{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SPOPFG3M22GUPJEMW77NITNX36","short_pith_number":"pith:SPOPFG3M","schema_version":"1.0","canonical_sha256":"93dcf29b6cd68d47a48cb7fed44db7df82076f9949d80f7f532a6313585b3299","source":{"kind":"arxiv","id":"2410.00086","version":2},"attestation_state":"computed","paper":{"title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaojie Mao, Chenwei Xie, Jingfeng Zhang, Jingren Zhou, Yulin Pan, Yu Liu, Zeyinzi Jiang, Zhen Han","submitted_at":"2024-09-30T17:56:27Z","abstract_excerpt":"Diffusion models have emerged as a powerful generative technology and have been found to be applicable in various scenarios. Most existing foundational diffusion models are primarily designed for text-guided visual generation and do not support multi-modal conditions, which are essential for many visual editing tasks. This limitation prevents these foundational diffusion models from serving as a unified model in the field of visual generation, like GPT-4 in the natural language processing field. In this work, we propose ACE, an All-round Creator and Editor, which achieves comparable performanc"},"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":"2410.00086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T17:56:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64200df644c4d37631255e0de08379a18eca7860d751867e414a5bb634b1dc34","abstract_canon_sha256":"9e36c6fff303eb1cea5e56efdae4e7113f476fbe44ce0c3febf012e367a94f37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:09.102012Z","signature_b64":"eEsqaPdzMbg0171zYuB5qckUN5xCiycrTUYw5ZX07pKTqyrqLw9cklwjeKDtcofDyAB9vRXgNEUfI3jFo1NFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93dcf29b6cd68d47a48cb7fed44db7df82076f9949d80f7f532a6313585b3299","last_reissued_at":"2026-07-05T09:31:09.101520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:09.101520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaojie Mao, Chenwei Xie, Jingfeng Zhang, Jingren Zhou, Yulin Pan, Yu Liu, Zeyinzi Jiang, Zhen Han","submitted_at":"2024-09-30T17:56:27Z","abstract_excerpt":"Diffusion models have emerged as a powerful generative technology and have been found to be applicable in various scenarios. Most existing foundational diffusion models are primarily designed for text-guided visual generation and do not support multi-modal conditions, which are essential for many visual editing tasks. This limitation prevents these foundational diffusion models from serving as a unified model in the field of visual generation, like GPT-4 in the natural language processing field. In this work, we propose ACE, an All-round Creator and Editor, which achieves comparable performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00086","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/2410.00086/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":"2410.00086","created_at":"2026-07-05T09:31:09.101579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00086v2","created_at":"2026-07-05T09:31:09.101579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00086","created_at":"2026-07-05T09:31:09.101579+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPOPFG3M22GU","created_at":"2026-07-05T09:31:09.101579+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPOPFG3M22GUPJEM","created_at":"2026-07-05T09:31:09.101579+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPOPFG3M","created_at":"2026-07-05T09:31:09.101579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26348","citing_title":"ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23763","citing_title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12175","citing_title":"Redefining Quality Criteria and Distance-Aware Score Modeling for Image Editing Assessment","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19406","citing_title":"HP-Edit: A Human-Preference Post-Training Framework for Image Editing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20258","citing_title":"Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36","json":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36.json","graph_json":"https://pith.science/api/pith-number/SPOPFG3M22GUPJEMW77NITNX36/graph.json","events_json":"https://pith.science/api/pith-number/SPOPFG3M22GUPJEMW77NITNX36/events.json","paper":"https://pith.science/paper/SPOPFG3M"},"agent_actions":{"view_html":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36","download_json":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36.json","view_paper":"https://pith.science/paper/SPOPFG3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00086&json=true","fetch_graph":"https://pith.science/api/pith-number/SPOPFG3M22GUPJEMW77NITNX36/graph.json","fetch_events":"https://pith.science/api/pith-number/SPOPFG3M22GUPJEMW77NITNX36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36/action/storage_attestation","attest_author":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36/action/author_attestation","sign_citation":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36/action/citation_signature","submit_replication":"https://pith.science/pith/SPOPFG3M22GUPJEMW77NITNX36/action/replication_record"}},"created_at":"2026-07-05T09:31:09.101579+00:00","updated_at":"2026-07-05T09:31:09.101579+00:00"}