{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FAQ5UX4WRWFXU7G6ZS4Z32LFYV","short_pith_number":"pith:FAQ5UX4W","schema_version":"1.0","canonical_sha256":"2821da5f968d8b7a7cdeccb99de965c540629df8ce244b6d57876e81e2962f95","source":{"kind":"arxiv","id":"2404.14768","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Hongyu Chen, Min Zhou, Peng Wang, Tiezheng Ge, Xubin Li, Yiqi Gao","submitted_at":"2024-04-23T06:10:43Z","abstract_excerpt":"Recently, integrating visual controls into text-to-image~(T2I) models, such as ControlNet method, has received significant attention for finer control capabilities. While various training-free methods make efforts to enhance prompt following in T2I models, the issue with visual control is still rarely studied, especially in the scenario that visual controls are misaligned with text prompts. In this paper, we address the challenge of ``Prompt Following With Visual Control\" and propose a training-free approach named Mask-guided Prompt Following (MGPF). Object masks are introduced to distinct ali"},"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":"2404.14768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T06:10:43Z","cross_cats_sorted":[],"title_canon_sha256":"f419c9eece21643ad397279609f463befbf55688a68b8583c269998b30c95abe","abstract_canon_sha256":"ba71e162e54f6120906d65c407b88036d9e62ca8b6ec02ac55cea000ab023541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:09.906567Z","signature_b64":"SV1GtswhqPaG0p1RVrUJ5jz/HLzeibZl8kPFst+FBDPqshLhNJVo2v9zll2tVOxv1KVTIcUV7p79I7I3eVeKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2821da5f968d8b7a7cdeccb99de965c540629df8ce244b6d57876e81e2962f95","last_reissued_at":"2026-07-05T08:11:09.906144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:09.906144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Hongyu Chen, Min Zhou, Peng Wang, Tiezheng Ge, Xubin Li, Yiqi Gao","submitted_at":"2024-04-23T06:10:43Z","abstract_excerpt":"Recently, integrating visual controls into text-to-image~(T2I) models, such as ControlNet method, has received significant attention for finer control capabilities. While various training-free methods make efforts to enhance prompt following in T2I models, the issue with visual control is still rarely studied, especially in the scenario that visual controls are misaligned with text prompts. In this paper, we address the challenge of ``Prompt Following With Visual Control\" and propose a training-free approach named Mask-guided Prompt Following (MGPF). Object masks are introduced to distinct ali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14768","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/2404.14768/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":"2404.14768","created_at":"2026-07-05T08:11:09.906201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14768v1","created_at":"2026-07-05T08:11:09.906201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14768","created_at":"2026-07-05T08:11:09.906201+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAQ5UX4WRWFX","created_at":"2026-07-05T08:11:09.906201+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAQ5UX4WRWFXU7G6","created_at":"2026-07-05T08:11:09.906201+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAQ5UX4W","created_at":"2026-07-05T08:11:09.906201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00954","citing_title":"COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12138","citing_title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV","json":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV.json","graph_json":"https://pith.science/api/pith-number/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/graph.json","events_json":"https://pith.science/api/pith-number/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/events.json","paper":"https://pith.science/paper/FAQ5UX4W"},"agent_actions":{"view_html":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV","download_json":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV.json","view_paper":"https://pith.science/paper/FAQ5UX4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14768&json=true","fetch_graph":"https://pith.science/api/pith-number/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/graph.json","fetch_events":"https://pith.science/api/pith-number/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/action/storage_attestation","attest_author":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/action/author_attestation","sign_citation":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/action/citation_signature","submit_replication":"https://pith.science/pith/FAQ5UX4WRWFXU7G6ZS4Z32LFYV/action/replication_record"}},"created_at":"2026-07-05T08:11:09.906201+00:00","updated_at":"2026-07-05T08:11:09.906201+00:00"}