{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PYGZTKHM7TAOW2T3RHHTJPE3OM","short_pith_number":"pith:PYGZTKHM","schema_version":"1.0","canonical_sha256":"7e0d99a8ecfcc0eb6a7b89cf34bc9b7322388ec7ce57e972c195b60472001e24","source":{"kind":"arxiv","id":"2111.14822","version":3},"attestation_state":"computed","paper":{"title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bo Zhang, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Lu Yuan, Shuyang Gu","submitted_at":"2021-11-29T18:59:46Z","abstract_excerpt":"We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). We find that this latent-space method is well-suited for text-to-image generation tasks because it not only eliminates the unidirectional bias with existing methods but also allows us to incorporate a mask-and-replace diffusion strategy to avoid the accumulation of errors, which is a serious problem w"},"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":"2111.14822","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T18:59:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"56224aade1924f001d739b95d040cba4b57f9c1dcf8776e944d3614348815da3","abstract_canon_sha256":"cf57bcebd7dab94d95f56e24d1bff9e3c8e075d209b9b55399320fc06272cdb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:44.894113Z","signature_b64":"kwwfcwyrb55sD79H/XrGXNfwUuvGDdIQRGMsep3A8u2WLWZWeg8cILfxXW13MG2QL2tOdiVg00e9NuksQ+apBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0d99a8ecfcc0eb6a7b89cf34bc9b7322388ec7ce57e972c195b60472001e24","last_reissued_at":"2026-07-05T04:01:44.893635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:44.893635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bo Zhang, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Lu Yuan, Shuyang Gu","submitted_at":"2021-11-29T18:59:46Z","abstract_excerpt":"We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). We find that this latent-space method is well-suited for text-to-image generation tasks because it not only eliminates the unidirectional bias with existing methods but also allows us to incorporate a mask-and-replace diffusion strategy to avoid the accumulation of errors, which is a serious problem w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14822","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/2111.14822/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":"2111.14822","created_at":"2026-07-05T04:01:44.893693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.14822v3","created_at":"2026-07-05T04:01:44.893693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14822","created_at":"2026-07-05T04:01:44.893693+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYGZTKHM7TAO","created_at":"2026-07-05T04:01:44.893693+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYGZTKHM7TAOW2T3","created_at":"2026-07-05T04:01:44.893693+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYGZTKHM","created_at":"2026-07-05T04:01:44.893693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22765","citing_title":"Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02777","citing_title":"PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2210.08402","citing_title":"LAION-5B: An open large-scale dataset for training next generation image-text models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2206.10789","citing_title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","ref_index":49,"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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07193","citing_title":"Coupling Models for One-Step Discrete Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM","json":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM.json","graph_json":"https://pith.science/api/pith-number/PYGZTKHM7TAOW2T3RHHTJPE3OM/graph.json","events_json":"https://pith.science/api/pith-number/PYGZTKHM7TAOW2T3RHHTJPE3OM/events.json","paper":"https://pith.science/paper/PYGZTKHM"},"agent_actions":{"view_html":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM","download_json":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM.json","view_paper":"https://pith.science/paper/PYGZTKHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.14822&json=true","fetch_graph":"https://pith.science/api/pith-number/PYGZTKHM7TAOW2T3RHHTJPE3OM/graph.json","fetch_events":"https://pith.science/api/pith-number/PYGZTKHM7TAOW2T3RHHTJPE3OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM/action/storage_attestation","attest_author":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM/action/author_attestation","sign_citation":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM/action/citation_signature","submit_replication":"https://pith.science/pith/PYGZTKHM7TAOW2T3RHHTJPE3OM/action/replication_record"}},"created_at":"2026-07-05T04:01:44.893693+00:00","updated_at":"2026-07-05T04:01:44.893693+00:00"}