{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JP4GN6WR2H4HK2JEYMBDM2W7JL","short_pith_number":"pith:JP4GN6WR","schema_version":"1.0","canonical_sha256":"4bf866fad1d1f8756924c302366adf4ad0805b0a40be1eb3b7ca51069681aa14","source":{"kind":"arxiv","id":"2302.05543","version":3},"attestation_state":"computed","paper":{"title":"Adding Conditional Control to Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models.","cross_cats":["cs.AI","cs.GR","cs.HC","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anyi Rao, Lvmin Zhang, Maneesh Agrawala","submitted_at":"2023-02-10T23:12:37Z","abstract_excerpt":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with \"zero convolutions\" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning co"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2302.05543","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T23:12:37Z","cross_cats_sorted":["cs.AI","cs.GR","cs.HC","cs.MM"],"title_canon_sha256":"c802ad03716e6f3260d24a90dcef2626bcb68f2f1371aaab7f3fa8d320eb8edb","abstract_canon_sha256":"354cfba2220db73fe22bf3e76b365043fbef9ec456ed18ece6e21b9722bac2d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.351011Z","signature_b64":"H1q84TvsDCzvljbeHt4Mphtqe1IQXW2d00eFe2vBtBvQhOzi9XE5b2BqSy8yeQvVvRtE4nJ8ANR5oXgD5qbdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf866fad1d1f8756924c302366adf4ad0805b0a40be1eb3b7ca51069681aa14","last_reissued_at":"2026-05-17T23:38:46.350422Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.350422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adding Conditional Control to Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models.","cross_cats":["cs.AI","cs.GR","cs.HC","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anyi Rao, Lvmin Zhang, Maneesh Agrawala","submitted_at":"2023-02-10T23:12:37Z","abstract_excerpt":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with \"zero convolutions\" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning co"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The zero convolutions progressively grow parameters from zero and ensure that no harmful noise could affect the finetuning, allowing the pretrained backbone to remain intact while learning new controls.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ceb25131b2b913ce597fef9e72bf1b4d5aeb174d0fbc78ad74f35388a5233deb"},"source":{"id":"2302.05543","kind":"arxiv","version":3},"verdict":{"id":"c291990c-fe75-4b25-b563-e900c875fbcb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T22:38:53.240545Z","strongest_claim":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls.","one_line_summary":"ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The zero convolutions progressively grow parameters from zero and ensure that no harmful noise could affect the finetuning, allowing the pretrained backbone to remain intact while learning new controls.","pith_extraction_headline":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models."},"references":{"count":99,"sample":[{"doi":"","year":2020,"title":"Weight initialization in neural network, inspired by andrew ng, https://medium.com/@safrin1128/weight- initialization-in-neural-network-inspired-by-andrew-ng- e0066dc4a566, 2020","work_id":"3f9ca0ba-f454-40c9-b7c4-a550dd074663","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"In- trinsic dimensionality explains the effectiveness of language model fine-tuning","work_id":"59996242-57e2-4905-a5ee-ddff83d2fc2f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Only a matter of style: Age transformation using a style-based regression model","work_id":"f567145e-0ca7-4163-94d8-e24ef8c8b91a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Hyperstyle: Stylegan inversion with hypernetworks for real image editing","work_id":"e058da51-899a-4555-b751-ec1e90b69a02","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Disco diffusion, https://github.com/alembics/disco- diffusion, 2022","work_id":"203b3fb8-4921-487f-9110-dda3201afe51","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":99,"snapshot_sha256":"0d6aa2f2d7e538e47c146e68c5e68fa5c1befbc4ff90b938d64e90da34937a3d","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46cd962887c3ef1518d72b679115b5e163ec5ad7c99142f28815d4356d358d27"},"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":"2302.05543","created_at":"2026-05-17T23:38:46.350506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05543v3","created_at":"2026-05-17T23:38:46.350506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05543","created_at":"2026-05-17T23:38:46.350506+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP4GN6WR2H4H","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP4GN6WR2H4HK2JE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP4GN6WR","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2502.04230","citing_title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2411.19182","citing_title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2504.01571","citing_title":"Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21611","citing_title":"UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20780","citing_title":"Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":242,"is_internal_anchor":true},{"citing_arxiv_id":"2506.14399","citing_title":"Factored Classifier-Free Guidance","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13857","citing_title":"MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17580","citing_title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2303.04671","citing_title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2310.04378","citing_title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2509.20427","citing_title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09699","citing_title":"A Real-Calibrated Synthetic-First Data Engine","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09622","citing_title":"Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00707","citing_title":"PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19411","citing_title":"GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08626","citing_title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2308.06721","citing_title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2307.01952","citing_title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02583","citing_title":"Stylistic Attribute Control in Latent Diffusion Models","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL","json":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL.json","graph_json":"https://pith.science/api/pith-number/JP4GN6WR2H4HK2JEYMBDM2W7JL/graph.json","events_json":"https://pith.science/api/pith-number/JP4GN6WR2H4HK2JEYMBDM2W7JL/events.json","paper":"https://pith.science/paper/JP4GN6WR"},"agent_actions":{"view_html":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL","download_json":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL.json","view_paper":"https://pith.science/paper/JP4GN6WR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05543&json=true","fetch_graph":"https://pith.science/api/pith-number/JP4GN6WR2H4HK2JEYMBDM2W7JL/graph.json","fetch_events":"https://pith.science/api/pith-number/JP4GN6WR2H4HK2JEYMBDM2W7JL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL/action/storage_attestation","attest_author":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL/action/author_attestation","sign_citation":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL/action/citation_signature","submit_replication":"https://pith.science/pith/JP4GN6WR2H4HK2JEYMBDM2W7JL/action/replication_record"}},"created_at":"2026-05-17T23:38:46.350506+00:00","updated_at":"2026-05-17T23:38:46.350506+00:00"}