{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQMRFNGDG6M47VRO2QQYW7MQ6X","short_pith_number":"pith:QQMRFNGD","schema_version":"1.0","canonical_sha256":"841912b4c33799cfd62ed4218b7d90f5f69717fa2697ef4639b297fc5782511b","source":{"kind":"arxiv","id":"2504.07963","version":1},"attestation_state":"computed","paper":{"title":"PixelFlow: Pixel-Space Generative Models with Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Peize Sun, Ping Luo, Shilong Zhang, Shoufa Chen","submitted_at":"2025-04-10T17:59:56Z","abstract_excerpt":"We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256$\\times$256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlo"},"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":"2504.07963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"48d2857e90a0674e4100752a282bcbc96083c81764a422884efe2fa09035c212","abstract_canon_sha256":"3e54fa3676ca093ff9170cc63fa0130e6d541a2a59c3145de15534e9017f3b00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:22.676225Z","signature_b64":"AGSvcTqOaHr2dJEQ0oML06Ido1BK421Dpi7Amwqou3dxEZZ9XirkK+NuoQepC3e74816Oh9tCsi152qtdSj1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841912b4c33799cfd62ed4218b7d90f5f69717fa2697ef4639b297fc5782511b","last_reissued_at":"2026-07-05T10:47:22.675798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:22.675798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixelFlow: Pixel-Space Generative Models with Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Peize Sun, Ping Luo, Shilong Zhang, Shoufa Chen","submitted_at":"2025-04-10T17:59:56Z","abstract_excerpt":"We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256$\\times$256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07963","kind":"arxiv","version":1},"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/2504.07963/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":"2504.07963","created_at":"2026-07-05T10:47:22.675857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07963v1","created_at":"2026-07-05T10:47:22.675857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07963","created_at":"2026-07-05T10:47:22.675857+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQMRFNGDG6M4","created_at":"2026-07-05T10:47:22.675857+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQMRFNGDG6M47VRO","created_at":"2026-07-05T10:47:22.675857+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQMRFNGD","created_at":"2026-07-05T10:47:22.675857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26016","citing_title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22527","citing_title":"Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00094","citing_title":"Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00647","citing_title":"Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31604","citing_title":"Representation Forcing for Bottleneck-Free Unified Multimodal Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12964","citing_title":"Asymmetric Flow Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26016","citing_title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15741","citing_title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18267","citing_title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00094","citing_title":"Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27760","citing_title":"PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27978","citing_title":"Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23531","citing_title":"PixIE: Prompted Pixel-Space Low-Light Image Enhancement","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21981","citing_title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21002","citing_title":"SURF: Signature-Retained Fast Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04883","citing_title":"Protein Autoregressive Modeling via Multiscale Structure Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24763","citing_title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15741","citing_title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17759","citing_title":"FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18267","citing_title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18749","citing_title":"WavFlow: Audio Generation in Waveform Space","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19365","citing_title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20645","citing_title":"PixelDiT: Pixel Diffusion Transformers for Image Generation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X","json":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X.json","graph_json":"https://pith.science/api/pith-number/QQMRFNGDG6M47VRO2QQYW7MQ6X/graph.json","events_json":"https://pith.science/api/pith-number/QQMRFNGDG6M47VRO2QQYW7MQ6X/events.json","paper":"https://pith.science/paper/QQMRFNGD"},"agent_actions":{"view_html":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X","download_json":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X.json","view_paper":"https://pith.science/paper/QQMRFNGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07963&json=true","fetch_graph":"https://pith.science/api/pith-number/QQMRFNGDG6M47VRO2QQYW7MQ6X/graph.json","fetch_events":"https://pith.science/api/pith-number/QQMRFNGDG6M47VRO2QQYW7MQ6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X/action/storage_attestation","attest_author":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X/action/author_attestation","sign_citation":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X/action/citation_signature","submit_replication":"https://pith.science/pith/QQMRFNGDG6M47VRO2QQYW7MQ6X/action/replication_record"}},"created_at":"2026-07-05T10:47:22.675857+00:00","updated_at":"2026-07-05T10:47:22.675857+00:00"}