{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMIVPW7LUWYUYOOQ3K3OFKJ74J","short_pith_number":"pith:JMIVPW7L","schema_version":"1.0","canonical_sha256":"4b1157dbeba5b14c39d0dab6e2a93fe27ae7bd67c17b0f37ab46229c8065a565","source":{"kind":"arxiv","id":"2410.01731","version":1},"attestation_state":"computed","paper":{"title":"ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.GR"],"primary_cat":"cs.CV","authors_text":"Adi Haviv, Amit H. Bermano, Daniel Cohen-Or, Gal Chechik, Rinon Gal, Yuval Alaluf","submitted_at":"2024-10-02T16:43:24Z","abstract_excerpt":"The practical use of text-to-image generation has evolved from simple, monolithic models to complex workflows that combine multiple specialized components. While workflow-based approaches can lead to improved image quality, crafting effective workflows requires significant expertise, owing to the large number of available components, their complex inter-dependence, and their dependence on the generation prompt. Here, we introduce the novel task of prompt-adaptive workflow generation, where the goal is to automatically tailor a workflow to each user prompt. We propose two LLM-based approaches t"},"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":"2410.01731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T16:43:24Z","cross_cats_sorted":["cs.CL","cs.GR"],"title_canon_sha256":"86418fe705989b8c5e29b6c4bcd6da0309908b999723122c13cc6404db21f5ec","abstract_canon_sha256":"3393ab17e068050b1bb269351ff944ca36e45700757fa5c7a8be64ed0df9d300"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:51.353782Z","signature_b64":"RAiQ+1gaJbH+1vlxe7C6s2WrJHJ8VA+yp6MDfcfRqG6Z1h6SgjBEEGZptKOvqw7d+kIEU8AOxzpDyxK6nNAHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b1157dbeba5b14c39d0dab6e2a93fe27ae7bd67c17b0f37ab46229c8065a565","last_reissued_at":"2026-07-05T09:14:51.353296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:51.353296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.GR"],"primary_cat":"cs.CV","authors_text":"Adi Haviv, Amit H. Bermano, Daniel Cohen-Or, Gal Chechik, Rinon Gal, Yuval Alaluf","submitted_at":"2024-10-02T16:43:24Z","abstract_excerpt":"The practical use of text-to-image generation has evolved from simple, monolithic models to complex workflows that combine multiple specialized components. While workflow-based approaches can lead to improved image quality, crafting effective workflows requires significant expertise, owing to the large number of available components, their complex inter-dependence, and their dependence on the generation prompt. Here, we introduce the novel task of prompt-adaptive workflow generation, where the goal is to automatically tailor a workflow to each user prompt. We propose two LLM-based approaches t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01731","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/2410.01731/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":"2410.01731","created_at":"2026-07-05T09:14:51.353366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01731v1","created_at":"2026-07-05T09:14:51.353366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01731","created_at":"2026-07-05T09:14:51.353366+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMIVPW7LUWYU","created_at":"2026-07-05T09:14:51.353366+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMIVPW7LUWYUYOOQ","created_at":"2026-07-05T09:14:51.353366+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMIVPW7L","created_at":"2026-07-05T09:14:51.353366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01709","citing_title":"COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09151","citing_title":"Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03530","citing_title":"How Far Are We from Generating Missing Modalities with Foundation Models?","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J","json":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J.json","graph_json":"https://pith.science/api/pith-number/JMIVPW7LUWYUYOOQ3K3OFKJ74J/graph.json","events_json":"https://pith.science/api/pith-number/JMIVPW7LUWYUYOOQ3K3OFKJ74J/events.json","paper":"https://pith.science/paper/JMIVPW7L"},"agent_actions":{"view_html":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J","download_json":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J.json","view_paper":"https://pith.science/paper/JMIVPW7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01731&json=true","fetch_graph":"https://pith.science/api/pith-number/JMIVPW7LUWYUYOOQ3K3OFKJ74J/graph.json","fetch_events":"https://pith.science/api/pith-number/JMIVPW7LUWYUYOOQ3K3OFKJ74J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J/action/storage_attestation","attest_author":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J/action/author_attestation","sign_citation":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J/action/citation_signature","submit_replication":"https://pith.science/pith/JMIVPW7LUWYUYOOQ3K3OFKJ74J/action/replication_record"}},"created_at":"2026-07-05T09:14:51.353366+00:00","updated_at":"2026-07-05T09:14:51.353366+00:00"}