{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PP4G2WDIUPAHG6DSL23G2IU34X","short_pith_number":"pith:PP4G2WDI","schema_version":"1.0","canonical_sha256":"7bf86d5868a3c07378725eb66d229be5c1806fd7ab0d1416993714fe1e88d3d4","source":{"kind":"arxiv","id":"2303.07909","version":3},"attestation_state":"computed","paper":{"title":"Text-to-image Diffusion Models in Generative AI: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Chenshuang Zhang, In So Kweon, Junmo Kim, Mengchun Zhang","submitted_at":"2023-03-14T13:49:54Z","abstract_excerpt":"This survey reviews the progress of diffusion models in generating images from text, ~\\textit{i.e.} text-to-image diffusion models. As a self-contained work, this survey starts with a brief introduction of how diffusion models work for image synthesis, followed by the background for text-conditioned image synthesis. Based on that, we present an organized review of pioneering methods and their improvements on text-to-image generation. We further summarize applications beyond image generation, such as text-guided generation for various modalities like videos, and text-guided image editing. Beyon"},"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":"2303.07909","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-14T13:49:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5e04cc72801c8b40ed3897578e207808f313d1022e6dc5cf0827544a2e90ab21","abstract_canon_sha256":"de6bf89690cdd3fcd33bfa207ae33a800eb26214ce604e206b916cc904e6bc69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:39.119753Z","signature_b64":"lFZofDa7f/T6haWnXeQV5dNejKWFl/mGqB5LrzhdFgC5ajN39rQ5ULUG2UuW6y/bRvddEbcCKryB/1AAXp3fCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bf86d5868a3c07378725eb66d229be5c1806fd7ab0d1416993714fe1e88d3d4","last_reissued_at":"2026-07-05T09:32:39.119326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:39.119326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-image Diffusion Models in Generative AI: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Chenshuang Zhang, In So Kweon, Junmo Kim, Mengchun Zhang","submitted_at":"2023-03-14T13:49:54Z","abstract_excerpt":"This survey reviews the progress of diffusion models in generating images from text, ~\\textit{i.e.} text-to-image diffusion models. As a self-contained work, this survey starts with a brief introduction of how diffusion models work for image synthesis, followed by the background for text-conditioned image synthesis. Based on that, we present an organized review of pioneering methods and their improvements on text-to-image generation. We further summarize applications beyond image generation, such as text-guided generation for various modalities like videos, and text-guided image editing. Beyon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07909","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/2303.07909/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":"2303.07909","created_at":"2026-07-05T09:32:39.119387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07909v3","created_at":"2026-07-05T09:32:39.119387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07909","created_at":"2026-07-05T09:32:39.119387+00:00"},{"alias_kind":"pith_short_12","alias_value":"PP4G2WDIUPAH","created_at":"2026-07-05T09:32:39.119387+00:00"},{"alias_kind":"pith_short_16","alias_value":"PP4G2WDIUPAHG6DS","created_at":"2026-07-05T09:32:39.119387+00:00"},{"alias_kind":"pith_short_8","alias_value":"PP4G2WDI","created_at":"2026-07-05T09:32:39.119387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26930","citing_title":"PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02361","citing_title":"Data Comics for Education: Evaluating Effectiveness, Benefits, and the Ethics of AI-Assisted Creation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02361","citing_title":"Data Comics for Education: Evaluating Effectiveness, Benefits, and the Ethics of AI-Assisted Creation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28421","citing_title":"JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2405.09806","citing_title":"A Generalist Model for Diverse Text-Guided Medical Image Synthesis","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22437","citing_title":"EmoCtrl: Controllable Emotional Image Content Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01554","citing_title":"InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07265","citing_title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03719","citing_title":"A public dataset of Ariel simulated observations for developing exoplanetary atmosphere data reduction pipelines","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10937","citing_title":"Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07253","citing_title":"LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X","json":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X.json","graph_json":"https://pith.science/api/pith-number/PP4G2WDIUPAHG6DSL23G2IU34X/graph.json","events_json":"https://pith.science/api/pith-number/PP4G2WDIUPAHG6DSL23G2IU34X/events.json","paper":"https://pith.science/paper/PP4G2WDI"},"agent_actions":{"view_html":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X","download_json":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X.json","view_paper":"https://pith.science/paper/PP4G2WDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07909&json=true","fetch_graph":"https://pith.science/api/pith-number/PP4G2WDIUPAHG6DSL23G2IU34X/graph.json","fetch_events":"https://pith.science/api/pith-number/PP4G2WDIUPAHG6DSL23G2IU34X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X/action/storage_attestation","attest_author":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X/action/author_attestation","sign_citation":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X/action/citation_signature","submit_replication":"https://pith.science/pith/PP4G2WDIUPAHG6DSL23G2IU34X/action/replication_record"}},"created_at":"2026-07-05T09:32:39.119387+00:00","updated_at":"2026-07-05T09:32:39.119387+00:00"}