{"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":"/task/text-to-image-generation/papers/ran/2","list_of":"/task/text-to-image-generation","task":"Text-to-Image Generation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":246,"counts":{"archive_papers_tagged":1085,"with_a_code_link":546,"where_syntology_ran_a_sample":246,"not_listed_spam_title":0,"listed":1085,"listed_where_code_ran":246,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":215,"every_run_a_failure_of_syntologys_instrument":31,"listed_with_a_run_with_no_instrument_failure":215,"listed_every_run_a_failure_of_syntologys_instrument":31,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/text-to-image-generation/papers/ran/1","prev":"/task/text-to-image-generation/papers/ran/1","next":"/task/text-to-image-generation/papers/ran/3","papers":[{"url":"/paper/learning-continuous-3d-words-for-text-to","slug":"learning-continuous-3d-words-for-text-to","title":"Learning Continuous 3D Words for Text-to-Image Generation","date":"2024-02-13","arxiv_id":"2402.08654","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/learning-continuous-3d-words-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2402.08654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08654"}},"official":{"repos":["ttchengab/continuous_3d_words_code"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/training-free-consistent-text-to-image","slug":"training-free-consistent-text-to-image","title":"Training-Free Consistent Text-to-Image Generation","date":"2024-02-05","arxiv_id":"2402.03286","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/training-free-consistent-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2402.03286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03286"}},"official":null}},{"url":"/paper/mastering-text-to-image-diffusion","slug":"mastering-text-to-image-diffusion","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","date":"2024-01-22","arxiv_id":"2401.11708","repositories_listed":1,"syntology":{"n":24,"n_ran":21,"n_constructed":0,"n_ran_checked":12,"n_instrument":9,"n_unverified":3,"n_honours":2,"n_violates":3,"n_no_contract":7,"n_pointer_only":16,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 3 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mastering-text-to-image-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.11708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11708"}},"official":{"repos":["yangling0818/rpg-diffusionmaster"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/connect-collapse-corrupt-learning-cross-modal","slug":"connect-collapse-corrupt-learning-cross-modal","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","date":"2024-01-16","arxiv_id":"2401.08567","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/connect-collapse-corrupt-learning-cross-modal#ran","syntology_url":"https://syntology.ai/paper/2401.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08567"}},"official":{"repos":["yuhui-zh15/c3"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pixart-d-fast-and-controllable-image","slug":"pixart-d-fast-and-controllable-image","title":"PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models","date":"2024-01-10","arxiv_id":"2401.05252","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pixart-d-fast-and-controllable-image#ran","syntology_url":"https://syntology.ai/paper/2401.05252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05252"}},"official":{"repos":["PixArt-alpha/PixArt-alpha"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-stability-of-diffusion-models","slug":"improving-the-stability-of-diffusion-models","title":"Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution","date":"2023-12-30","arxiv_id":"2401.00877","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improving-the-stability-of-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2401.00877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00877"}},"official":{"repos":["csslc/ccsr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cross-initialization-for-personalized-text-to","slug":"cross-initialization-for-personalized-text-to","title":"Cross Initialization for Personalized Text-to-Image Generation","date":"2023-12-26","arxiv_id":"2312.15905","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cross-initialization-for-personalized-text-to#ran","syntology_url":"https://syntology.ai/paper/2312.15905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15905"}},"official":{"repos":["lyupang/crossinitialization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/brush-your-text-synthesize-any-scene-text-on","slug":"brush-your-text-synthesize-any-scene-text-on","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","date":"2023-12-19","arxiv_id":"2312.12232","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":19,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/brush-your-text-synthesize-any-scene-text-on#ran","syntology_url":"https://syntology.ai/paper/2312.12232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12232"}},"official":{"repos":["ecnuljzhang/brush-your-text"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/scedit-efficient-and-controllable-image","slug":"scedit-efficient-and-controllable-image","title":"SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing","date":"2023-12-18","arxiv_id":"2312.11392","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scedit-efficient-and-controllable-image#ran","syntology_url":"https://syntology.ai/paper/2312.11392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11392"}},"official":{"repos":["modelscope/scepter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rich-human-feedback-for-text-to-image","slug":"rich-human-feedback-for-text-to-image","title":"Rich Human Feedback for Text-to-Image Generation","date":"2023-12-15","arxiv_id":"2312.10240","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rich-human-feedback-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2312.10240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10240"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/semantic-driven-initial-image-construction","slug":"semantic-driven-initial-image-construction","title":"The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization","date":"2023-12-13","arxiv_id":"2312.08872","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":3,"n_no_contract":2,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-driven-initial-image-construction#ran","syntology_url":"https://syntology.ai/paper/2312.08872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08872"}},"official":{"repos":["UT-Mao/Initial-Noise-Construction"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-and-conquer-attack-harnessing-the","slug":"divide-and-conquer-attack-harnessing-the","title":"Harnessing LLM to Attack LLM-Guarded Text-to-Image Models","date":"2023-12-12","arxiv_id":"2312.07130","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/divide-and-conquer-attack-harnessing-the#ran","syntology_url":"https://syntology.ai/paper/2312.07130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07130"}},"official":{"repos":["researchcode001/divide-and-conquer-attack"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/correcting-diffusion-generation-through","slug":"correcting-diffusion-generation-through","title":"Correcting Diffusion Generation through Resampling","date":"2023-12-10","arxiv_id":"2312.06038","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/correcting-diffusion-generation-through#ran","syntology_url":"https://syntology.ai/paper/2312.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06038"}},"official":{"repos":["ucsb-nlp-chang/diffusion_resampling"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/photomaker-customizing-realistic-human-photos","slug":"photomaker-customizing-realistic-human-photos","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","date":"2023-12-07","arxiv_id":"2312.04461","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/photomaker-customizing-realistic-human-photos#ran","syntology_url":"https://syntology.ai/paper/2312.04461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04461"}},"official":{"repos":["TencentARC/PhotoMaker"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-illustrated-instructions","slug":"generating-illustrated-instructions","title":"Generating Illustrated Instructions","date":"2023-12-07","arxiv_id":"2312.04552","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generating-illustrated-instructions#ran","syntology_url":"https://syntology.ai/paper/2312.04552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04552"}},"official":{"repos":["sachit-menon/generating-illustrated-instructions-reproduction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/kandinsky-3-0-technical-report","slug":"kandinsky-3-0-technical-report","title":"Kandinsky 3.0 Technical Report","date":"2023-12-06","arxiv_id":"2312.03511","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/kandinsky-3-0-technical-report#ran","syntology_url":"https://syntology.ai/paper/2312.03511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03511"}},"official":{"repos":["ai-forever/kandinsky-3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/diversified-in-domain-synthesis-with","slug":"diversified-in-domain-synthesis-with","title":"Diversified in-domain synthesis with efficient fine-tuning for few-shot classification","date":"2023-12-05","arxiv_id":"2312.03046","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diversified-in-domain-synthesis-with#ran","syntology_url":"https://syntology.ai/paper/2312.03046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03046"}},"official":{"repos":["vturrisi/disef"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/removing-nsfw-concepts-from-vision-and","slug":"removing-nsfw-concepts-from-vision-and","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","date":"2023-11-27","arxiv_id":"2311.16254","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/removing-nsfw-concepts-from-vision-and#ran","syntology_url":"https://syntology.ai/paper/2311.16254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16254"}},"official":{"repos":["aimagelab/safe-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/instastyle-inversion-noise-of-a-stylized","slug":"instastyle-inversion-noise-of-a-stylized","title":"InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser","date":"2023-11-25","arxiv_id":"2311.15040","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instastyle-inversion-noise-of-a-stylized#ran","syntology_url":"https://syntology.ai/paper/2311.15040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15040"}},"official":{"repos":["cuixing100876/instastyle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-model-alignment-using-direct","slug":"diffusion-model-alignment-using-direct","title":"Diffusion Model Alignment Using Direct Preference Optimization","date":"2023-11-21","arxiv_id":"2311.12908","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diffusion-model-alignment-using-direct#ran","syntology_url":"https://syntology.ai/paper/2311.12908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12908"}},"official":null}},{"url":"/paper/ufogen-you-forward-once-large-scale-text-to","slug":"ufogen-you-forward-once-large-scale-text-to","title":"UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs","date":"2023-11-14","arxiv_id":"2311.09257","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ufogen-you-forward-once-large-scale-text-to#ran","syntology_url":"https://syntology.ai/paper/2311.09257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09257"}},"official":{"repos":["xuyanwu/SIDDMs-UFOGen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/antifakeprompt-prompt-tuned-vision-language","slug":"antifakeprompt-prompt-tuned-vision-language","title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","date":"2023-10-26","arxiv_id":"2310.17419","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/antifakeprompt-prompt-tuned-vision-language#ran","syntology_url":"https://syntology.ai/paper/2310.17419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17419"}},"official":{"repos":["nctu-eva-lab/antifakeprompt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/quality-diversity-through-human-feedback","slug":"quality-diversity-through-human-feedback","title":"Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization","date":"2023-10-18","arxiv_id":"2310.12103","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quality-diversity-through-human-feedback#ran","syntology_url":"https://syntology.ai/paper/2310.12103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12103"}},"official":{"repos":["ld-ing/qdhf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-blueprint-enabling-text-to-image","slug":"llm-blueprint-enabling-text-to-image","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","date":"2023-10-16","arxiv_id":"2310.10640","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llm-blueprint-enabling-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2310.10640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10640"}},"official":{"repos":["hananshafi/llmblueprint"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lamp-learn-a-motion-pattern-for-few-shot","slug":"lamp-learn-a-motion-pattern-for-few-shot","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","date":"2023-10-16","arxiv_id":"2310.10769","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lamp-learn-a-motion-pattern-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2310.10769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10769"}},"official":{"repos":["RQ-Wu/LAMP"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tailored-visions-enhancing-text-to-image","slug":"tailored-visions-enhancing-text-to-image","title":"Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting","date":"2023-10-12","arxiv_id":"2310.08129","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tailored-visions-enhancing-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2310.08129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08129"}},"official":{"repos":["zzjchen/tailored-visions"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-consistency-models-synthesizing-high","slug":"latent-consistency-models-synthesizing-high","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","date":"2023-10-06","arxiv_id":"2310.04378","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/latent-consistency-models-synthesizing-high#ran","syntology_url":"https://syntology.ai/paper/2310.04378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04378"}},"official":{"repos":["luosiallen/latent-consistency-model"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kandinsky-an-improved-text-to-image-synthesis","slug":"kandinsky-an-improved-text-to-image-synthesis","title":"Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion","date":"2023-10-05","arxiv_id":"2310.03502","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_constructed":1,"n_ran_checked":7,"n_instrument":5,"n_unverified":6,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/kandinsky-an-improved-text-to-image-synthesis#ran","syntology_url":"https://syntology.ai/paper/2310.03502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03502"}},"official":{"repos":["ai-forever/Kandinsky-2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/imagenhub-standardizing-the-evaluation-of","slug":"imagenhub-standardizing-the-evaluation-of","title":"ImagenHub: Standardizing the evaluation of conditional image generation models","date":"2023-10-02","arxiv_id":"2310.01596","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imagenhub-standardizing-the-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2310.01596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01596"}},"official":{"repos":["chromaica/chromaica.github.io","TIGER-AI-Lab/ImagenHub"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/instructcv-instruction-tuned-text-to-image","slug":"instructcv-instruction-tuned-text-to-image","title":"InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists","date":"2023-09-30","arxiv_id":"2310.00390","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/instructcv-instruction-tuned-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2310.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00390"}},"official":{"repos":["AlaaLab/InstructCV"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/pixart-a-fast-training-of-diffusion","slug":"pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","arxiv_id":"2310.00426","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pixart-a-fast-training-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2310.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00426"}},"official":{"repos":["PixArt-alpha/PixArt-alpha"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/language-models-as-black-box-optimizers-for","slug":"language-models-as-black-box-optimizers-for","title":"Language Models as Black-Box Optimizers for Vision-Language Models","date":"2023-09-12","arxiv_id":"2309.05950","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/language-models-as-black-box-optimizers-for#ran","syntology_url":"https://syntology.ai/paper/2309.05950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05950"}},"official":{"repos":["shihongl1998/llm-as-a-blackbox-optimizer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/prompting4debugging-red-teaming-text-to-image","slug":"prompting4debugging-red-teaming-text-to-image","title":"Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts","date":"2023-09-12","arxiv_id":"2309.06135","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompting4debugging-red-teaming-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2309.06135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06135"}},"official":{"repos":["joycenerd/p4d"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/instaflow-one-step-is-enough-for-high-quality","slug":"instaflow-one-step-is-enough-for-high-quality","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","date":"2023-09-12","arxiv_id":"2309.06380","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instaflow-one-step-is-enough-for-high-quality#ran","syntology_url":"https://syntology.ai/paper/2309.06380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06380"}},"official":{"repos":["gnobitab/instaflow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/iti-gen-inclusive-text-to-image-generation","slug":"iti-gen-inclusive-text-to-image-generation","title":"ITI-GEN: Inclusive Text-to-Image Generation","date":"2023-09-11","arxiv_id":"2309.05569","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/iti-gen-inclusive-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/2309.05569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05569"}},"official":{"repos":["humansensinglab/ITI-GEN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/photoverse-tuning-free-image-customization","slug":"photoverse-tuning-free-image-customization","title":"PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models","date":"2023-09-11","arxiv_id":"2309.05793","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/photoverse-tuning-free-image-customization#ran","syntology_url":"https://syntology.ai/paper/2309.05793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05793"}},"official":null}},{"url":"/paper/diffusion-model-is-secretly-a-training-free","slug":"diffusion-model-is-secretly-a-training-free","title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","date":"2023-09-06","arxiv_id":"2309.02773","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-model-is-secretly-a-training-free#ran","syntology_url":"https://syntology.ai/paper/2309.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.02773"}},"official":{"repos":["VCG-team/DiffSegmenter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exchanging-based-multimodal-fusion-with","slug":"exchanging-based-multimodal-fusion-with","title":"Exchanging-based Multimodal Fusion with Transformer","date":"2023-09-05","arxiv_id":"2309.02190","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exchanging-based-multimodal-fusion-with#ran","syntology_url":"https://syntology.ai/paper/2309.02190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.02190"}},"official":{"repos":["recklessronan/muse"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pathldm-text-conditioned-latent-diffusion","slug":"pathldm-text-conditioned-latent-diffusion","title":"PathLDM: Text conditioned Latent Diffusion Model for Histopathology","date":"2023-09-01","arxiv_id":"2309.00748","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pathldm-text-conditioned-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2309.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00748"}},"official":{"repos":["cvlab-stonybrook/pathldm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dense-text-to-image-generation-with-attention","slug":"dense-text-to-image-generation-with-attention","title":"Dense Text-to-Image Generation with Attention Modulation","date":"2023-08-24","arxiv_id":"2308.12964","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dense-text-to-image-generation-with-attention#ran","syntology_url":"https://syntology.ai/paper/2308.12964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12964"}},"official":{"repos":["naver-ai/densediffusion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-multilingual-models-pivot-zero-shot","slug":"large-multilingual-models-pivot-zero-shot","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","date":"2023-08-23","arxiv_id":"2308.12038","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-multilingual-models-pivot-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2308.12038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12038"}},"official":{"repos":["openbmb/viscpm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-generate-semantic-layouts-for","slug":"learning-to-generate-semantic-layouts-for","title":"Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis","date":"2023-08-16","arxiv_id":"2308.08157","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":2,"n_honours":4,"n_violates":3,"n_no_contract":7,"n_pointer_only":17,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 4 honoured, 3 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-to-generate-semantic-layouts-for#ran","syntology_url":"https://syntology.ai/paper/2308.08157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08157"}},"official":{"repos":["pmh9960/GCDP"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/layoutllm-t2i-eliciting-layout-guidance-from","slug":"layoutllm-t2i-eliciting-layout-guidance-from","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","date":"2023-08-09","arxiv_id":"2308.05095","repositories_listed":1,"syntology":{"n":17,"n_ran":11,"n_constructed":4,"n_ran_checked":9,"n_instrument":2,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":17,"phrase":"11 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/layoutllm-t2i-eliciting-layout-guidance-from#ran","syntology_url":"https://syntology.ai/paper/2308.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05095"}},"official":null}},{"url":"/paper/conceptlab-creative-generation-using","slug":"conceptlab-creative-generation-using","title":"ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints","date":"2023-08-03","arxiv_id":"2308.02669","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conceptlab-creative-generation-using#ran","syntology_url":"https://syntology.ai/paper/2308.02669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02669"}},"official":{"repos":["kfirgoldberg/ConceptLab"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reverse-stable-diffusion-what-prompt-was-used","slug":"reverse-stable-diffusion-what-prompt-was-used","title":"Reverse Stable Diffusion: What prompt was used to generate this image?","date":"2023-08-02","arxiv_id":"2308.01472","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reverse-stable-diffusion-what-prompt-was-used#ran","syntology_url":"https://syntology.ai/paper/2308.01472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01472"}},"official":{"repos":["croitorualin/reverse-stable-diffusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-bias-amplification-paradox-in-text-to","slug":"the-bias-amplification-paradox-in-text-to","title":"The Bias Amplification Paradox in Text-to-Image Generation","date":"2023-08-01","arxiv_id":"2308.00755","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-bias-amplification-paradox-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2308.00755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00755"}},"official":{"repos":["preethiseshadri518/bias-amplification-paradox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tf-icon-diffusion-based-training-free-cross","slug":"tf-icon-diffusion-based-training-free-cross","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","date":"2023-07-24","arxiv_id":"2307.12493","repositories_listed":2,"syntology":{"n":26,"n_ran":20,"n_constructed":3,"n_ran_checked":13,"n_instrument":7,"n_unverified":6,"n_honours":0,"n_violates":3,"n_no_contract":10,"n_pointer_only":14,"phrase":"20 ran (of which 3 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 3 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/tf-icon-diffusion-based-training-free-cross#ran","syntology_url":"https://syntology.ai/paper/2307.12493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12493"}},"official":{"repos":["Shilin-LU/TF-ICON"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/subject-diffusion-open-domain-personalized","slug":"subject-diffusion-open-domain-personalized","title":"Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","date":"2023-07-21","arxiv_id":"2307.11410","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/subject-diffusion-open-domain-personalized#ran","syntology_url":"https://syntology.ai/paper/2307.11410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11410"}},"official":{"repos":["OPPO-Mente-Lab/Subject-Diffusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/boxdiff-text-to-image-synthesis-with-training","slug":"boxdiff-text-to-image-synthesis-with-training","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","date":"2023-07-20","arxiv_id":"2307.10816","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boxdiff-text-to-image-synthesis-with-training#ran","syntology_url":"https://syntology.ai/paper/2307.10816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10816"}},"official":{"repos":["showlab/boxdiff","sierkinhane/boxdiff"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-bind-your-attention-for-improved","slug":"divide-bind-your-attention-for-improved","title":"Divide & Bind Your Attention for Improved Generative Semantic Nursing","date":"2023-07-20","arxiv_id":"2307.10864","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/divide-bind-your-attention-for-improved#ran","syntology_url":"https://syntology.ai/paper/2307.10864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10864"}},"official":{"repos":["boschresearch/Divide-and-Bind"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/t2i-compbench-a-comprehensive-benchmark-for-1","slug":"t2i-compbench-a-comprehensive-benchmark-for-1","title":"T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation","date":"2023-07-12","arxiv_id":"2307.06350","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/t2i-compbench-a-comprehensive-benchmark-for-1#ran","syntology_url":"https://syntology.ai/paper/2307.06350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06350"}},"official":null}},{"url":"/paper/exact-diffusion-inversion-via-bi-directional","slug":"exact-diffusion-inversion-via-bi-directional","title":"Exact Diffusion Inversion via Bi-directional Integration Approximation","date":"2023-07-10","arxiv_id":"2307.10829","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":16,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/exact-diffusion-inversion-via-bi-directional#ran","syntology_url":"https://syntology.ai/paper/2307.10829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10829"}},"official":{"repos":["guoqiang-zhang-x/BDIA"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/practical-and-asymptotically-exact-1","slug":"practical-and-asymptotically-exact-1","title":"Practical and Asymptotically Exact Conditional Sampling in Diffusion Models","date":"2023-06-30","arxiv_id":"2306.17775","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":1,"n_ran_checked":2,"n_instrument":7,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":15,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/practical-and-asymptotically-exact-1#ran","syntology_url":"https://syntology.ai/paper/2306.17775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17775"}},"official":{"repos":["blt2114/twisted_diffusion_sampler"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/contrasting-intra-modal-and-ranking-cross","slug":"contrasting-intra-modal-and-ranking-cross","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","date":"2023-06-15","arxiv_id":"2306.08832","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrasting-intra-modal-and-ranking-cross#ran","syntology_url":"https://syntology.ai/paper/2306.08832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08832"}},"official":{"repos":["lezhang7/Enhance-FineGrained","magiccircuit/enhance-finegrained"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/norm-guided-latent-space-exploration-for-text-1","slug":"norm-guided-latent-space-exploration-for-text-1","title":"Norm-guided latent space exploration for text-to-image generation","date":"2023-06-14","arxiv_id":"2306.08687","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/norm-guided-latent-space-exploration-for-text-1#ran","syntology_url":"https://syntology.ai/paper/2306.08687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08687"}},"official":{"repos":["dvirsamuel/SeedSelect"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vico-detail-preserving-visual-condition-for","slug":"vico-detail-preserving-visual-condition-for","title":"ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation","date":"2023-06-01","arxiv_id":"2306.00971","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":3,"n_no_contract":4,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vico-detail-preserving-visual-condition-for#ran","syntology_url":"https://syntology.ai/paper/2306.00971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00971"}},"official":{"repos":["haoosz/vico"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intelligent-grimm-open-ended-visual","slug":"intelligent-grimm-open-ended-visual","title":"Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models","date":"2023-06-01","arxiv_id":"2306.00973","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/intelligent-grimm-open-ended-visual#ran","syntology_url":"https://syntology.ai/paper/2306.00973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00973"}},"official":{"repos":["haoningwu3639/StoryGen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/styledrop-text-to-image-generation-in-any","slug":"styledrop-text-to-image-generation-in-any","title":"StyleDrop: Text-to-Image Generation in Any Style","date":"2023-06-01","arxiv_id":"2306.00983","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/styledrop-text-to-image-generation-in-any#ran","syntology_url":"https://syntology.ai/paper/2306.00983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00983"}},"official":null}},{"url":"/paper/real-world-image-variation-by-aligning-1","slug":"real-world-image-variation-by-aligning-1","title":"Real-World Image Variation by Aligning Diffusion Inversion Chain","date":"2023-05-30","arxiv_id":"2305.18729","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/real-world-image-variation-by-aligning-1#ran","syntology_url":"https://syntology.ai/paper/2305.18729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18729"}},"official":{"repos":["dvlab-research/rival"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/on-architectural-compression-of-text-to-image","slug":"on-architectural-compression-of-text-to-image","title":"BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion","date":"2023-05-25","arxiv_id":"2305.15798","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-architectural-compression-of-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2305.15798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15798"}},"official":{"repos":["Nota-NetsPresso/BK-SDM","segmind/distill-sd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prospect-expanded-conditioning-for-the","slug":"prospect-expanded-conditioning-for-the","title":"ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models","date":"2023-05-25","arxiv_id":"2305.16225","repositories_listed":3,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":3,"n_no_contract":4,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prospect-expanded-conditioning-for-the#ran","syntology_url":"https://syntology.ai/paper/2305.16225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16225"}},"official":{"repos":["zyxElsa/ProSpect"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-programming-for-text-to-image","slug":"visual-programming-for-text-to-image","title":"Visual Programming for Text-to-Image Generation and Evaluation","date":"2023-05-24","arxiv_id":"2305.15328","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-programming-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2305.15328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15328"}},"official":null}},{"url":"/paper/layoutgpt-compositional-visual-planning-and","slug":"layoutgpt-compositional-visual-planning-and","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","date":"2023-05-24","arxiv_id":"2305.15393","repositories_listed":1,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/layoutgpt-compositional-visual-planning-and#ran","syntology_url":"https://syntology.ai/paper/2305.15393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15393"}},"official":{"repos":["weixi-feng/layoutgpt"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/audiotoken-adaptation-of-text-conditioned-1","slug":"audiotoken-adaptation-of-text-conditioned-1","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","date":"2023-05-22","arxiv_id":"2305.13050","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/audiotoken-adaptation-of-text-conditioned-1#ran","syntology_url":"https://syntology.ai/paper/2305.13050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13050"}},"official":{"repos":["guyyariv/AudioToken"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/training-diffusion-models-with-reinforcement","slug":"training-diffusion-models-with-reinforcement","title":"Training Diffusion Models with Reinforcement Learning","date":"2023-05-22","arxiv_id":"2305.13301","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/training-diffusion-models-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2305.13301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13301"}},"official":{"repos":["kvablack/ddpo-pytorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/discriminative-diffusion-models-as-few-shot","slug":"discriminative-diffusion-models-as-few-shot","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","date":"2023-05-18","arxiv_id":"2305.10722","repositories_listed":1,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/discriminative-diffusion-models-as-few-shot#ran","syntology_url":"https://syntology.ai/paper/2305.10722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10722"}},"official":{"repos":["eric-ai-lab/dsd"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/fastcomposer-tuning-free-multi-subject-image","slug":"fastcomposer-tuning-free-multi-subject-image","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","date":"2023-05-17","arxiv_id":"2305.10431","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fastcomposer-tuning-free-multi-subject-image#ran","syntology_url":"https://syntology.ai/paper/2305.10431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10431"}},"official":{"repos":["mit-han-lab/fastcomposer"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sur-adapter-enhancing-text-to-image-pre","slug":"sur-adapter-enhancing-text-to-image-pre","title":"SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models","date":"2023-05-09","arxiv_id":"2305.05189","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sur-adapter-enhancing-text-to-image-pre#ran","syntology_url":"https://syntology.ai/paper/2305.05189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05189"}},"official":{"repos":["Qrange-group/SUR-adapter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pick-a-pic-an-open-dataset-of-user","slug":"pick-a-pic-an-open-dataset-of-user","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","date":"2023-05-02","arxiv_id":"2305.01569","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pick-a-pic-an-open-dataset-of-user#ran","syntology_url":"https://syntology.ai/paper/2305.01569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01569"}},"official":{"repos":["yuvalkirstain/pickscore"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tr0n-translator-networks-for-0-shot-plug-and","slug":"tr0n-translator-networks-for-0-shot-plug-and","title":"TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation","date":"2023-04-26","arxiv_id":"2304.13742","repositories_listed":2,"syntology":{"n":19,"n_ran":17,"n_constructed":1,"n_ran_checked":12,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":9,"phrase":"17 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tr0n-translator-networks-for-0-shot-plug-and#ran","syntology_url":"https://syntology.ai/paper/2304.13742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13742"}},"official":{"repos":["layer6ai-labs/tr0n"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/masactrl-tuning-free-mutual-self-attention","slug":"masactrl-tuning-free-mutual-self-attention","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","date":"2023-04-17","arxiv_id":"2304.08465","repositories_listed":4,"syntology":{"n":7,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/masactrl-tuning-free-mutual-self-attention#ran","syntology_url":"https://syntology.ai/paper/2304.08465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08465"}},"official":{"repos":["tencentarc/masactrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/expressive-text-to-image-generation-with-rich","slug":"expressive-text-to-image-generation-with-rich","title":"Expressive Text-to-Image Generation with Rich Text","date":"2023-04-13","arxiv_id":"2304.06720","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/expressive-text-to-image-generation-with-rich#ran","syntology_url":"https://syntology.ai/paper/2304.06720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06720"}},"official":{"repos":["songweige/rich-text-to-image"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/imagereward-learning-and-evaluating-human-1","slug":"imagereward-learning-and-evaluating-human-1","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","date":"2023-04-12","arxiv_id":"2304.05977","repositories_listed":3,"syntology":{"n":12,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/imagereward-learning-and-evaluating-human-1#ran","syntology_url":"https://syntology.ai/paper/2304.05977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05977"}},"official":{"repos":["thudm/imagereward"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/uncurated-image-text-datasets-shedding-light","slug":"uncurated-image-text-datasets-shedding-light","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","date":"2023-04-06","arxiv_id":"2304.02828","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/uncurated-image-text-datasets-shedding-light#ran","syntology_url":"https://syntology.ai/paper/2304.02828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02828"}},"official":{"repos":["noagarcia/phase"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/follow-your-pose-pose-guided-text-to-video","slug":"follow-your-pose-pose-guided-text-to-video","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","date":"2023-04-03","arxiv_id":"2304.01186","repositories_listed":2,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/follow-your-pose-pose-guided-text-to-video#ran","syntology_url":"https://syntology.ai/paper/2304.01186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01186"}},"official":{"repos":["mayuelala/followyourpose"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/glyphdraw-learning-to-draw-chinese-characters","slug":"glyphdraw-learning-to-draw-chinese-characters","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","date":"2023-03-31","arxiv_id":"2303.17870","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyphdraw-learning-to-draw-chinese-characters#ran","syntology_url":"https://syntology.ai/paper/2303.17870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17870"}},"official":{"repos":["OPPO-Mente-Lab/GlyphDraw"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/tifa-accurate-and-interpretable-text-to-image","slug":"tifa-accurate-and-interpretable-text-to-image","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","date":"2023-03-21","arxiv_id":"2303.11897","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tifa-accurate-and-interpretable-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2303.11897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11897"}},"official":{"repos":["Yushi-Hu/tifa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/magvlt-masked-generative-vision-and-language","slug":"magvlt-masked-generative-vision-and-language","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","date":"2023-03-21","arxiv_id":"2303.12208","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":5,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/magvlt-masked-generative-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2303.12208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12208"}},"official":{"repos":["kakaobrain/magvlt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/svdiff-compact-parameter-space-for-diffusion","slug":"svdiff-compact-parameter-space-for-diffusion","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","date":"2023-03-20","arxiv_id":"2303.11305","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/svdiff-compact-parameter-space-for-diffusion#ran","syntology_url":"https://syntology.ai/paper/2303.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11305"}},"official":null}},{"url":"/paper/localizing-object-level-shape-variations-with","slug":"localizing-object-level-shape-variations-with","title":"Localizing Object-level Shape Variations with Text-to-Image Diffusion Models","date":"2023-03-20","arxiv_id":"2303.11306","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/localizing-object-level-shape-variations-with#ran","syntology_url":"https://syntology.ai/paper/2303.11306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11306"}},"official":null}},{"url":"/paper/p-extended-textual-conditioning-in-text-to","slug":"p-extended-textual-conditioning-in-text-to","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","date":"2023-03-16","arxiv_id":"2303.09522","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/p-extended-textual-conditioning-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2303.09522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09522"}},"official":null}},{"url":"/paper/one-transformer-fits-all-distributions-in","slug":"one-transformer-fits-all-distributions-in","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","date":"2023-03-12","arxiv_id":"2303.06555","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/one-transformer-fits-all-distributions-in#ran","syntology_url":"https://syntology.ai/paper/2303.06555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06555"}},"official":{"repos":["thu-ml/unidiffuser"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/scaling-up-gans-for-text-to-image-synthesis","slug":"scaling-up-gans-for-text-to-image-synthesis","title":"Scaling up GANs for Text-to-Image Synthesis","date":"2023-03-09","arxiv_id":"2303.05511","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":3,"n_no_contract":5,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 3 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-up-gans-for-text-to-image-synthesis#ran","syntology_url":"https://syntology.ai/paper/2303.05511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05511"}},"official":null}},{"url":"/paper/elite-encoding-visual-concepts-into-textual","slug":"elite-encoding-visual-concepts-into-textual","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","date":"2023-02-27","arxiv_id":"2302.13848","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/elite-encoding-visual-concepts-into-textual#ran","syntology_url":"https://syntology.ai/paper/2302.13848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13848"}},"official":{"repos":["csyxwei/elite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reduce-reuse-recycle-compositional-generation","slug":"reduce-reuse-recycle-compositional-generation","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","date":"2023-02-22","arxiv_id":"2302.11552","repositories_listed":3,"syntology":{"n":24,"n_ran":19,"n_constructed":1,"n_ran_checked":16,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"19 ran (of which 1 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/reduce-reuse-recycle-compositional-generation#ran","syntology_url":"https://syntology.ai/paper/2302.11552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11552"}},"official":{"repos":["yilundu/reduce_reuse_recycle"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multidiffusion-fusing-diffusion-paths-for","slug":"multidiffusion-fusing-diffusion-paths-for","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","date":"2023-02-16","arxiv_id":"2302.08113","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multidiffusion-fusing-diffusion-paths-for#ran","syntology_url":"https://syntology.ai/paper/2302.08113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08113"}},"official":{"repos":["omerbt/MultiDiffusion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/is-this-loss-informative-faster-text-to-image-1","slug":"is-this-loss-informative-faster-text-to-image-1","title":"Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics","date":"2023-02-09","arxiv_id":"2302.04841","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/is-this-loss-informative-faster-text-to-image-1#ran","syntology_url":"https://syntology.ai/paper/2302.04841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04841"}},"official":{"repos":["yandex-research/dvar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-zero-shot-classification-with","slug":"boosting-zero-shot-classification-with","title":"Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion","date":"2023-02-07","arxiv_id":"2302.03298","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boosting-zero-shot-classification-with#ran","syntology_url":"https://syntology.ai/paper/2302.03298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03298"}},"official":{"repos":["jordan-hs/diversity_is_definitely_needed"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fair-diffusion-instructing-text-to-image","slug":"fair-diffusion-instructing-text-to-image","title":"Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness","date":"2023-02-07","arxiv_id":"2302.10893","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fair-diffusion-instructing-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2302.10893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10893"}},"official":{"repos":["ml-research/fair-diffusion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/galip-generative-adversarial-clips-for-text","slug":"galip-generative-adversarial-clips-for-text","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","date":"2023-01-30","arxiv_id":"2301.12959","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/galip-generative-adversarial-clips-for-text#ran","syntology_url":"https://syntology.ai/paper/2301.12959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12959"}},"official":{"repos":["tobran/galip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/accelerating-guided-diffusion-sampling-with","slug":"accelerating-guided-diffusion-sampling-with","title":"Accelerating Guided Diffusion Sampling with Splitting Numerical Methods","date":"2023-01-27","arxiv_id":"2301.11558","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/accelerating-guided-diffusion-sampling-with#ran","syntology_url":"https://syntology.ai/paper/2301.11558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11558"}},"official":{"repos":["swizad/split-diffusion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/gligen-open-set-grounded-text-to-image","slug":"gligen-open-set-grounded-text-to-image","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","date":"2023-01-17","arxiv_id":"2301.07093","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/gligen-open-set-grounded-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2301.07093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.07093"}},"official":{"repos":["gligen/GLIGEN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/muse-text-to-image-generation-via-masked","slug":"muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","arxiv_id":"2301.00704","repositories_listed":5,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":8,"n_instrument":11,"n_unverified":2,"n_honours":2,"n_violates":5,"n_no_contract":1,"n_pointer_only":11,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/muse-text-to-image-generation-via-masked#ran","syntology_url":"https://syntology.ai/paper/2301.00704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00704"}},"official":null}},{"url":"/paper/benchmarking-spatial-relationships-in-text-to","slug":"benchmarking-spatial-relationships-in-text-to","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","date":"2022-12-20","arxiv_id":"2212.10015","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-spatial-relationships-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2212.10015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10015"}},"official":{"repos":["microsoft/VISOR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-prompts-for-text-to-image-1","slug":"optimizing-prompts-for-text-to-image-1","title":"Optimizing Prompts for Text-to-Image Generation","date":"2022-12-19","arxiv_id":"2212.09611","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/optimizing-prompts-for-text-to-image-1#ran","syntology_url":"https://syntology.ai/paper/2212.09611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09611"}},"official":{"repos":["microsoft/lmops"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/are-multimodal-models-robust-to-image-and","slug":"are-multimodal-models-robust-to-image-and","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift","date":"2022-12-15","arxiv_id":"2212.08044","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-multimodal-models-robust-to-image-and#ran","syntology_url":"https://syntology.ai/paper/2212.08044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08044"}},"official":null}},{"url":"/paper/smartbrush-text-and-shape-guided-object","slug":"smartbrush-text-and-shape-guided-object","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","date":"2022-12-09","arxiv_id":"2212.05034","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/smartbrush-text-and-shape-guided-object#ran","syntology_url":"https://syntology.ai/paper/2212.05034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05034"}},"official":null}},{"url":"/paper/shifted-diffusion-for-text-to-image","slug":"shifted-diffusion-for-text-to-image","title":"Shifted Diffusion for Text-to-image Generation","date":"2022-11-24","arxiv_id":"2211.15388","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":6,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/shifted-diffusion-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2211.15388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15388"}},"official":{"repos":["drboog/Shifted_Diffusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-text-conditional-discrete-denoising-on","slug":"fast-text-conditional-discrete-denoising-on","title":"A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent Spaces","date":"2022-11-14","arxiv_id":"2211.07292","repositories_listed":4,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/fast-text-conditional-discrete-denoising-on#ran","syntology_url":"https://syntology.ai/paper/2211.07292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07292"}},"official":{"repos":["dome272/paella"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/altclip-altering-the-language-encoder-in-clip#ran","syntology_url":"https://syntology.ai/paper/2211.06679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06679"}},"official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"28905fc7a710a18d7a4148e60649e14da992fa2e80d74e791ea1f23ec5290d43","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}