{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q4X3FKBQD2ZEKQQAKO44VQH6UU","short_pith_number":"pith:Q4X3FKBQ","schema_version":"1.0","canonical_sha256":"872fb2a8301eb245420053b9cac0fea51a9373a7b55c7a97d6097984565dca73","source":{"kind":"arxiv","id":"2108.00946","version":2},"attestation_state":"computed","paper":{"title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Gal Chechik, Haggai Maron, Or Patashnik, Rinon Gal","submitted_at":"2021-08-02T14:46:46Z","abstract_excerpt":"Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image? In other words: can an image generator be trained \"blindly\"? Leveraging the semantic power of large scale Contrastive-Language-Image-Pre-training (CLIP) models, we present a text-driven method that allows shifting a generative model to new domains, without having to collect even a single image. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains characterized by diverse styles "},"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":"2108.00946","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T14:46:46Z","cross_cats_sorted":["cs.CL","cs.GR","cs.LG"],"title_canon_sha256":"65ca6c295303c2fd72f7b5f82a8e6210627bf5e7904619a9e19588f29df36cf3","abstract_canon_sha256":"4d7200d6ab1a04efeea7f2c4f82ed96a11b43bb123eb3d4505291f869257fad5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:26.075864Z","signature_b64":"J9oNGVo/r+j+ftdxJkxTzDvoMmhPOrZaThmUyOUZnk+2SOwMQ3pqNKbv4F1/9CUxdq2uLZ6pVX0mpUGEECImCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872fb2a8301eb245420053b9cac0fea51a9373a7b55c7a97d6097984565dca73","last_reissued_at":"2026-07-05T03:41:26.075449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:26.075449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Gal Chechik, Haggai Maron, Or Patashnik, Rinon Gal","submitted_at":"2021-08-02T14:46:46Z","abstract_excerpt":"Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image? In other words: can an image generator be trained \"blindly\"? Leveraging the semantic power of large scale Contrastive-Language-Image-Pre-training (CLIP) models, we present a text-driven method that allows shifting a generative model to new domains, without having to collect even a single image. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains characterized by diverse styles "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00946","kind":"arxiv","version":2},"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/2108.00946/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":"2108.00946","created_at":"2026-07-05T03:41:26.075506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00946v2","created_at":"2026-07-05T03:41:26.075506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00946","created_at":"2026-07-05T03:41:26.075506+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4X3FKBQD2ZE","created_at":"2026-07-05T03:41:26.075506+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4X3FKBQD2ZEKQQA","created_at":"2026-07-05T03:41:26.075506+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4X3FKBQ","created_at":"2026-07-05T03:41:26.075506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28628","citing_title":"Envisage: Diffusion-Based Rhinoplasty Goal Visualization with Mask-Decomposed Evaluation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01618","citing_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01626","citing_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU","json":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU.json","graph_json":"https://pith.science/api/pith-number/Q4X3FKBQD2ZEKQQAKO44VQH6UU/graph.json","events_json":"https://pith.science/api/pith-number/Q4X3FKBQD2ZEKQQAKO44VQH6UU/events.json","paper":"https://pith.science/paper/Q4X3FKBQ"},"agent_actions":{"view_html":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU","download_json":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU.json","view_paper":"https://pith.science/paper/Q4X3FKBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00946&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4X3FKBQD2ZEKQQAKO44VQH6UU/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4X3FKBQD2ZEKQQAKO44VQH6UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU/action/storage_attestation","attest_author":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU/action/author_attestation","sign_citation":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU/action/citation_signature","submit_replication":"https://pith.science/pith/Q4X3FKBQD2ZEKQQAKO44VQH6UU/action/replication_record"}},"created_at":"2026-07-05T03:41:26.075506+00:00","updated_at":"2026-07-05T03:41:26.075506+00:00"}