{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJM3MUBBJAN7JBAKIPMO2POFUI","short_pith_number":"pith:XJM3MUBB","schema_version":"1.0","canonical_sha256":"ba59b65021481bf4840a43d8ed3dc5a227f1eb0818124225bea98d3f2b23b4f0","source":{"kind":"arxiv","id":"2410.07718","version":2},"attestation_state":"computed","paper":{"title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhou, Hanlin Shang, Hao Zhu, Hui Li, Jiahao Cui, Jingdong Wang, Kaihui Cheng, Siyu Zhu, Yao Yao","submitted_at":"2024-10-10T08:34:41Z","abstract_excerpt":"Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several design enhancements to extend its capabilities. First, we extend the method to produce long-duration videos. To address substantial challenges such as appearance drift and temporal artifacts, we investigate augmentation strategies within the image space of conditional motion frames. Specifically, we introduce a patch-drop technique augmented with Gaussian noise"},"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":"2410.07718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T08:34:41Z","cross_cats_sorted":[],"title_canon_sha256":"3f2bd1c9d8aa1b75f92d42c7313dce5c8799108e45957b4e3f3081a7f195c22a","abstract_canon_sha256":"bd56a7108d039620adf1f30bd3fac482da832074b2448bab4f03068bccc4bfbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:04.643086Z","signature_b64":"z7Xlqvd3mNTyI+x2+REpvEbosreHb8ahkZSDLO23Eqj5qteNz75T9RhHyMYpkBpU97+IreyMYerWQia0zl9rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba59b65021481bf4840a43d8ed3dc5a227f1eb0818124225bea98d3f2b23b4f0","last_reissued_at":"2026-07-05T09:20:04.642597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:04.642597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhou, Hanlin Shang, Hao Zhu, Hui Li, Jiahao Cui, Jingdong Wang, Kaihui Cheng, Siyu Zhu, Yao Yao","submitted_at":"2024-10-10T08:34:41Z","abstract_excerpt":"Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several design enhancements to extend its capabilities. First, we extend the method to produce long-duration videos. To address substantial challenges such as appearance drift and temporal artifacts, we investigate augmentation strategies within the image space of conditional motion frames. Specifically, we introduce a patch-drop technique augmented with Gaussian noise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07718","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/2410.07718/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":"2410.07718","created_at":"2026-07-05T09:20:04.642655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07718v2","created_at":"2026-07-05T09:20:04.642655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07718","created_at":"2026-07-05T09:20:04.642655+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJM3MUBBJAN7","created_at":"2026-07-05T09:20:04.642655+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJM3MUBBJAN7JBAK","created_at":"2026-07-05T09:20:04.642655+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJM3MUBB","created_at":"2026-07-05T09:20:04.642655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01031","citing_title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31088","citing_title":"Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30019","citing_title":"OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25488","citing_title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16748","citing_title":"Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2411.09209","citing_title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12052","citing_title":"FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23586","citing_title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23632","citing_title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23325","citing_title":"EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22865","citing_title":"MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08405","citing_title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI","json":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI.json","graph_json":"https://pith.science/api/pith-number/XJM3MUBBJAN7JBAKIPMO2POFUI/graph.json","events_json":"https://pith.science/api/pith-number/XJM3MUBBJAN7JBAKIPMO2POFUI/events.json","paper":"https://pith.science/paper/XJM3MUBB"},"agent_actions":{"view_html":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI","download_json":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI.json","view_paper":"https://pith.science/paper/XJM3MUBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07718&json=true","fetch_graph":"https://pith.science/api/pith-number/XJM3MUBBJAN7JBAKIPMO2POFUI/graph.json","fetch_events":"https://pith.science/api/pith-number/XJM3MUBBJAN7JBAKIPMO2POFUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI/action/storage_attestation","attest_author":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI/action/author_attestation","sign_citation":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI/action/citation_signature","submit_replication":"https://pith.science/pith/XJM3MUBBJAN7JBAKIPMO2POFUI/action/replication_record"}},"created_at":"2026-07-05T09:20:04.642655+00:00","updated_at":"2026-07-05T09:20:04.642655+00:00"}