{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JZGZOOHUEH4TIAXEGJHUFJJGS6","short_pith_number":"pith:JZGZOOHU","schema_version":"1.0","canonical_sha256":"4e4d9738f421f93402e4324f42a5269784fff1acaab8244900f49b175f89f709","source":{"kind":"arxiv","id":"2302.11710","version":2},"attestation_state":"computed","paper":{"title":"Controlled and Conditional Text to Image Generation with Diffusion Prior","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajinkya Kale, Alvin Ghouas, Baldo Faieta, Fengbin Chen, Hareesh Ravi, Malavika Ramprasad, Midhun Harikumar, Naveen Marri, Pranav Aggarwal, Purvak Lapsiya, Ritiz Tambi, Sachin Kelkar, Sarah Saber, Sudharshan Reddy Kakumanu, Vinh Khuc","submitted_at":"2023-02-23T00:10:40Z","abstract_excerpt":"Denoising Diffusion models have shown remarkable performance in generating diverse, high quality images from text. Numerous techniques have been proposed on top of or in alignment with models like Stable Diffusion and Imagen that generate images directly from text. A lesser explored approach is DALLE-2's two step process comprising a Diffusion Prior that generates a CLIP image embedding from text and a Diffusion Decoder that generates an image from a CLIP image embedding. We explore the capabilities of the Diffusion Prior and the advantages of an intermediate CLIP representation. We observe th"},"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":"2302.11710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-23T00:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"53a72a0e79ca3d8eacc0d705d31b09b362aba2044a96770ff490fa636de933c5","abstract_canon_sha256":"e954ac4dee126736baf039721337fba9cef817fbafe60d23ea552929de626415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:29.931528Z","signature_b64":"1AjKF8wiWMLzBHTQ4tJBANp6PCrCNL3ItEcjxS/wwo6oQlFNFZ/M/23Zek2OLhxYyKO4RjyTISWw1a2YKXHGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e4d9738f421f93402e4324f42a5269784fff1acaab8244900f49b175f89f709","last_reissued_at":"2026-07-05T06:36:29.930997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:29.930997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlled and Conditional Text to Image Generation with Diffusion Prior","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajinkya Kale, Alvin Ghouas, Baldo Faieta, Fengbin Chen, Hareesh Ravi, Malavika Ramprasad, Midhun Harikumar, Naveen Marri, Pranav Aggarwal, Purvak Lapsiya, Ritiz Tambi, Sachin Kelkar, Sarah Saber, Sudharshan Reddy Kakumanu, Vinh Khuc","submitted_at":"2023-02-23T00:10:40Z","abstract_excerpt":"Denoising Diffusion models have shown remarkable performance in generating diverse, high quality images from text. Numerous techniques have been proposed on top of or in alignment with models like Stable Diffusion and Imagen that generate images directly from text. A lesser explored approach is DALLE-2's two step process comprising a Diffusion Prior that generates a CLIP image embedding from text and a Diffusion Decoder that generates an image from a CLIP image embedding. We explore the capabilities of the Diffusion Prior and the advantages of an intermediate CLIP representation. We observe th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11710","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/2302.11710/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":"2302.11710","created_at":"2026-07-05T06:36:29.931058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11710v2","created_at":"2026-07-05T06:36:29.931058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11710","created_at":"2026-07-05T06:36:29.931058+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZGZOOHUEH4T","created_at":"2026-07-05T06:36:29.931058+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZGZOOHUEH4TIAXE","created_at":"2026-07-05T06:36:29.931058+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZGZOOHU","created_at":"2026-07-05T06:36:29.931058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6","json":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6.json","graph_json":"https://pith.science/api/pith-number/JZGZOOHUEH4TIAXEGJHUFJJGS6/graph.json","events_json":"https://pith.science/api/pith-number/JZGZOOHUEH4TIAXEGJHUFJJGS6/events.json","paper":"https://pith.science/paper/JZGZOOHU"},"agent_actions":{"view_html":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6","download_json":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6.json","view_paper":"https://pith.science/paper/JZGZOOHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11710&json=true","fetch_graph":"https://pith.science/api/pith-number/JZGZOOHUEH4TIAXEGJHUFJJGS6/graph.json","fetch_events":"https://pith.science/api/pith-number/JZGZOOHUEH4TIAXEGJHUFJJGS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6/action/storage_attestation","attest_author":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6/action/author_attestation","sign_citation":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6/action/citation_signature","submit_replication":"https://pith.science/pith/JZGZOOHUEH4TIAXEGJHUFJJGS6/action/replication_record"}},"created_at":"2026-07-05T06:36:29.931058+00:00","updated_at":"2026-07-05T06:36:29.931058+00:00"}