{"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":"/paper/clear-conv-like-linearization-revs-pre","title":"CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up","arxiv_id":"2412.16112","date":"2024-12-20","proceeding":null,"authors":["Songhua Liu","Zhenxiong Tan","Xinchao Wang"],"abstract":"Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when generating high-resolution images. To address this issue, we aim at a linear attention mechanism in this paper that reduces the complexity of pre-trained DiTs to linear. We begin our exploration with a comprehensive summary of existing efficient attention mechanisms and identify four key factors crucial for successful linearization of pre-trained DiTs: locality, formulation consistency, high-rank attention maps, and feature integrity. Based on these insights, we introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token, and thus achieves linear complexity. Our experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity, yielding results comparable to the teacher model. Simultaneously, it reduces attention computations by 99.5% and accelerates generation by 6.3 times for generating 8K-resolution images. Furthermore, we investigate favorable properties in the distilled attention layers, such as zero-shot generalization cross various models and plugins, and improved support for multi-GPU parallel inference. Models and codes are available here: https://github.com/Huage001/CLEAR.","url_abs":"https://arxiv.org/abs/2412.16112v1","url_pdf":"https://arxiv.org/pdf/2412.16112v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"clear-conv-like-linearization-revs-pre","repo_url":"https://github.com/huage001/clear","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"clear-conv-like-linearization-revs-pre","repo_url":"https://github.com/huage001/linfusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"8k"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.16112","atlas_url":"https://app.syntology.ai/?focus=2412.16112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.16112"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.16112"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.16112"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.16112\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2412.16112"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.16112\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.16112"},"call":"get_concepts_for_paper(arxiv_id=\"2412.16112\")"}],"by_repo":[{"repo":"huage001/clear","kind":"official","samples":13,"ran":10,"instrument":2,"unverified":3},{"repo":"huage001/linfusion","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2409.02097"],"harvested_for_calls":[{"arxiv_id":"2409.02097","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.02097"},"call":"get_harvested_code_for_paper(arxiv_id=\"2409.02097\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2412.16112.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2412.16112.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huage001/clear","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huage001/linfusion","reach":null}],"summary":{"ran":6,"ran_violates":1,"ran_fixture":1,"ran_honours":1,"ran_draft_wrong":1,"unverified":3},"n_samples":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_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_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)"},"by_repo_kind":{"official":{"samples":13,"ran":10,"n_ran_checked":8,"n_instrument":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"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_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":5,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":9,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"667cd02575574903","code_sha256_prefix":"667cd02575574903","entry":"c_crop","repo":"huage001/clear","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/huage001/clear/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:Image/0/?","fixture_out_type":"Image","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"667cd02575574903"}},{"code_sha256":"4e3ad3679e5c37b2","code_sha256_prefix":"4e3ad3679e5c37b2","entry":"calculate_shift","repo":"huage001/clear","repo_kind":"official","path":"pipeline_flux_img2img.py","file_url":"https://github.com/huage001/clear/blob/HEAD/pipeline_flux_img2img.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"image_seq_len:int/0/int, base_seq_len:int/0/int, max_seq_len:int/0/int, base_shift:float/0/float, max_shift:float/0/float","fixture_out_type":"float","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/calculate-shift","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4e3ad3679e5c37b2"}},{"code_sha256":"66a1a388e37620ac","code_sha256_prefix":"66a1a388e37620ac","entry":"crop_to_aspect_ratio","repo":"huage001/clear","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/huage001/clear/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:Image/0/?, ratio:str/0/str","fixture_out_type":"Image","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"66a1a388e37620ac"}},{"code_sha256":"67daa643d2f19a49","code_sha256_prefix":"67daa643d2f19a49","entry":"encode_prompt","repo":"huage001/clear","repo_kind":"official","path":"cache_prompt_embeds.py","file_url":"https://github.com/huage001/clear/blob/HEAD/cache_prompt_embeds.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"text_encoders:list/1/callable, tokenizers:list/1/callable, prompt:str/0/str, max_sequence_length:int/0/int, device:device/0/?, num_images_per_prompt:int/0/int, text_input_ids_list:NoneType/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T04:00:33.621019+00:00","code_page":"/code/encode-prompt","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"67daa643d2f19a49"}},{"code_sha256":"3a2a628bb69065bf","code_sha256_prefix":"3a2a628bb69065bf","entry":"image_resize","repo":"huage001/clear","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/huage001/clear/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"img:Image/0/?, max_size:int/0/int","fixture_out_type":"Image","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","code_page":"/code/image-resize","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3a2a628bb69065bf"}},{"code_sha256":"212f670149d23d38","code_sha256_prefix":"212f670149d23d38","entry":"import_model_class_from_model_name_or_path","repo":"huage001/clear","repo_kind":"official","path":"distill.py","file_url":"https://github.com/huage001/clear/blob/HEAD/distill.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pretrained_model_name_or_path:str/0/str, revision:str/0/str, subfolder:str/0/str","fixture_out_type":"type","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/import-model-class-from-model-name-or-path","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from DragonisCV/EyeControl, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"212f670149d23d38"}},{"code_sha256":"509fc25c579c767d","code_sha256_prefix":"509fc25c579c767d","entry":"parse_args","repo":"huage001/clear","repo_kind":"official","path":"cache_latent_codes.py","file_url":"https://github.com/huage001/clear/blob/HEAD/cache_latent_codes.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input_args:list/1/str","fixture_out_type":"Namespace","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":"/code/parse-args","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"509fc25c579c767d"}},{"code_sha256":"98bcd15cf273e3b4","code_sha256_prefix":"98bcd15cf273e3b4","entry":"retrieve_latents","repo":"huage001/clear","repo_kind":"official","path":"pipeline_flux_img2img.py","file_url":"https://github.com/huage001/clear/blob/HEAD/pipeline_flux_img2img.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"encoder_output:MockEncoderOutputWithDist/0/?, generator:Generator/0/?, sample_mode:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/retrieve-latents","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JS-CHU/RoamScene3D, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"98bcd15cf273e3b4"}},{"code_sha256":"0b56680ee1708fee","code_sha256_prefix":"0b56680ee1708fee","entry":"retrieve_timesteps","repo":"huage001/clear","repo_kind":"official","path":"pipeline_flux_img2img.py","file_url":"https://github.com/huage001/clear/blob/HEAD/pipeline_flux_img2img.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"scheduler:MockScheduler/0/?, num_inference_steps:int/0/int, device:NoneType/0/?, timesteps:NoneType/0/?, sigmas:NoneType/0/?","fixture_out_type":"tuple","code_page":"/code/retrieve-timesteps","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from krafton-ai/Rare-to-Frequent, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"0b56680ee1708fee"}},{"code_sha256":"eb4f8a321d97a458","code_sha256_prefix":"eb4f8a321d97a458","entry":"tokenize_prompt","repo":"huage001/clear","repo_kind":"official","path":"cache_prompt_embeds.py","file_url":"https://github.com/huage001/clear/blob/HEAD/cache_prompt_embeds.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Mock","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/tokenize-prompt","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from DragonisCV/EyeControl, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"eb4f8a321d97a458"}},{"code_sha256":"28a7c6dea6157b37","code_sha256_prefix":"28a7c6dea6157b37","entry":"load_text_encoders","repo":"huage001/clear","repo_kind":"official","path":"distill.py","file_url":"https://github.com/huage001/clear/blob/HEAD/distill.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-text-encoders","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from DragonisCV/EyeControl, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"28a7c6dea6157b37"}},{"code_sha256":"8affca81b78ce6f7","code_sha256_prefix":"8affca81b78ce6f7","entry":"log_validation","repo":"huage001/clear","repo_kind":"official","path":"distill.py","file_url":"https://github.com/huage001/clear/blob/HEAD/distill.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/log-validation","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8affca81b78ce6f7"}},{"code_sha256":"9e59d8e6626d076b","code_sha256_prefix":"9e59d8e6626d076b","entry":"parse_args","repo":"huage001/clear","repo_kind":"official","path":"cache_prompt_embeds.py","file_url":"https://github.com/huage001/clear/blob/HEAD/cache_prompt_embeds.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/parse-args","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9e59d8e6626d076b"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"fb7a6c5c5849c2af00e2a45c58587dff7c71acd716601cbba94692c3d97423ec","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}