, lengthy fine-tuning processes, and the need for multiple reference images. Conversely, existing ID embedding-based methods, while requiring only a single forward inference, face challenges: they either necessitate extensive fine-tuning across numerous model parameters, lack compatibility with community pre-trained models, or fail to maintain high face fidelity. Addressing these limitations, we ","authors_text":"Anthony Chen, Haofan Wang, Huaxia Li, Qixun Wang, Xu Bai, Xu Tang, Yao Hu, Zekui Qin","cross_cats":["cs.AI"],"headline":"InstantID generates high-fidelity personalized images from one face photo in seconds without fine-tuning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T07:50:18Z","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds"},"references":{"count":28,"internal_anchors":7,"resolved_work":28,"sample":[{"cited_arxiv_id":"2211.01324","doi":"","is_internal_anchor":true,"ref_index":1,"title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","work_id":"2cd7b629-ab37-4ce5-b51e-aa4d99547468","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2307.09481 (2023)","work_id":"b5906af7-b3b8-4517-a1d2-9687f00960ea","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","work_id":"8e700a39-a905-4502-b336-4e1a69b5bf6a","year":2021},{"cited_arxiv_id":"2208.01618","doi":"10.48550/arxiv.2208.01618","is_internal_anchor":true,"ref_index":4,"title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","work_id":"ca618c21-3ba6-448e-bd86-bcecff3cdeb5","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Designing an encoder for fast personalization of text-to-image models","work_id":"38db57b1-fb65-4b24-9152-ee4147c37fb4","year":2023}],"snapshot_sha256":"d825eb2dc763f997431cb7886d5e136835bba665b743088a5786fdf3f3995597"},"source":{"id":"2401.07519","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T20:57:42.525913Z","id":"ece50b4f-89f0-4340-beb7-5021bdf36772","model_set":{"reader":"grok-4.3"},"one_line_summary":"InstantID enables zero-shot identity-preserving image generation from one facial image via a novel IdentityNet that combines strong semantic and weak spatial conditioning with text prompts in diffusion models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"InstantID generates high-fidelity personalized images from one face photo in seconds without fine-tuning.","strongest_claim":"Our plug-and-play module adeptly handles image personalization in various styles using just a single facial image, while ensuring high fidelity.","weakest_assumption":"That the IdentityNet design, by imposing strong semantic and weak spatial conditions on facial and landmark images integrated with textual prompts, will deliver high face fidelity across styles without fine-tuning or multiple references."}},"verdict_id":"ece50b4f-89f0-4340-beb7-5021bdf36772"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5fca6546f56e068b907066de1798b2efbaac0078d8e61cd21012e5c24e22c7e4","target":"record","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1453585afe60e10c953c7cf24965f2a5e62be976a2aca5a311124f3eb83bf0e6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T07:50:18Z","title_canon_sha256":"8d6ea9a5cfb31dd659312284b07e1456c05cee79909eb5f36658bebbd67e5318"},"schema_version":"1.0","source":{"id":"2401.07519","kind":"arxiv","version":2}},"canonical_sha256":"6171dcd918ad527a7856515268af4238ee61806a698f4fccb46dc582f104ca30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6171dcd918ad527a7856515268af4238ee61806a698f4fccb46dc582f104ca30","first_computed_at":"2026-05-17T23:38:13.087758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.087758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhGoLdyq1Q6NcguQ7CUVt+wtz2rHf2SEReQ+CznklMrF5aqV2kMGXGbM6X3NM38rnZC9/VvyHNQS9Xq918GGCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.088365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07519","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fca6546f56e068b907066de1798b2efbaac0078d8e61cd21012e5c24e22c7e4","sha256:962cd1d93c7f3b3fd584eae98178de5afb60f4bcba641491622b9f86336d8449"],"state_sha256":"dfa1ebb97d220826615718cd35601e86249cbadf00b7b023e8ff8c185ee281bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsvNJPPleOeJxiQc+Gnh3eyfFNRMxMuagUeOc/lTzT14EJrFipi0ZJ+fHPw/P4EkjXmz0ntfpNB3J4I2oz6dAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T05:51:26.745639Z","bundle_sha256":"fd1b905f8621024036db3cbcd58ad9ffa6a80c8472ddb111180706dc2f1d6070"}}