{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W5HOEO55XSCA5OT2L5X5JMLG7D","short_pith_number":"pith:W5HOEO55","canonical_record":{"source":{"id":"2410.10629","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T15:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"e95928638dc8b30e52d7551e409e10ea8ac631fff31b5419ab2807f3683bd070","abstract_canon_sha256":"15afb39d277185e4366dd1119febf88c6db3f739196fb284b0c253610968d58f"},"schema_version":"1.0"},"canonical_sha256":"b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b","source":{"kind":"arxiv","id":"2410.10629","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10629","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10629v3","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10629","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"W5HOEO55XSCA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"W5HOEO55XSCA5OT2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"W5HOEO55","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W5HOEO55XSCA5OT2L5X5JMLG7D","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10629","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T15:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"e95928638dc8b30e52d7551e409e10ea8ac631fff31b5419ab2807f3683bd070","abstract_canon_sha256":"15afb39d277185e4366dd1119febf88c6db3f739196fb284b0c253610968d58f"},"schema_version":"1.0"},"canonical_sha256":"b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.190527Z","signature_b64":"avjaSPFXO2OZr70FL6fha0OdL8nCdDjGdpkwT/3uCI82FDS9+SqS3y6mDIfPJDxWaTu1Tpz+x7bP/XzrZ9k8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b","last_reissued_at":"2026-05-17T23:39:05.189950Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.189950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10629","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRUPN1JzxEgR2e6mU8vNrWpNNtr5Czf+/S6kWcVt9SBcOZYi2SrCr2Ufw2KgUlIsf6jlpDWbPvcmSZLqOq6qDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:07:34.688410Z"},"content_sha256":"3b6fd3ba7f1bb7866d3e05556fa176c843681e576e725d23e94832d66eb56f85","schema_version":"1.0","event_id":"sha256:3b6fd3ba7f1bb7866d3e05556fa176c843681e576e725d23e94832d66eb56f85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W5HOEO55XSCA5OT2L5X5JMLG7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Han Cai, Haotian Tang, Junsong Chen, Junyu Chen, Ligeng Zhu, Muyang Li, Song Han, Yao Lu, Yujun Lin, Zhekai Zhang","submitted_at":"2024-10-14T15:36:42Z","abstract_excerpt":"We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096$\\times$4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8$\\times$, we trained an AE that can compress images 32$\\times$, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 32x deep-compression autoencoder preserves sufficient perceptual quality and text alignment at high resolutions without introducing artifacts that linear attention cannot correct.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b59caa39f172598343a38d0cc619ff6837b0e3aaf67b4883cf3057076ac0fbaa"},"source":{"id":"2410.10629","kind":"arxiv","version":3},"verdict":{"id":"dc9f5c27-201c-4f60-b8ef-12c3f83aef97","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:52:14.386983Z","strongest_claim":"Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput.","one_line_summary":"Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 32x deep-compression autoencoder preserves sufficient perceptual quality and text alignment at high resolutions without introducing artifacts that linear attention cannot correct.","pith_extraction_headline":"Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs."},"references":{"count":29,"sample":[{"doi":"","year":null,"title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","work_id":"2cd7b629-ab37-4ce5-b51e-aa4d99547468","ref_index":1,"cited_arxiv_id":"2211.01324","is_internal_anchor":true},{"doi":"","year":2022,"title":"All are worth words: a vit backbone for score-based diffusion models","work_id":"98f35013-1df4-4a37-8b71-6206599f9833","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","ref_index":3,"cited_arxiv_id":"2005.14165","is_internal_anchor":true},{"doi":"","year":2020,"title":"Mahoney, and Kurt Keutzer","work_id":"911a6b35-56a0-42b3-9951-b6f6ac9da2ed","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"PixArt- : Weak-to-strong training of diffusion transformer for 4k text-to-image generation","work_id":"5dc0cfb7-2014-4631-be70-f632bf6ca9ec","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"8dab2fbac73eaa14a78aa7dcdf69c72b55b8576ffa2200f5345add58a55a44ee","internal_anchors":11},"formal_canon":{"evidence_count":1,"snapshot_sha256":"a7925ba5afbca173b270de0c9e79d4db4aa675988ba6f9d8760e372d6fde38d2"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"dc9f5c27-201c-4f60-b8ef-12c3f83aef97"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/81F+Fp2lsHgX/6pab3ztt29ZnXgpKx7rDkX2OrKEau97wHIBLFjxfvZg8qFzEyaNf44rgZ9hIH0lC2XTOTIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:07:34.689327Z"},"content_sha256":"c32bd7f9401d1dbdd5cf1cbf0803abfa2763299e376a2bbd039beb23e207ccb2","schema_version":"1.0","event_id":"sha256:c32bd7f9401d1dbdd5cf1cbf0803abfa2763299e376a2bbd039beb23e207ccb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5HOEO55XSCA5OT2L5X5JMLG7D/bundle.json","state_url":"https://pith.science/pith/W5HOEO55XSCA5OT2L5X5JMLG7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5HOEO55XSCA5OT2L5X5JMLG7D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T15:07:34Z","links":{"resolver":"https://pith.science/pith/W5HOEO55XSCA5OT2L5X5JMLG7D","bundle":"https://pith.science/pith/W5HOEO55XSCA5OT2L5X5JMLG7D/bundle.json","state":"https://pith.science/pith/W5HOEO55XSCA5OT2L5X5JMLG7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5HOEO55XSCA5OT2L5X5JMLG7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W5HOEO55XSCA5OT2L5X5JMLG7D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"15afb39d277185e4366dd1119febf88c6db3f739196fb284b0c253610968d58f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T15:36:42Z","title_canon_sha256":"e95928638dc8b30e52d7551e409e10ea8ac631fff31b5419ab2807f3683bd070"},"schema_version":"1.0","source":{"id":"2410.10629","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10629","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10629v3","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10629","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"W5HOEO55XSCA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"W5HOEO55XSCA5OT2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"W5HOEO55","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c32bd7f9401d1dbdd5cf1cbf0803abfa2763299e376a2bbd039beb23e207ccb2","target":"graph","created_at":"2026-05-17T23:39:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 32x deep-compression autoencoder preserves sufficient perceptual quality and text alignment at high resolutions without introducing artifacts that linear attention cannot correct."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs."}],"snapshot_sha256":"b59caa39f172598343a38d0cc619ff6837b0e3aaf67b4883cf3057076ac0fbaa"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"a7925ba5afbca173b270de0c9e79d4db4aa675988ba6f9d8760e372d6fde38d2"},"paper":{"abstract_excerpt":"We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096$\\times$4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8$\\times$, we trained an AE that can compress images 32$\\times$, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolu","authors_text":"Enze Xie, Han Cai, Haotian Tang, Junsong Chen, Junyu Chen, Ligeng Zhu, Muyang Li, Song Han, Yao Lu, Yujun Lin, Zhekai Zhang","cross_cats":[],"headline":"Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T15:36:42Z","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers"},"references":{"count":29,"internal_anchors":11,"resolved_work":29,"sample":[{"cited_arxiv_id":"2211.01324","doi":"","is_internal_anchor":true,"ref_index":1,"title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","work_id":"2cd7b629-ab37-4ce5-b51e-aa4d99547468","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"All are worth words: a vit backbone for score-based diffusion models","work_id":"98f35013-1df4-4a37-8b71-6206599f9833","year":2022},{"cited_arxiv_id":"2005.14165","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","year":2005},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Mahoney, and Kurt Keutzer","work_id":"911a6b35-56a0-42b3-9951-b6f6ac9da2ed","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"PixArt- : Weak-to-strong training of diffusion transformer for 4k text-to-image generation","work_id":"5dc0cfb7-2014-4631-be70-f632bf6ca9ec","year":null}],"snapshot_sha256":"8dab2fbac73eaa14a78aa7dcdf69c72b55b8576ffa2200f5345add58a55a44ee"},"source":{"id":"2410.10629","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T00:52:14.386983Z","id":"dc9f5c27-201c-4f60-b8ef-12c3f83aef97","model_set":{"reader":"grok-4.3"},"one_line_summary":"Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs.","strongest_claim":"Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput.","weakest_assumption":"The 32x deep-compression autoencoder preserves sufficient perceptual quality and text alignment at high resolutions without introducing artifacts that linear attention cannot correct."}},"verdict_id":"dc9f5c27-201c-4f60-b8ef-12c3f83aef97"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3b6fd3ba7f1bb7866d3e05556fa176c843681e576e725d23e94832d66eb56f85","target":"record","created_at":"2026-05-17T23:39:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"15afb39d277185e4366dd1119febf88c6db3f739196fb284b0c253610968d58f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T15:36:42Z","title_canon_sha256":"e95928638dc8b30e52d7551e409e10ea8ac631fff31b5419ab2807f3683bd070"},"schema_version":"1.0","source":{"id":"2410.10629","kind":"arxiv","version":3}},"canonical_sha256":"b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b","first_computed_at":"2026-05-17T23:39:05.189950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:05.189950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"avjaSPFXO2OZr70FL6fha0OdL8nCdDjGdpkwT/3uCI82FDS9+SqS3y6mDIfPJDxWaTu1Tpz+x7bP/XzrZ9k8Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:05.190527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10629","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b6fd3ba7f1bb7866d3e05556fa176c843681e576e725d23e94832d66eb56f85","sha256:c32bd7f9401d1dbdd5cf1cbf0803abfa2763299e376a2bbd039beb23e207ccb2"],"state_sha256":"51f76c30cec40ffc0e7776ec5f26f09a52661436a01fff56a148bf3036fb472e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/gd2IughLDmZ0+y7ggBOjg9UOlRNxn5KIOj03U0pmtZKKnFF6KO7robkZgN8tAVSaBB+ChBQvwx4dXBZIn2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:07:34.693431Z","bundle_sha256":"c892154b62b379db925c36fb9fe947c10014ba89eed7b71b058f51a1a4ab16ac"}}