{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LVPY63IZ7RIA5CGK7B7UB2K4WW","short_pith_number":"pith:LVPY63IZ","schema_version":"1.0","canonical_sha256":"5d5f8f6d19fc500e88caf87f40e95cb58bc9e82f758ee01f0ffffea676e11aff","source":{"kind":"arxiv","id":"2408.09240","version":1},"attestation_state":"computed","paper":{"title":"RepControlNet: ControlNet Reparameterization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyi Wang, Kaibin Zhou, Zhaoli Deng, Zhenpeng Mi","submitted_at":"2024-08-17T16:21:51Z","abstract_excerpt":"With the wide application of diffusion model, the high cost of inference resources has became an important bottleneck for its universal application. Controllable generation, such as ControlNet, is one of the key research directions of diffusion model, and the research related to inference acceleration and model compression is more important. In order to solve this problem, this paper proposes a modal reparameterization method, RepControlNet, to realize the controllable generation of diffusion models without increasing computation. In the training process, RepControlNet uses the adapter to modu"},"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":"2408.09240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-17T16:21:51Z","cross_cats_sorted":[],"title_canon_sha256":"e90ad17694c1de3bd075b161a2cc7bcb3a81c7167d88d8bd7b2beb259adba775","abstract_canon_sha256":"3b12a2becef15fa8969ca0009c485b292fb809e2a582b96ffe8904d6cc6cf8fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:30.096848Z","signature_b64":"T6n+EsWrlORoecJ0b4ACVUCE6iehPjEaeMtY+gYoI1rZcyg7JJ+DvhTma8ViXyrjZvjh6LgIr1oHKVDQdtw5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d5f8f6d19fc500e88caf87f40e95cb58bc9e82f758ee01f0ffffea676e11aff","last_reissued_at":"2026-07-05T08:56:30.096442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:30.096442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepControlNet: ControlNet Reparameterization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyi Wang, Kaibin Zhou, Zhaoli Deng, Zhenpeng Mi","submitted_at":"2024-08-17T16:21:51Z","abstract_excerpt":"With the wide application of diffusion model, the high cost of inference resources has became an important bottleneck for its universal application. Controllable generation, such as ControlNet, is one of the key research directions of diffusion model, and the research related to inference acceleration and model compression is more important. In order to solve this problem, this paper proposes a modal reparameterization method, RepControlNet, to realize the controllable generation of diffusion models without increasing computation. In the training process, RepControlNet uses the adapter to modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09240","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/2408.09240/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":"2408.09240","created_at":"2026-07-05T08:56:30.096498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09240v1","created_at":"2026-07-05T08:56:30.096498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09240","created_at":"2026-07-05T08:56:30.096498+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVPY63IZ7RIA","created_at":"2026-07-05T08:56:30.096498+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVPY63IZ7RIA5CGK","created_at":"2026-07-05T08:56:30.096498+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVPY63IZ","created_at":"2026-07-05T08:56:30.096498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10451","citing_title":"FlexControl: Computation-Aware ControlNet with Differentiable Router for Text-to-Image Generation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW","json":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW.json","graph_json":"https://pith.science/api/pith-number/LVPY63IZ7RIA5CGK7B7UB2K4WW/graph.json","events_json":"https://pith.science/api/pith-number/LVPY63IZ7RIA5CGK7B7UB2K4WW/events.json","paper":"https://pith.science/paper/LVPY63IZ"},"agent_actions":{"view_html":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW","download_json":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW.json","view_paper":"https://pith.science/paper/LVPY63IZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09240&json=true","fetch_graph":"https://pith.science/api/pith-number/LVPY63IZ7RIA5CGK7B7UB2K4WW/graph.json","fetch_events":"https://pith.science/api/pith-number/LVPY63IZ7RIA5CGK7B7UB2K4WW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW/action/storage_attestation","attest_author":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW/action/author_attestation","sign_citation":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW/action/citation_signature","submit_replication":"https://pith.science/pith/LVPY63IZ7RIA5CGK7B7UB2K4WW/action/replication_record"}},"created_at":"2026-07-05T08:56:30.096498+00:00","updated_at":"2026-07-05T08:56:30.096498+00:00"}