{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/tensor-to-pil","entry":"tensor_to_pil","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":16,"n_papers_ran":14,"n_papers_ran_no_instrument_failure":9,"n_papers_ran_instrument_only":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":15,"n_samples_ran":13,"n_samples_constructed":0,"n_samples_ran_checked":9,"n_samples_instrument":4,"n_samples_unverified":2,"n_samples_fingerprinted":1,"n_places":16,"n_places_pointer_only":5,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":2,"ran":9,"unverified":2},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2503.09641","arxiv_id_is_arxiv":true,"paper":"/paper/sana-sprint-one-step-diffusion-with","title":"SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":"archive","repo":"NVlabs/Sana","path":"app/sana_pipeline_inpaint.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/sana_pipeline_inpaint.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","code_sha256":"01b02ff9e21d4414","code_sha256_prefix":"01b02ff9e21d4414","mcp_get_code":{"code_sha256":"01b02ff9e21d4414"}},{"arxiv_id":"2502.13995","arxiv_id_is_arxiv":true,"paper":"/paper/fantasyid-face-knowledge-enhanced-id","title":"FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation","date":null,"month_inferred_from_arxiv_id":"2025-02","title_source":"archive","repo":"Fantasy-AMAP/fantasy-id","path":"models/utils.py","file_url":"https://github.com/Fantasy-AMAP/fantasy-id/blob/HEAD/models/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6d7dce3292d1b3e1","code_sha256_prefix":"6d7dce3292d1b3e1","mcp_get_code":{"code_sha256":"6d7dce3292d1b3e1"}},{"arxiv_id":"2502.13987","arxiv_id_is_arxiv":true,"paper":"/paper/selfage-personalized-facial-age","title":"SelfAge: Personalized Facial Age Transformation Using Self-reference Images","date":null,"month_inferred_from_arxiv_id":"2025-02","title_source":"archive","repo":"shiiiijp/selfage","path":"utils/null_inversion.py","file_url":"https://github.com/shiiiijp/selfage/blob/HEAD/utils/null_inversion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8ee6b99a7c5c84b6","code_sha256_prefix":"8ee6b99a7c5c84b6","mcp_get_code":{"code_sha256":"8ee6b99a7c5c84b6"}},{"arxiv_id":"2502.13146","arxiv_id_is_arxiv":true,"paper":"/paper/re-align-aligning-vision-language-models-via","title":"Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization","date":"2025-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taco-group/re-align","path":"train_rdpo.py","file_url":"https://github.com/taco-group/re-align/blob/HEAD/train_rdpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"086706fdb4ecf607","code_sha256_prefix":"086706fdb4ecf607","mcp_get_code":{"code_sha256":"086706fdb4ecf607"}},{"arxiv_id":"2501.01790","arxiv_id_is_arxiv":true,"paper":"/paper/ingredients-blending-custom-photos-with-video","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","date":"2025-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/ingredients","path":"models/utils.py","file_url":"https://github.com/feizc/ingredients/blob/HEAD/models/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"aabdf33f95d21edf","code_sha256_prefix":"aabdf33f95d21edf","mcp_get_code":{"code_sha256":"aabdf33f95d21edf"}},{"arxiv_id":"2412.06566","arxiv_id_is_arxiv":true,"paper":"/paper/dex-data-channel-extension-for-efficient-cnn","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Nokia-Bell-Labs/data-channel-extension","path":"utils/data_augmentation.py","file_url":"https://github.com/Nokia-Bell-Labs/data-channel-extension/blob/HEAD/utils/data_augmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Nokia-Bell-Labs/data-channel-extension (NOASSERTION)","code_sha256":"0a28a925c0af32a6","code_sha256_prefix":"0a28a925c0af32a6","mcp_get_code":{"code_sha256":"0a28a925c0af32a6"}},{"arxiv_id":"2407.16364","arxiv_id_is_arxiv":true,"paper":"/paper/harmonizing-visual-text-comprehension-and","title":"Harmonizing Visual Text Comprehension and Generation","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/textharmony","path":"TextHarmony/utils/clip_sim_score.py","file_url":"https://github.com/bytedance/textharmony/blob/HEAD/TextHarmony/utils/clip_sim_score.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1af97eee0d5e9a78","code_sha256_prefix":"1af97eee0d5e9a78","mcp_get_code":{"code_sha256":"1af97eee0d5e9a78"}},{"arxiv_id":"2407.11394","arxiv_id_is_arxiv":true,"paper":"/paper/dreamcatalyst-fast-and-high-quality-3d","title":"DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation","date":"2024-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaist-cvml-lab/DreamCatalyst","path":"nerfstudio/dc/dc.py","file_url":"https://github.com/kaist-cvml-lab/DreamCatalyst/blob/HEAD/nerfstudio/dc/dc.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, kaist-cvml-lab/DreamCatalyst when it was checked","code_sha256":"9ab7f0a872fbd552","code_sha256_prefix":"9ab7f0a872fbd552","mcp_get_code":{"code_sha256":"9ab7f0a872fbd552"}},{"arxiv_id":"2405.15232","arxiv_id_is_arxiv":true,"paper":"/paper/deem-diffusion-models-serve-as-the-eyes-of","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rainbowluocs/deem","path":"uni_interleaved/utils/clip_sim_score.py","file_url":"https://github.com/rainbowluocs/deem/blob/HEAD/uni_interleaved/utils/clip_sim_score.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1af97eee0d5e9a78","code_sha256_prefix":"1af97eee0d5e9a78","mcp_get_code":{"code_sha256":"1af97eee0d5e9a78"}},{"arxiv_id":"2405.12211","arxiv_id_is_arxiv":true,"paper":"/paper/slicedit-zero-shot-video-editing-with-text-to","title":"Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fallenshock/Slicedit","path":"Slicedit/inversion_utils.py","file_url":"https://github.com/fallenshock/Slicedit/blob/HEAD/Slicedit/inversion_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6fd0be0931229e05","code_sha256_prefix":"6fd0be0931229e05","mcp_get_code":{"code_sha256":"6fd0be0931229e05"}},{"arxiv_id":"2404.06139","arxiv_id_is_arxiv":true,"paper":"/paper/diffharmony-latent-diffusion-model-meets","title":"DiffHarmony: Latent Diffusion Model Meets Image Harmonization","date":"2024-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicecv/diffharmony","path":"src/utils.py","file_url":"https://github.com/nicecv/diffharmony/blob/HEAD/src/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, nicecv/diffharmony when it was checked","code_sha256":"4aa2c69430a0613f","code_sha256_prefix":"4aa2c69430a0613f","mcp_get_code":{"code_sha256":"4aa2c69430a0613f"}},{"arxiv_id":"2403.14370","arxiv_id_is_arxiv":true,"paper":"/paper/synctweedies-a-general-generative-framework","title":"SyncTweedies: A General Generative Framework Based on Synchronized Diffusions","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KAIST-Visual-AI-Group/SyncTweedies","path":"synctweedies/model/ambiguous_image_model.py","file_url":"https://github.com/KAIST-Visual-AI-Group/SyncTweedies/blob/HEAD/synctweedies/model/ambiguous_image_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"83e452f2cc3b34a0","code_sha256_prefix":"83e452f2cc3b34a0","mcp_get_code":{"code_sha256":"83e452f2cc3b34a0"}},{"arxiv_id":"2310.18640","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2310.18640","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":null,"repo":"naver-ai/dual-teacher","path":"seg_core/augmentations.py","file_url":"https://github.com/naver-ai/dual-teacher/blob/HEAD/seg_core/augmentations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, naver-ai/dual-teacher (NOASSERTION)","code_sha256":"235d463040d7d43d","code_sha256_prefix":"235d463040d7d43d","mcp_get_code":{"code_sha256":"235d463040d7d43d"}},{"arxiv_id":"2306.08276","arxiv_id_is_arxiv":true,"paper":"/paper/tryondiffusion-a-tale-of-two-unets-1","title":"TryOnDiffusion: A Tale of Two UNets","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fashn-AI/tryondiffusion","path":"tryondiffusion/common/torch_transforms.py","file_url":"https://github.com/fashn-AI/tryondiffusion/blob/HEAD/tryondiffusion/common/torch_transforms.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"90b652d305c72806","code_sha256_prefix":"90b652d305c72806","mcp_get_code":{"code_sha256":"90b652d305c72806"}},{"arxiv_id":"2306.04848","arxiv_id_is_arxiv":true,"paper":"/paper/interpreting-and-improving-diffusion-models","title":"Interpreting and Improving Diffusion Models from an Optimization Perspective","date":"2023-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ToyotaResearchInstitute/gradient-estimation-sampler","path":"experiments/stable_diffusion_exp.py","file_url":"https://github.com/ToyotaResearchInstitute/gradient-estimation-sampler/blob/HEAD/experiments/stable_diffusion_exp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d4f6bea07d7f48a0","code_sha256_prefix":"d4f6bea07d7f48a0","mcp_get_code":{"code_sha256":"d4f6bea07d7f48a0"}},{"arxiv_id":"2210.12965","arxiv_id_is_arxiv":true,"paper":"/paper/high-resolution-image-editing-via-multi-stage","title":"High-Resolution Image Editing via Multi-Stage Blended Diffusion","date":"2022-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pfnet-research/multi-stage-blended-diffusion","path":"multi-scale-blended-diffusion/msbd/msbd_utils.py","file_url":"https://github.com/pfnet-research/multi-stage-blended-diffusion/blob/HEAD/multi-scale-blended-diffusion/msbd/msbd_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0826c2d86d3de3bf","code_sha256_prefix":"0826c2d86d3de3bf","mcp_get_code":{"code_sha256":"0826c2d86d3de3bf"}}],"record_sha256":"06fdaab80e37d474e61dfb60293039e2e0514d4d7cc8020c3be8c713e76d4e5f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}