{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C2YITPAKE45VNAYAONL7LSDD3S","short_pith_number":"pith:C2YITPAK","schema_version":"1.0","canonical_sha256":"16b089bc0a273b5683007357f5c863dc88ce2ea39d39eb82e51db4670cdd539f","source":{"kind":"arxiv","id":"2411.04746","version":3},"attestation_state":"computed","paper":{"title":"Taming Rectified Flow for Inversion and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangshan Wang, Jiayi Guo, Junfu Pu, Nisha Huang, Xiu Li, Ying Shan, Yue Ma, Yuxin Chen, Zhongang Qi","submitted_at":"2024-11-07T14:29:02Z","abstract_excerpt":"Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust generative capabilities, these models often struggle with inversion inaccuracies, which could further limit their effectiveness in downstream tasks such as image and video editing. To address this issue, we propose RF-Solver, a novel training-free sampler that effectively enhances inversion precision by mitigating the errors in the ODE-solving process of rectified flow. Specifically, we derive the exact formulation of the "},"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":"2411.04746","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T14:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"a2d0e31d552e39a362e231af5c70c94816bda6462e29f35a61a262986d35b72d","abstract_canon_sha256":"2f50eaec18ecb0779e23976a026933fe3e41e9a394b89eb297251463685fb47d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:47.969341Z","signature_b64":"zJbrOYVCOwczAzg+ZBaxzBq3ivUxoI6EKTB1pfm1+FKE+rUjrck35jEw1ArmZx7kotAR4M4uhYG+K49mYuY6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16b089bc0a273b5683007357f5c863dc88ce2ea39d39eb82e51db4670cdd539f","last_reissued_at":"2026-07-05T11:20:47.968021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:47.968021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming Rectified Flow for Inversion and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangshan Wang, Jiayi Guo, Junfu Pu, Nisha Huang, Xiu Li, Ying Shan, Yue Ma, Yuxin Chen, Zhongang Qi","submitted_at":"2024-11-07T14:29:02Z","abstract_excerpt":"Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust generative capabilities, these models often struggle with inversion inaccuracies, which could further limit their effectiveness in downstream tasks such as image and video editing. To address this issue, we propose RF-Solver, a novel training-free sampler that effectively enhances inversion precision by mitigating the errors in the ODE-solving process of rectified flow. Specifically, we derive the exact formulation of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04746","kind":"arxiv","version":3},"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/2411.04746/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":"2411.04746","created_at":"2026-07-05T11:20:47.968091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04746v3","created_at":"2026-07-05T11:20:47.968091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04746","created_at":"2026-07-05T11:20:47.968091+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2YITPAKE45V","created_at":"2026-07-05T11:20:47.968091+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2YITPAKE45VNAYA","created_at":"2026-07-05T11:20:47.968091+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2YITPAK","created_at":"2026-07-05T11:20:47.968091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26740","citing_title":"LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07760","citing_title":"scCBGM: Interpretable Single-Cell Counterfactual Editing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03216","citing_title":"Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06498","citing_title":"Semantic-Structural Alignment for Generative Pictorial Charts","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29319","citing_title":"FDM-MFVT: Few-step Sampling Diffusion Model for Mask-Free Virtual Try-On","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30003","citing_title":"GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22051","citing_title":"EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16603","citing_title":"Controlla: Learning Controllability via Graph-Constrained Latent Geometry","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15803","citing_title":"Embedding-perturbed Exploration Preference Optimization for Flow Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15661","citing_title":"VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation","ref_index":16,"is_internal_anchor":false},{"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19974","citing_title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02438","citing_title":"Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20038","citing_title":"FluSplat: Sparse-View 3D Editing without Test-Time Optimization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14591","citing_title":"Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15871","citing_title":"UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S","json":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S.json","graph_json":"https://pith.science/api/pith-number/C2YITPAKE45VNAYAONL7LSDD3S/graph.json","events_json":"https://pith.science/api/pith-number/C2YITPAKE45VNAYAONL7LSDD3S/events.json","paper":"https://pith.science/paper/C2YITPAK"},"agent_actions":{"view_html":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S","download_json":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S.json","view_paper":"https://pith.science/paper/C2YITPAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04746&json=true","fetch_graph":"https://pith.science/api/pith-number/C2YITPAKE45VNAYAONL7LSDD3S/graph.json","fetch_events":"https://pith.science/api/pith-number/C2YITPAKE45VNAYAONL7LSDD3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S/action/storage_attestation","attest_author":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S/action/author_attestation","sign_citation":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S/action/citation_signature","submit_replication":"https://pith.science/pith/C2YITPAKE45VNAYAONL7LSDD3S/action/replication_record"}},"created_at":"2026-07-05T11:20:47.968091+00:00","updated_at":"2026-07-05T11:20:47.968091+00:00"}