{"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-1","name":"Text to Image Generation","slug":"text-to-image-generation-1","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":969,"papers_with_code":461,"benchmarks":0,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":null,"slug":"text-to-image-generation-on-diffusiondb","dataset":"DiffusionDB","dataset_url":"/dataset/diffusiondb","rows_in_archive":0,"metrics":["Fréchet Inception Distance","Inception Score","Similarity Score (CLIP)"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/diffusiondb","name":"DiffusionDB","full_name":"","num_papers_in_archive":70}],"subtasks":[{"url":"/task/text-to-3d","name":"Text to 3D"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":10,"rows_per_page":100,"shown":100,"of":969,"of_with_code":461,"tagged_in_all":969,"counts":{"archive_papers_tagged":969,"with_a_code_link":461,"where_syntology_ran_a_sample":198,"not_listed_spam_title":0,"listed":969,"listed_where_code_ran":198,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":164,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":164,"listed_every_run_a_failure_of_syntologys_instrument":34,"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"},"items":[{"url":"/paper/attngan-fine-grained-text-to-image-generation","slug":"attngan-fine-grained-text-to-image-generation","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","date":"2017-11-28","arxiv_id":"1711.10485","repositories_listed":20,"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":0,"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/attngan-fine-grained-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/1711.10485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10485"}},"official":null}},{"url":"/paper/adding-conditional-control-to-text-to-image","slug":"adding-conditional-control-to-text-to-image","title":"Adding Conditional Control to Text-to-Image Diffusion Models","date":"2023-02-10","arxiv_id":"2302.05543","repositories_listed":12,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adding-conditional-control-to-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2302.05543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05543"}},"official":{"repos":["lllyasviel/controlnet"],"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/zero-shot-text-to-image-generation","slug":"zero-shot-text-to-image-generation","title":"Zero-Shot Text-to-Image Generation","date":"2021-02-24","arxiv_id":"2102.12092","repositories_listed":12,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/2102.12092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12092"}},"official":{"repos":["openai/DALL-E"],"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/an-image-is-worth-one-word-personalizing-text","slug":"an-image-is-worth-one-word-personalizing-text","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","date":"2022-08-02","arxiv_id":"2208.01618","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_constructed":3,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-image-is-worth-one-word-personalizing-text#ran","syntology_url":"https://syntology.ai/paper/2208.01618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01618"}},"official":{"repos":["rinongal/textual_inversion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/composer-creative-and-controllable-image","slug":"composer-creative-and-controllable-image","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","date":"2023-02-20","arxiv_id":"2302.09778","repositories_listed":6,"syntology":null},{"url":"/paper/instructpix2pix-learning-to-follow-image","slug":"instructpix2pix-learning-to-follow-image","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","date":"2022-11-17","arxiv_id":"2211.09800","repositories_listed":6,"syntology":{"n":20,"n_ran":17,"n_constructed":2,"n_ran_checked":12,"n_instrument":5,"n_unverified":3,"n_honours":2,"n_violates":5,"n_no_contract":5,"n_pointer_only":4,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 5 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/instructpix2pix-learning-to-follow-image#ran","syntology_url":"https://syntology.ai/paper/2211.09800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09800"}},"official":{"repos":["timothybrooks/instruct-pix2pix"],"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/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/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/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/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/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/cogview-mastering-text-to-image-generation","slug":"cogview-mastering-text-to-image-generation","title":"CogView: Mastering Text-to-Image Generation via Transformers","date":"2021-05-26","arxiv_id":"2105.13290","repositories_listed":4,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/cogview-mastering-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/2105.13290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13290"}},"official":{"repos":["THUDM/CogView"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/navigating-the-synthetic-realm-harnessing","slug":"navigating-the-synthetic-realm-harnessing","title":"Navigating the Synthetic Realm: Harnessing Diffusion-based Models for Laparoscopic Text-to-Image Generation","date":"2023-12-05","arxiv_id":"2312.03043","repositories_listed":3,"syntology":null},{"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/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/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/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/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/dpm-solver-fast-solver-for-guided-sampling-of","slug":"dpm-solver-fast-solver-for-guided-sampling-of","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","date":"2022-11-02","arxiv_id":"2211.01095","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dpm-solver-fast-solver-for-guided-sampling-of#ran","syntology_url":"https://syntology.ai/paper/2211.01095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01095"}},"official":{"repos":["luchengthu/dpm-solver"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/all-are-worth-words-a-vit-backbone-for-score","slug":"all-are-worth-words-a-vit-backbone-for-score","title":"All are Worth Words: A ViT Backbone for Diffusion Models","date":"2022-09-25","arxiv_id":"2209.12152","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/all-are-worth-words-a-vit-backbone-for-score#ran","syntology_url":"https://syntology.ai/paper/2209.12152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12152"}},"official":{"repos":["baofff/U-ViT"],"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/lafite-towards-language-free-training-for","slug":"lafite-towards-language-free-training-for","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","date":"2021-11-27","arxiv_id":"2111.13792","repositories_listed":3,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"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) · 6 unverified","sample_list":"/paper/lafite-towards-language-free-training-for#ran","syntology_url":"https://syntology.ai/paper/2111.13792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13792"}},"official":{"repos":["drboog/Lafite"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/conditional-image-generation-and-manipulation","slug":"conditional-image-generation-and-manipulation","title":"Conditional Image Generation and Manipulation for User-Specified Content","date":"2020-05-11","arxiv_id":"2005.04909","repositories_listed":3,"syntology":null},{"url":"/paper/keep-drawing-it-iterative-language-based","slug":"keep-drawing-it-iterative-language-based","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","date":"2018-11-24","arxiv_id":"1811.09845","repositories_listed":3,"syntology":null},{"url":"/paper/uniworld-v1-high-resolution-semantic-encoders","slug":"uniworld-v1-high-resolution-semantic-encoders","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","date":"2025-06-03","arxiv_id":"2506.03147","repositories_listed":2,"syntology":null},{"url":"/paper/hidream-i1-a-high-efficient-image-generative","slug":"hidream-i1-a-high-efficient-image-generative","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","date":"2025-05-28","arxiv_id":"2505.22705","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/hidream-i1-a-high-efficient-image-generative#ran","syntology_url":"https://syntology.ai/paper/2505.22705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22705"}},"official":{"repos":["hidream-ai/hidream-e1","hidream-ai/hidream-i1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/imgedit-a-unified-image-editing-dataset-and","slug":"imgedit-a-unified-image-editing-dataset-and","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","date":"2025-05-26","arxiv_id":"2505.20275","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":2,"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/imgedit-a-unified-image-editing-dataset-and#ran","syntology_url":"https://syntology.ai/paper/2505.20275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20275"}},"official":{"repos":["pku-yuangroup/imgedit"],"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"]}}},{"url":"/paper/t2i-r1-reinforcing-image-generation-with","slug":"t2i-r1-reinforcing-image-generation-with","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","date":"2025-05-01","arxiv_id":"2505.00703","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/t2i-r1-reinforcing-image-generation-with#ran","syntology_url":"https://syntology.ai/paper/2505.00703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00703"}},"official":{"repos":["caraj7/t2i-r1"],"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/omni-dish-photorealistic-and-faithful-image","slug":"omni-dish-photorealistic-and-faithful-image","title":"Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes","date":"2025-04-14","arxiv_id":"2504.09948","repositories_listed":2,"syntology":null},{"url":"/paper/halton-scheduler-for-masked-generative-image","slug":"halton-scheduler-for-masked-generative-image","title":"Halton Scheduler For Masked Generative Image Transformer","date":"2025-03-21","arxiv_id":"2503.17076","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/halton-scheduler-for-masked-generative-image#ran","syntology_url":"https://syntology.ai/paper/2503.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17076"}},"official":{"repos":["valeoai/halton-maskgit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wise-a-world-knowledge-informed-semantic","slug":"wise-a-world-knowledge-informed-semantic","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","date":"2025-03-10","arxiv_id":"2503.07265","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wise-a-world-knowledge-informed-semantic#ran","syntology_url":"https://syntology.ai/paper/2503.07265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07265"}},"official":{"repos":["pku-yuangroup/wise"],"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/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","repositories_listed":2,"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/open-sora-democratizing-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2412.20404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20404"}},"official":{"repos":["hpcaitech/open-sora"],"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/itercomp-iterative-composition-aware-feedback","slug":"itercomp-iterative-composition-aware-feedback","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","date":"2024-10-09","arxiv_id":"2410.07171","repositories_listed":2,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":7,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/itercomp-iterative-composition-aware-feedback#ran","syntology_url":"https://syntology.ai/paper/2410.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07171"}},"official":{"repos":["yangling0818/itercomp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/accelerating-auto-regressive-text-to-image","slug":"accelerating-auto-regressive-text-to-image","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","date":"2024-10-02","arxiv_id":"2410.01699","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/accelerating-auto-regressive-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2410.01699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01699"}},"official":{"repos":["tyshiwo1/Accelerating-T2I-AR-with-SJD"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-agnostic-adversarial-perturbation-for","slug":"prompt-agnostic-adversarial-perturbation-for","title":"Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models","date":"2024-08-20","arxiv_id":"2408.10571","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/prompt-agnostic-adversarial-perturbation-for#ran","syntology_url":"https://syntology.ai/paper/2408.10571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10571"}},"official":{"repos":["vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io","vancyland/vancyland.github.io-project-PAP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02657","slug":"2408-02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","date":"2024-08-05","arxiv_id":"2408.02657","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"7 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2408-02657#ran","syntology_url":"https://syntology.ai/paper/2408.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02657"}},"official":{"repos":["alpha-vllm/lumina-mgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/long-and-short-guidance-in-score-identity","slug":"long-and-short-guidance-in-score-identity","title":"Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation","date":"2024-06-03","arxiv_id":"2406.01561","repositories_listed":2,"syntology":{"n":24,"n_ran":19,"n_constructed":0,"n_ran_checked":9,"n_instrument":10,"n_unverified":5,"n_honours":4,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/long-and-short-guidance-in-score-identity#ran","syntology_url":"https://syntology.ai/paper/2406.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01561"}},"official":{"repos":["mingyuanzhou/sid-lsg"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["community","official"]}}},{"url":"/paper/conceptprune-concept-editing-in-diffusion","slug":"conceptprune-concept-editing-in-diffusion","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","date":"2024-05-29","arxiv_id":"2405.19237","repositories_listed":2,"syntology":null},{"url":"/paper/imageinwords-unlocking-hyper-detailed-image","slug":"imageinwords-unlocking-hyper-detailed-image","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","date":"2024-05-05","arxiv_id":"2405.02793","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/imageinwords-unlocking-hyper-detailed-image#ran","syntology_url":"https://syntology.ai/paper/2405.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02793"}},"official":{"repos":["google/imageinwords"],"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/comat-aligning-text-to-image-diffusion-model","slug":"comat-aligning-text-to-image-diffusion-model","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","date":"2024-04-04","arxiv_id":"2404.03653","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 4 unverified","sample_list":"/paper/comat-aligning-text-to-image-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2404.03653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03653"}},"official":{"repos":["caraj7/comat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-different-language-models-and","slug":"bridging-different-language-models-and","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","date":"2024-03-12","arxiv_id":"2403.07860","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/bridging-different-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2403.07860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07860"}},"official":{"repos":["shihaozhaozsh/lavi-bridge"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ella-equip-diffusion-models-with-llm-for","slug":"ella-equip-diffusion-models-with-llm-for","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","date":"2024-03-08","arxiv_id":"2403.05135","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ella-equip-diffusion-models-with-llm-for#ran","syntology_url":"https://syntology.ai/paper/2403.05135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05135"}},"official":null}},{"url":"/paper/pixart-s-weak-to-strong-training-of-diffusion","slug":"pixart-s-weak-to-strong-training-of-diffusion","title":"PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","date":"2024-03-07","arxiv_id":"2403.04692","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pixart-s-weak-to-strong-training-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2403.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04692"}},"official":{"repos":["PixArt-alpha/PixArt-sigma"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/scaling-rectified-flow-transformers-for-high","slug":"scaling-rectified-flow-transformers-for-high","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","date":"2024-03-05","arxiv_id":"2403.03206","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":6,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-rectified-flow-transformers-for-high#ran","syntology_url":"https://syntology.ai/paper/2403.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03206"}},"official":null}},{"url":"/paper/realcompo-dynamic-equilibrium-between-realism","slug":"realcompo-dynamic-equilibrium-between-realism","title":"RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models","date":"2024-02-20","arxiv_id":"2402.12908","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"8 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/realcompo-dynamic-equilibrium-between-realism#ran","syntology_url":"https://syntology.ai/paper/2402.12908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12908"}},"official":{"repos":["yangling0818/realcompo"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"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":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 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":2,"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/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/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/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":1,"n_no_contract":5,"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, 1 violated, 5 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/a-systematic-survey-of-prompt-engineering-on","slug":"a-systematic-survey-of-prompt-engineering-on","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","date":"2023-07-24","arxiv_id":"2307.12980","repositories_listed":2,"syntology":null},{"url":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}},"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"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/linguistic-binding-in-diffusion-models-1","slug":"linguistic-binding-in-diffusion-models-1","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","date":"2023-06-15","arxiv_id":"2306.08877","repositories_listed":2,"syntology":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/fisedit-accelerating-text-to-image-editing","slug":"fisedit-accelerating-text-to-image-editing","title":"Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference","date":"2023-05-27","arxiv_id":"2305.17423","repositories_listed":2,"syntology":null},{"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":0,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 5 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":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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":3,"n_instrument":1,"n_unverified":6,"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) · 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":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/new-benchmarks-for-accountable-text-based","slug":"new-benchmarks-for-accountable-text-based","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","date":"2023-03-10","arxiv_id":"2303.05983","repositories_listed":2,"syntology":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/semantic-conditional-diffusion-networks-for","slug":"semantic-conditional-diffusion-networks-for","title":"Semantic-Conditional Diffusion Networks for Image Captioning","date":"2022-12-06","arxiv_id":"2212.03099","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-vilg-2-0-improving-text-to-image","slug":"ernie-vilg-2-0-improving-text-to-image","title":"ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts","date":"2022-10-27","arxiv_id":"2210.15257","repositories_listed":2,"syntology":null},{"url":"/paper/character-centric-story-visualization-via","slug":"character-centric-story-visualization-via","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","date":"2022-10-16","arxiv_id":"2210.08465","repositories_listed":2,"syntology":{"n":21,"n_ran":12,"n_constructed":7,"n_ran_checked":9,"n_instrument":3,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/character-centric-story-visualization-via#ran","syntology_url":"https://syntology.ai/paper/2210.08465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08465"}},"official":{"repos":["pluslabnlp/vp-csv","sairin1202/vp-csv"],"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":["found_in_text"]}}},{"url":"/paper/what-the-daam-interpreting-stable-diffusion","slug":"what-the-daam-interpreting-stable-diffusion","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","date":"2022-10-10","arxiv_id":"2210.04885","repositories_listed":2,"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/what-the-daam-interpreting-stable-diffusion#ran","syntology_url":"https://syntology.ai/paper/2210.04885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04885"}},"official":{"repos":["castorini/daam"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-autoregressive-models-for-content","slug":"scaling-autoregressive-models-for-content","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","date":"2022-06-22","arxiv_id":"2206.10789","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-autoregressive-models-for-content#ran","syntology_url":"https://syntology.ai/paper/2206.10789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10789"}},"official":null}},{"url":"/paper/clip-gen-language-free-training-of-a-text-to","slug":"clip-gen-language-free-training-of-a-text-to","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","date":"2022-03-01","arxiv_id":"2203.00386","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/clip-gen-language-free-training-of-a-text-to#ran","syntology_url":"https://syntology.ai/paper/2203.00386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.00386"}},"official":null}},{"url":"/paper/dall-eval-probing-the-reasoning-skills-and","slug":"dall-eval-probing-the-reasoning-skills-and","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","date":"2022-02-08","arxiv_id":"2202.04053","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"10 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; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dall-eval-probing-the-reasoning-skills-and#ran","syntology_url":"https://syntology.ai/paper/2202.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04053"}},"official":{"repos":["j-min/dalleval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ernie-vilg-unified-generative-pre-training","slug":"ernie-vilg-unified-generative-pre-training","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","date":"2021-12-31","arxiv_id":"2112.15283","repositories_listed":2,"syntology":null},{"url":"/paper/translation-equivariant-image-quantizer-for","slug":"translation-equivariant-image-quantizer-for","title":"Exploration into Translation-Equivariant Image Quantization","date":"2021-12-01","arxiv_id":"2112.00384","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":3,"n_instrument":10,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/translation-equivariant-image-quantizer-for#ran","syntology_url":"https://syntology.ai/paper/2112.00384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00384"}},"official":{"repos":["wcshin-git/te-vqgan"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vector-quantized-diffusion-model-for-text-to","slug":"vector-quantized-diffusion-model-for-text-to","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","date":"2021-11-29","arxiv_id":"2111.14822","repositories_listed":2,"syntology":null},{"url":"/paper/controllable-text-to-image-generation","slug":"controllable-text-to-image-generation","title":"Controllable Text-to-Image Generation","date":"2019-09-16","arxiv_id":"1909.07083","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"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 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) · 3 unverified","sample_list":"/paper/controllable-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/1909.07083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07083"}},"official":{"repos":["mrlibw/ControlGAN"],"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/mirrorgan-learning-text-to-image-generation","slug":"mirrorgan-learning-text-to-image-generation","title":"MirrorGAN: Learning Text-to-image Generation by Redescription","date":"2019-03-14","arxiv_id":"1903.05854","repositories_listed":2,"syntology":null},{"url":"/paper/mc-gan-multi-conditional-generative","slug":"mc-gan-multi-conditional-generative","title":"MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis","date":"2018-05-03","arxiv_id":"1805.01123","repositories_listed":2,"syntology":null},{"url":"/paper/characonsist-fine-grained-consistent","slug":"characonsist-fine-grained-consistent","title":"CharaConsist: Fine-Grained Consistent Character Generation","date":"2025-07-15","arxiv_id":"2507.11533","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/characonsist-fine-grained-consistent#ran","syntology_url":"https://syntology.ai/paper/2507.11533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11533"}},"official":{"repos":["murray-wang/characonsist"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/neobabel-a-multilingual-open-tower-for-visual","slug":"neobabel-a-multilingual-open-tower-for-visual","title":"NeoBabel: A Multilingual Open Tower for Visual Generation","date":"2025-07-08","arxiv_id":"2507.06137","repositories_listed":1,"syntology":null},{"url":"/paper/ovis-u1-technical-report","slug":"ovis-u1-technical-report","title":"Ovis-U1 Technical Report","date":"2025-06-29","arxiv_id":"2506.23044","repositories_listed":1,"syntology":null},{"url":"/paper/rethink-sparse-signals-for-pose-guided-text","slug":"rethink-sparse-signals-for-pose-guided-text","title":"Rethink Sparse Signals for Pose-guided Text-to-image Generation","date":"2025-06-26","arxiv_id":"2506.20983","repositories_listed":1,"syntology":null},{"url":"/paper/xverse-consistent-multi-subject-control-of","slug":"xverse-consistent-multi-subject-control-of","title":"XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation","date":"2025-06-26","arxiv_id":"2506.21416","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/xverse-consistent-multi-subject-control-of#ran","syntology_url":"https://syntology.ai/paper/2506.21416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21416"}},"official":{"repos":["bytedance/xverse"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sharegpt-4o-image-aligning-multimodal-models","slug":"sharegpt-4o-image-aligning-multimodal-models","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","date":"2025-06-22","arxiv_id":"2506.18095","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/sharegpt-4o-image-aligning-multimodal-models#ran","syntology_url":"https://syntology.ai/paper/2506.18095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18095"}},"official":{"repos":["freedomintelligence/sharegpt-4o-image"],"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/consistent-story-generation-with-asymmetry","slug":"consistent-story-generation-with-asymmetry","title":"Consistent Story Generation with Asymmetry Zigzag Sampling","date":"2025-06-11","arxiv_id":"2506.09612","repositories_listed":1,"syntology":null},{"url":"/paper/sage-exploring-the-boundaries-of-unsafe","slug":"sage-exploring-the-boundaries-of-unsafe","title":"SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing","date":"2025-06-11","arxiv_id":"2506.09363","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-inversion-turns-clip-into-a-decoder","slug":"implicit-inversion-turns-clip-into-a-decoder","title":"Implicit Inversion turns CLIP into a Decoder","date":"2025-05-29","arxiv_id":"2505.23161","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-rag-sub-dimensional-retrieval","slug":"cross-modal-rag-sub-dimensional-retrieval","title":"Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation","date":"2025-05-28","arxiv_id":"2505.21956","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-masked-autoregressive-models","slug":"hierarchical-masked-autoregressive-models","title":"Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots","date":"2025-05-26","arxiv_id":"2505.20288","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-llm-guided-semantic-correction-in","slug":"multimodal-llm-guided-semantic-correction-in","title":"Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion","date":"2025-05-26","arxiv_id":"2505.20053","repositories_listed":1,"syntology":null},{"url":"/paper/strict-stress-test-of-rendering-images","slug":"strict-stress-test-of-rendering-images","title":"STRICT: Stress Test of Rendering Images Containing Text","date":"2025-05-25","arxiv_id":"2505.18985","repositories_listed":1,"syntology":null},{"url":"/paper/align-beyond-prompts-evaluating-world","slug":"align-beyond-prompts-evaluating-world","title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","date":"2025-05-24","arxiv_id":"2505.18730","repositories_listed":1,"syntology":null},{"url":"/paper/test-time-scaling-of-diffusion-models-via","slug":"test-time-scaling-of-diffusion-models-via","title":"Test-Time Scaling of Diffusion Models via Noise Trajectory Search","date":"2025-05-24","arxiv_id":"2506.03164","repositories_listed":1,"syntology":null},{"url":"/paper/co-reinforcement-learning-for-unified","slug":"co-reinforcement-learning-for-unified","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","date":"2025-05-23","arxiv_id":"2505.17534","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":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/co-reinforcement-learning-for-unified#ran","syntology_url":"https://syntology.ai/paper/2505.17534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17534"}},"official":{"repos":["mm-vl/ulm-r1"],"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/reprompt-reasoning-augmented-reprompting-for","slug":"reprompt-reasoning-augmented-reprompting-for","title":"RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning","date":"2025-05-23","arxiv_id":"2505.17540","repositories_listed":1,"syntology":null},{"url":"/paper/mmada-multimodal-large-diffusion-language","slug":"mmada-multimodal-large-diffusion-language","title":"MMaDA: Multimodal Large Diffusion Language Models","date":"2025-05-21","arxiv_id":"2505.15809","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"8 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmada-multimodal-large-diffusion-language#ran","syntology_url":"https://syntology.ai/paper/2505.15809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15809"}},"official":{"repos":["gen-verse/mmada"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-diffusion-transformers-efficiently","slug":"scaling-diffusion-transformers-efficiently","title":"Scaling Diffusion Transformers Efficiently via $μ$P","date":"2025-05-21","arxiv_id":"2505.15270","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-sparsity-for-parameter-efficient","slug":"exploring-sparsity-for-parameter-efficient","title":"Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets","date":"2025-05-18","arxiv_id":"2505.12532","repositories_listed":1,"syntology":null},{"url":"/paper/loft-lora-fused-training-dataset-generation","slug":"loft-lora-fused-training-dataset-generation","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","date":"2025-05-16","arxiv_id":"2505.11703","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-deep-fusion-of-large-language","slug":"exploring-the-deep-fusion-of-large-language","title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis","date":"2025-05-15","arxiv_id":"2505.10046","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/exploring-the-deep-fusion-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2505.10046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10046"}},"official":{"repos":["tang-bd/fuse-dit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hcma-hierarchical-cross-model-alignment-for","slug":"hcma-hierarchical-cross-model-alignment-for","title":"HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation","date":"2025-05-10","arxiv_id":"2505.06512","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-benchmarking-and-recommendation-of","slug":"multimodal-benchmarking-and-recommendation-of","title":"Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models","date":"2025-05-06","arxiv_id":"2505.04650","repositories_listed":1,"syntology":null},{"url":"/paper/ming-lite-uni-advancements-in-unified","slug":"ming-lite-uni-advancements-in-unified","title":"Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction","date":"2025-05-05","arxiv_id":"2505.02471","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-understanding-and","slug":"unified-multimodal-understanding-and","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","date":"2025-05-05","arxiv_id":"2505.02567","repositories_listed":1,"syntology":null}],"syntology_records":63,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":198,"papers_where_code_ran_first_page":"/task/text-to-image-generation-1/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":10,"url":"/task/text-to-image-generation-1/papers/2","json":"/task/text-to-image-generation-1/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/text-to-image-generation-1/papers/3","json":"/task/text-to-image-generation-1/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/text-to-image-generation-1/papers/4","json":"/task/text-to-image-generation-1/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/text-to-image-generation-1/papers/5","json":"/task/text-to-image-generation-1/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/text-to-image-generation-1/papers/6","json":"/task/text-to-image-generation-1/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/text-to-image-generation-1/papers/7","json":"/task/text-to-image-generation-1/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/text-to-image-generation-1/papers/8","json":"/task/text-to-image-generation-1/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/text-to-image-generation-1/papers/9","json":"/task/text-to-image-generation-1/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/text-to-image-generation-1/papers/10","json":"/task/text-to-image-generation-1/papers/10.json","rows":69},{"order":"ran","page":1,"of":2,"url":"/task/text-to-image-generation-1/papers/ran/1","json":"/task/text-to-image-generation-1/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/text-to-image-generation-1/papers/ran/2","json":"/task/text-to-image-generation-1/papers/ran/2.json","rows":98}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"319ebfbaaceb8aa9b1e260aee3ff5f3113345ec55eff61e973130610834220ce","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}