{"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/4","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":11,"rows_per_page":100,"rows":[301,400],"of":1085,"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","prev":"/task/text-to-image-generation/papers/3","next":"/task/text-to-image-generation/papers/5","papers":[{"url":"/paper/diffusion-features-to-bridge-domain-gap-for","slug":"diffusion-features-to-bridge-domain-gap-for","title":"Diffusion Features to Bridge Domain Gap for Semantic Segmentation","date":"2024-06-02","arxiv_id":"2406.00777","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/diffusion-features-to-bridge-domain-gap-for#ran","syntology_url":"https://syntology.ai/paper/2406.00777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00777"}},"official":{"repos":["Yux1angJi/DIFF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/amortizing-intractable-inference-in-diffusion","slug":"amortizing-intractable-inference-in-diffusion","title":"Amortizing intractable inference in diffusion models for vision, language, and control","date":"2024-05-31","arxiv_id":"2405.20971","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/amortizing-intractable-inference-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.20971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20971"}},"official":{"repos":["gfnorg/diffusion-finetuning"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-generation-via-cross-modal-in","slug":"multi-modal-generation-via-cross-modal-in","title":"Multi-modal Generation via Cross-Modal In-Context Learning","date":"2024-05-28","arxiv_id":"2405.18304","repositories_listed":1,"syntology":null},{"url":"/paper/user-friendly-customized-generation-with","slug":"user-friendly-customized-generation-with","title":"User-Friendly Customized Generation with Multi-Modal Prompts","date":"2024-05-26","arxiv_id":"2405.16501","repositories_listed":1,"syntology":null},{"url":"/paper/lateralization-mlp-a-simple-brain-inspired","slug":"lateralization-mlp-a-simple-brain-inspired","title":"Lateralization MLP: A Simple Brain-inspired Architecture for Diffusion","date":"2024-05-25","arxiv_id":"2405.16098","repositories_listed":1,"syntology":null},{"url":"/paper/defensive-unlearning-with-adversarial","slug":"defensive-unlearning-with-adversarial","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","date":"2024-05-24","arxiv_id":"2405.15234","repositories_listed":1,"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":4,"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/defensive-unlearning-with-adversarial#ran","syntology_url":"https://syntology.ai/paper/2405.15234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15234"}},"official":{"repos":["optml-group/advunlearn"],"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/learning-multi-dimensional-human-preference","slug":"learning-multi-dimensional-human-preference","title":"Learning Multi-dimensional Human Preference for Text-to-Image Generation","date":"2024-05-23","arxiv_id":"2405.14705","repositories_listed":1,"syntology":null},{"url":"/paper/curriculum-direct-preference-optimization-for","slug":"curriculum-direct-preference-optimization-for","title":"Curriculum Direct Preference Optimization for Diffusion and Consistency Models","date":"2024-05-22","arxiv_id":"2405.13637","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"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) · 5 unverified","sample_list":"/paper/curriculum-direct-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2405.13637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13637"}},"official":{"repos":["croitorualin/curriculum-dpo"],"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":["official"]}}},{"url":"/paper/an-empirical-study-and-analysis-of-text-to","slug":"an-empirical-study-and-analysis-of-text-to","title":"An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation","date":"2024-05-21","arxiv_id":"2405.12914","repositories_listed":1,"syntology":null},{"url":"/paper/masterweaver-taming-editability-and-identity","slug":"masterweaver-taming-editability-and-identity","title":"MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation","date":"2024-05-09","arxiv_id":"2405.05806","repositories_listed":1,"syntology":null},{"url":"/paper/g-refine-a-general-quality-refiner-for-text","slug":"g-refine-a-general-quality-refiner-for-text","title":"G-Refine: A General Quality Refiner for Text-to-Image Generation","date":"2024-04-29","arxiv_id":"2404.18343","repositories_listed":1,"syntology":null},{"url":"/paper/pulid-pure-and-lightning-id-customization-via","slug":"pulid-pure-and-lightning-id-customization-via","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","date":"2024-04-24","arxiv_id":"2404.16022","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pulid-pure-and-lightning-id-customization-via#ran","syntology_url":"https://syntology.ai/paper/2404.16022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16022"}},"official":{"repos":["tothebeginning/pulid"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["community","official"]}}},{"url":"/paper/textcengen-attention-guided-text-centric","slug":"textcengen-attention-guided-text-centric","title":"TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation","date":"2024-04-18","arxiv_id":"2404.11824","repositories_listed":1,"syntology":null},{"url":"/paper/ladic-are-diffusion-models-really-inferior-to","slug":"ladic-are-diffusion-models-really-inferior-to","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","date":"2024-04-16","arxiv_id":"2404.10763","repositories_listed":1,"syntology":null},{"url":"/paper/cat-contrastive-adapter-training-for","slug":"cat-contrastive-adapter-training-for","title":"CAT: Contrastive Adapter Training for Personalized Image Generation","date":"2024-04-11","arxiv_id":"2404.07554","repositories_listed":1,"syntology":null},{"url":"/paper/latent-guard-a-safety-framework-for-text-to","slug":"latent-guard-a-safety-framework-for-text-to","title":"Latent Guard: a Safety Framework for Text-to-image Generation","date":"2024-04-11","arxiv_id":"2404.08031","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/latent-guard-a-safety-framework-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2404.08031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08031"}},"official":{"repos":["rt219/latentguard"],"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/mc-2-multi-concept-guidance-for-customized","slug":"mc-2-multi-concept-guidance-for-customized","title":"MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation","date":"2024-04-08","arxiv_id":"2404.05268","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-prompt-optimizing-for-text-to-image","slug":"dynamic-prompt-optimizing-for-text-to-image","title":"Dynamic Prompt Optimizing for Text-to-Image Generation","date":"2024-04-05","arxiv_id":"2404.04095","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":2,"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/dynamic-prompt-optimizing-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2404.04095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04095"}},"official":{"repos":["mowenyii/pae"],"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/instantstyle-free-lunch-towards-style","slug":"instantstyle-free-lunch-towards-style","title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","date":"2024-04-03","arxiv_id":"2404.02733","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/instantstyle-free-lunch-towards-style#ran","syntology_url":"https://syntology.ai/paper/2404.02733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02733"}},"official":{"repos":["instantstyle/instantstyle"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/capability-aware-prompt-reformulation","slug":"capability-aware-prompt-reformulation","title":"Capability-aware Prompt Reformulation Learning for Text-to-Image Generation","date":"2024-03-27","arxiv_id":"2403.19716","repositories_listed":1,"syntology":null},{"url":"/paper/be-yourself-bounded-attention-for-multi","slug":"be-yourself-bounded-attention-for-multi","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","date":"2024-03-25","arxiv_id":"2403.16990","repositories_listed":1,"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":0,"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/be-yourself-bounded-attention-for-multi#ran","syntology_url":"https://syntology.ai/paper/2403.16990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16990"}},"official":null}},{"url":"/paper/flashface-human-image-personalization-with","slug":"flashface-human-image-personalization-with","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","date":"2024-03-25","arxiv_id":"2403.17008","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 8 unverified","sample_list":"/paper/flashface-human-image-personalization-with#ran","syntology_url":"https://syntology.ai/paper/2403.17008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17008"}},"official":null}},{"url":"/paper/rl-for-consistency-models-faster-reward","slug":"rl-for-consistency-models-faster-reward","title":"RL for Consistency Models: Faster Reward Guided Text-to-Image Generation","date":"2024-03-25","arxiv_id":"2404.03673","repositories_listed":1,"syntology":null},{"url":"/paper/sdxs-real-time-one-step-latent-diffusion","slug":"sdxs-real-time-one-step-latent-diffusion","title":"SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions","date":"2024-03-25","arxiv_id":"2403.16627","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":1,"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/sdxs-real-time-one-step-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2403.16627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16627"}},"official":{"repos":["IDKiro/sdxs"],"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/skews-in-the-phenomenon-space-hinder","slug":"skews-in-the-phenomenon-space-hinder","title":"Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation","date":"2024-03-25","arxiv_id":"2403.16394","repositories_listed":1,"syntology":null},{"url":"/paper/clip-vqdiffusion-langauge-free-training-of","slug":"clip-vqdiffusion-langauge-free-training-of","title":"CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusion model","date":"2024-03-22","arxiv_id":"2403.14944","repositories_listed":1,"syntology":null},{"url":"/paper/long-clip-unlocking-the-long-text-capability","slug":"long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","arxiv_id":"2403.15378","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":4,"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, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/long-clip-unlocking-the-long-text-capability#ran","syntology_url":"https://syntology.ai/paper/2403.15378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15378"}},"official":{"repos":["beichenzbc/long-clip"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/designedit-multi-layered-latent-decomposition","slug":"designedit-multi-layered-latent-decomposition","title":"DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing","date":"2024-03-21","arxiv_id":"2403.14487","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-attention-maps-with-token","slug":"open-vocabulary-attention-maps-with-token","title":"Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models","date":"2024-03-21","arxiv_id":"2403.14291","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/open-vocabulary-attention-maps-with-token#ran","syntology_url":"https://syntology.ai/paper/2403.14291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14291"}},"official":{"repos":["vpulab/ovam"],"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/fouriscale-a-frequency-perspective-on","slug":"fouriscale-a-frequency-perspective-on","title":"FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis","date":"2024-03-19","arxiv_id":"2403.12963","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/fouriscale-a-frequency-perspective-on#ran","syntology_url":"https://syntology.ai/paper/2403.12963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12963"}},"official":{"repos":["leonhlj/fouriscale"],"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/you-only-sample-once-taming-one-step-text-to","slug":"you-only-sample-once-taming-one-step-text-to","title":"You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs","date":"2024-03-19","arxiv_id":"2403.12931","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/you-only-sample-once-taming-one-step-text-to#ran","syntology_url":"https://syntology.ai/paper/2403.12931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12931"}},"official":{"repos":["luo-yihong/yoso"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/omg-occlusion-friendly-personalized-multi","slug":"omg-occlusion-friendly-personalized-multi","title":"OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models","date":"2024-03-16","arxiv_id":"2403.10983","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 7 unverified","sample_list":"/paper/omg-occlusion-friendly-personalized-multi#ran","syntology_url":"https://syntology.ai/paper/2403.10983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10983"}},"official":{"repos":["kongzhecn/omg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/dialoggen-multi-modal-interactive-dialogue","slug":"dialoggen-multi-modal-interactive-dialogue","title":"DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation","date":"2024-03-13","arxiv_id":"2403.08857","repositories_listed":1,"syntology":null},{"url":"/paper/stable-makeup-when-real-world-makeup-transfer","slug":"stable-makeup-when-real-world-makeup-transfer","title":"Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model","date":"2024-03-12","arxiv_id":"2403.07764","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":1,"n_no_contract":5,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/stable-makeup-when-real-world-makeup-transfer#ran","syntology_url":"https://syntology.ai/paper/2403.07764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07764"}},"official":{"repos":["Xiaojiu-z/Stable-Makeup"],"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/facechain-sude-building-derived-class-to","slug":"facechain-sude-building-derived-class-to","title":"FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation","date":"2024-03-11","arxiv_id":"2403.06775","repositories_listed":1,"syntology":null},{"url":"/paper/mace-mass-concept-erasure-in-diffusion-models","slug":"mace-mass-concept-erasure-in-diffusion-models","title":"MACE: Mass Concept Erasure in Diffusion Models","date":"2024-03-10","arxiv_id":"2403.06135","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/mace-mass-concept-erasure-in-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2403.06135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06135"}},"official":{"repos":["shilin-lu/mace"],"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/cogview3-finer-and-faster-text-to-image","slug":"cogview3-finer-and-faster-text-to-image","title":"CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion","date":"2024-03-08","arxiv_id":"2403.05121","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/cogview3-finer-and-faster-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2403.05121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05121"}},"official":null}},{"url":"/paper/face2diffusion-for-fast-and-editable-face","slug":"face2diffusion-for-fast-and-editable-face","title":"Face2Diffusion for Fast and Editable Face Personalization","date":"2024-03-08","arxiv_id":"2403.05094","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 1 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/face2diffusion-for-fast-and-editable-face#ran","syntology_url":"https://syntology.ai/paper/2403.05094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05094"}},"official":{"repos":["mapooon/face2diffusion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/noisecollage-a-layout-aware-text-to-image","slug":"noisecollage-a-layout-aware-text-to-image","title":"NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging","date":"2024-03-06","arxiv_id":"2403.03485","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"5 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/noisecollage-a-layout-aware-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2403.03485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03485"}},"official":{"repos":["univ-esuty/noisecollage"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/promptcharm-text-to-image-generation-through","slug":"promptcharm-text-to-image-generation-through","title":"PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement","date":"2024-03-06","arxiv_id":"2403.04014","repositories_listed":1,"syntology":null},{"url":"/paper/improving-explicit-spatial-relationships-in","slug":"improving-explicit-spatial-relationships-in","title":"Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived Dataset","date":"2024-03-01","arxiv_id":"2403.00587","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-contextualized-diffusion-models","slug":"cross-modal-contextualized-diffusion-models","title":"Contextualized Diffusion Models for Text-Guided Image and Video Generation","date":"2024-02-26","arxiv_id":"2402.16627","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/cross-modal-contextualized-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2402.16627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16627"}},"official":{"repos":["yangling0818/contextdiff"],"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/visual-style-prompting-with-swapping-self","slug":"visual-style-prompting-with-swapping-self","title":"Visual Style Prompting with Swapping Self-Attention","date":"2024-02-20","arxiv_id":"2402.12974","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-style-prompting-with-swapping-self#ran","syntology_url":"https://syntology.ai/paper/2402.12974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12974"}},"official":{"repos":["naver-ai/Visual-Style-Prompting"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unlearncanvas-a-stylized-image-dataset-to","slug":"unlearncanvas-a-stylized-image-dataset-to","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","date":"2024-02-19","arxiv_id":"2402.11846","repositories_listed":1,"syntology":{"n":74,"n_ran":55,"n_constructed":0,"n_ran_checked":43,"n_instrument":12,"n_unverified":19,"n_honours":2,"n_violates":1,"n_no_contract":40,"n_pointer_only":40,"phrase":"55 ran (of which 0 constructed an object rather than computing a result; 43 with no instrument failure: 2 honoured, 1 violated, 40 with no contract checked; 12 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/unlearncanvas-a-stylized-image-dataset-to#ran","syntology_url":"https://syntology.ai/paper/2402.11846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11846"}},"official":{"repos":["optml-group/unlearncanvas"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/universal-prompt-optimizer-for-safe-text-to","slug":"universal-prompt-optimizer-for-safe-text-to","title":"Universal Prompt Optimizer for Safe Text-to-Image Generation","date":"2024-02-16","arxiv_id":"2402.10882","repositories_listed":1,"syntology":null},{"url":"/paper/textual-localization-decomposing-multi","slug":"textual-localization-decomposing-multi","title":"Textual Localization: Decomposing Multi-concept Images for Subject-Driven Text-to-Image Generation","date":"2024-02-15","arxiv_id":"2402.09966","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-nibbler-an-open-red-teaming","slug":"adversarial-nibbler-an-open-red-teaming","title":"Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation","date":"2024-02-14","arxiv_id":"2403.12075","repositories_listed":1,"syntology":null},{"url":"/paper/magic-me-identity-specific-video-customized","slug":"magic-me-identity-specific-video-customized","title":"Magic-Me: Identity-Specific Video Customized Diffusion","date":"2024-02-14","arxiv_id":"2402.09368","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 5 unverified","sample_list":"/paper/magic-me-identity-specific-video-customized#ran","syntology_url":"https://syntology.ai/paper/2402.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09368"}},"official":{"repos":["zhen-dong/magic-me"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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/multilingual-text-to-image-generation","slug":"multilingual-text-to-image-generation","title":"Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You","date":"2024-01-29","arxiv_id":"2401.16092","repositories_listed":1,"syntology":null},{"url":"/paper/taiyi-diffusion-xl-advancing-bilingual-text","slug":"taiyi-diffusion-xl-advancing-bilingual-text","title":"Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support","date":"2024-01-26","arxiv_id":"2401.14688","repositories_listed":1,"syntology":null},{"url":"/paper/bootpig-bootstrapping-zero-shot-personalized","slug":"bootpig-bootstrapping-zero-shot-personalized","title":"BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models","date":"2024-01-25","arxiv_id":"2401.13974","repositories_listed":1,"syntology":null},{"url":"/paper/creativesynth-creative-blending-and-synthesis","slug":"creativesynth-creative-blending-and-synthesis","title":"CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion","date":"2024-01-25","arxiv_id":"2401.14066","repositories_listed":1,"syntology":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/beyond-the-surface-a-global-scale-analysis-of","slug":"beyond-the-surface-a-global-scale-analysis-of","title":"ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation","date":"2024-01-12","arxiv_id":"2401.06310","repositories_listed":1,"syntology":null},{"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/specref-a-fast-training-free-baseline-of","slug":"specref-a-fast-training-free-baseline-of","title":"SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing","date":"2024-01-07","arxiv_id":"2401.03433","repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-and-benchmark-for-copyright","slug":"a-dataset-and-benchmark-for-copyright","title":"A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models","date":"2024-01-04","arxiv_id":"2403.12052","repositories_listed":1,"syntology":null},{"url":"/paper/amused-an-open-muse-reproduction","slug":"amused-an-open-muse-reproduction","title":"aMUSEd: An Open MUSE Reproduction","date":"2024-01-03","arxiv_id":"2401.01808","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-grimm-open-ended-visual-1","slug":"intelligent-grimm-open-ended-visual-1","title":"Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/one-dimensional-adapter-to-rule-them-all","slug":"one-dimensional-adapter-to-rule-them-all","title":"One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications","date":"2023-12-26","arxiv_id":"2312.16145","repositories_listed":1,"syntology":null},{"url":"/paper/a-recipe-for-scaling-up-text-to-video","slug":"a-recipe-for-scaling-up-text-to-video","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","date":"2023-12-25","arxiv_id":"2312.15770","repositories_listed":1,"syntology":null},{"url":"/paper/asymmetric-bias-in-text-to-image-generation","slug":"asymmetric-bias-in-text-to-image-generation","title":"Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks","date":"2023-12-22","arxiv_id":"2312.14440","repositories_listed":1,"syntology":null},{"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/decoupled-textual-embeddings-for-customized","slug":"decoupled-textual-embeddings-for-customized","title":"Decoupled Textual Embeddings for Customized Image Generation","date":"2023-12-19","arxiv_id":"2312.11826","repositories_listed":1,"syntology":null},{"url":"/paper/vl-gpt-a-generative-pre-trained-transformer","slug":"vl-gpt-a-generative-pre-trained-transformer","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","date":"2023-12-14","arxiv_id":"2312.09251","repositories_listed":1,"syntology":null},{"url":"/paper/adapedit-spatio-temporal-guided-adaptive","slug":"adapedit-spatio-temporal-guided-adaptive","title":"AdapEdit: Spatio-Temporal Guided Adaptive Editing Algorithm for Text-Based Continuity-Sensitive Image Editing","date":"2023-12-13","arxiv_id":"2312.08019","repositories_listed":1,"syntology":null},{"url":"/paper/clockwork-diffusion-efficient-generation-with","slug":"clockwork-diffusion-efficient-generation-with","title":"Clockwork Diffusion: Efficient Generation With Model-Step Distillation","date":"2023-12-13","arxiv_id":"2312.08128","repositories_listed":1,"syntology":null},{"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/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/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/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/tokencompose-grounding-diffusion-with-token","slug":"tokencompose-grounding-diffusion-with-token","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","date":"2023-12-06","arxiv_id":"2312.03626","repositories_listed":1,"syntology":null},{"url":"/paper/customization-assistant-for-text-to-image","slug":"customization-assistant-for-text-to-image","title":"Customization Assistant for Text-to-image Generation","date":"2023-12-05","arxiv_id":"2312.03045","repositories_listed":1,"syntology":null},{"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/fergi-automatic-annotation-of-user","slug":"fergi-automatic-annotation-of-user","title":"FERGI: Automatic Scoring of User Preferences for Text-to-Image Generation from Spontaneous Facial Expression Reaction","date":"2023-12-05","arxiv_id":"2312.03187","repositories_listed":1,"syntology":null},{"url":"/paper/pea-diffusion-parameter-efficient-adapter","slug":"pea-diffusion-parameter-efficient-adapter","title":"PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation","date":"2023-11-28","arxiv_id":"2311.17086","repositories_listed":1,"syntology":null},{"url":"/paper/self-discovering-interpretable-diffusion","slug":"self-discovering-interpretable-diffusion","title":"Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation","date":"2023-11-28","arxiv_id":"2311.17216","repositories_listed":1,"syntology":null},{"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/self-correcting-llm-controlled-diffusion","slug":"self-correcting-llm-controlled-diffusion","title":"Self-correcting LLM-controlled Diffusion Models","date":"2023-11-27","arxiv_id":"2311.16090","repositories_listed":1,"syntology":null},{"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/neuroprompts-an-adaptive-framework-to","slug":"neuroprompts-an-adaptive-framework-to","title":"NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation","date":"2023-11-20","arxiv_id":"2311.12229","repositories_listed":1,"syntology":null},{"url":"/paper/the-chosen-one-consistent-characters-in-text","slug":"the-chosen-one-consistent-characters-in-text","title":"The Chosen One: Consistent Characters in Text-to-Image Diffusion Models","date":"2023-11-16","arxiv_id":"2311.10093","repositories_listed":1,"syntology":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/mukh-oboyob-stable-diffusion-and-banglabert","slug":"mukh-oboyob-stable-diffusion-and-banglabert","title":"Mukh-Oboyob: Stable Diffusion and BanglaBERT enhanced Bangla Text-to-Face Synthesis","date":"2023-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/bridging-the-gap-between-synthetic-and","slug":"bridging-the-gap-between-synthetic-and","title":"Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation","date":"2023-10-20","arxiv_id":"2310.13361","repositories_listed":1,"syntology":null},{"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/elucidating-the-design-space-of-classifier","slug":"elucidating-the-design-space-of-classifier","title":"Elucidating The Design Space of Classifier-Guided Diffusion Generation","date":"2023-10-17","arxiv_id":"2310.11311","repositories_listed":1,"syntology":null},{"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/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/making-multimodal-generation-easier-when","slug":"making-multimodal-generation-easier-when","title":"EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs","date":"2023-10-13","arxiv_id":"2310.08949","repositories_listed":1,"syntology":null},{"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/conditionvideo-training-free-condition-guided","slug":"conditionvideo-training-free-condition-guided","title":"ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation","date":"2023-10-11","arxiv_id":"2310.07697","repositories_listed":1,"syntology":null},{"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"]}}}],"record_sha256":"32b980404f5307248b8c917c0d18335e796824b1ad311c55f0c4e847bb0b01dd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}