{"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/papers/3","list_of":"/task/text-to-image-generation-1","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":3,"pages_in_order":10,"rows_per_page":100,"rows":[201,300],"of":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":171,"every_run_a_failure_of_syntologys_instrument":27,"listed_with_a_run_with_no_instrument_failure":171,"listed_every_run_a_failure_of_syntologys_instrument":27,"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-1","prev":"/task/text-to-image-generation-1/papers/2","next":"/task/text-to-image-generation-1/papers/4","papers":[{"url":"/paper/adversarial-attacks-on-parts-of-speech-an","slug":"adversarial-attacks-on-parts-of-speech-an","title":"Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation","date":"2024-09-21","arxiv_id":"2409.15381","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-image-hallucination-in-text-to","slug":"evaluating-image-hallucination-in-text-to","title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","date":"2024-09-19","arxiv_id":"2409.12784","repositories_listed":1,"syntology":null},{"url":"/paper/storymaker-towards-holistic-consistent","slug":"storymaker-towards-holistic-consistent","title":"StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation","date":"2024-09-19","arxiv_id":"2409.12576","repositories_listed":1,"syntology":null},{"url":"/paper/omnigen-unified-image-generation","slug":"omnigen-unified-image-generation","title":"OmniGen: Unified Image Generation","date":"2024-09-17","arxiv_id":"2409.11340","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/omnigen-unified-image-generation#ran","syntology_url":"https://syntology.ai/paper/2409.11340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11340"}},"official":{"repos":["vectorspacelab/omnigen"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/finetuning-clip-to-reason-about-pairwise","slug":"finetuning-clip-to-reason-about-pairwise","title":"Finetuning CLIP to Reason about Pairwise Differences","date":"2024-09-15","arxiv_id":"2409.09721","repositories_listed":1,"syntology":null},{"url":"/paper/scribble-guided-diffusion-for-training-free","slug":"scribble-guided-diffusion-for-training-free","title":"Scribble-Guided Diffusion for Training-free Text-to-Image Generation","date":"2024-09-12","arxiv_id":"2409.08026","repositories_listed":1,"syntology":null},{"url":"/paper/styletokenizer-defining-image-style-by-a","slug":"styletokenizer-defining-image-style-by-a","title":"StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models","date":"2024-09-04","arxiv_id":"2409.02543","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/styletokenizer-defining-image-style-by-a#ran","syntology_url":"https://syntology.ai/paper/2409.02543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02543"}},"official":{"repos":["alipay/style-tokenizer"],"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/resvg-enhancing-relation-and-semantic","slug":"resvg-enhancing-relation-and-semantic","title":"ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding","date":"2024-08-29","arxiv_id":"2408.16314","repositories_listed":1,"syntology":null},{"url":"/paper/stereo-towards-adversarially-robust-concept","slug":"stereo-towards-adversarially-robust-concept","title":"STEREO: Towards Adversarially Robust Concept Erasing from Text-to-Image Generation Models","date":"2024-08-29","arxiv_id":"2408.16807","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/stereo-towards-adversarially-robust-concept#ran","syntology_url":"https://syntology.ai/paper/2408.16807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16807"}},"official":{"repos":["koushiksrivats/robust-concept-erasing"],"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/merging-and-splitting-diffusion-paths-for","slug":"merging-and-splitting-diffusion-paths-for","title":"Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas","date":"2024-08-28","arxiv_id":"2408.15660","repositories_listed":1,"syntology":null},{"url":"/paper/show-o-one-single-transformer-to-unify","slug":"show-o-one-single-transformer-to-unify","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","date":"2024-08-22","arxiv_id":"2408.12528","repositories_listed":1,"syntology":null},{"url":"/paper/megafusion-extend-diffusion-models-towards","slug":"megafusion-extend-diffusion-models-towards","title":"MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning","date":"2024-08-20","arxiv_id":"2408.11001","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/megafusion-extend-diffusion-models-towards#ran","syntology_url":"https://syntology.ai/paper/2408.11001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11001"}},"official":{"repos":["haoningwu3639/MegaFusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/muses-3d-controllable-image-generation-via","slug":"muses-3d-controllable-image-generation-via","title":"MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration","date":"2024-08-20","arxiv_id":"2408.10605","repositories_listed":1,"syntology":null},{"url":"/paper/zepo-zero-shot-portrait-stylization-with","slug":"zepo-zero-shot-portrait-stylization-with","title":"ZePo: Zero-Shot Portrait Stylization with Faster Sampling","date":"2024-08-10","arxiv_id":"2408.05492","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00523","slug":"2408-00523","title":"Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models","date":"2024-08-01","arxiv_id":"2408.00523","repositories_listed":1,"syntology":null},{"url":"/paper/reproducibility-study-of-iti-gen-inclusive","slug":"reproducibility-study-of-iti-gen-inclusive","title":"Reproducibility Study of \"ITI-GEN: Inclusive Text-to-Image Generation\"","date":"2024-07-29","arxiv_id":"2407.19996","repositories_listed":1,"syntology":null},{"url":"/paper/record-reasoning-and-correcting-diffusion-for","slug":"record-reasoning-and-correcting-diffusion-for","title":"ReCorD: Reasoning and Correcting Diffusion for HOI Generation","date":"2024-07-25","arxiv_id":"2407.17911","repositories_listed":1,"syntology":null},{"url":"/paper/membench-memorized-image-trigger-prompt","slug":"membench-memorized-image-trigger-prompt","title":"MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models","date":"2024-07-24","arxiv_id":"2407.17095","repositories_listed":1,"syntology":null},{"url":"/paper/greenstableyolo-optimizing-inference-time-and","slug":"greenstableyolo-optimizing-inference-time-and","title":"GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation","date":"2024-07-20","arxiv_id":"2407.14982","repositories_listed":1,"syntology":null},{"url":"/paper/subject-driven-text-to-image-generation-via-1","slug":"subject-driven-text-to-image-generation-via-1","title":"Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning","date":"2024-07-16","arxiv_id":"2407.12164","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/subject-driven-text-to-image-generation-via-1#ran","syntology_url":"https://syntology.ai/paper/2407.12164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12164"}},"official":{"repos":["andrew-miao/RPO"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/conceptexpress-harnessing-diffusion-models","slug":"conceptexpress-harnessing-diffusion-models","title":"ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction","date":"2024-07-09","arxiv_id":"2407.07077","repositories_listed":1,"syntology":null},{"url":"/paper/humanrefiner-benchmarking-abnormal-human","slug":"humanrefiner-benchmarking-abnormal-human","title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance","date":"2024-07-09","arxiv_id":"2407.06937","repositories_listed":1,"syntology":null},{"url":"/paper/powerful-and-flexible-personalized-text-to","slug":"powerful-and-flexible-personalized-text-to","title":"Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning","date":"2024-07-09","arxiv_id":"2407.06642","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/powerful-and-flexible-personalized-text-to#ran","syntology_url":"https://syntology.ai/paper/2407.06642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06642"}},"official":{"repos":["wfanyue/dpg-t2i-personalization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mj-bench-is-your-multimodal-reward-model","slug":"mj-bench-is-your-multimodal-reward-model","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","date":"2024-07-05","arxiv_id":"2407.04842","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mj-bench-is-your-multimodal-reward-model#ran","syntology_url":"https://syntology.ai/paper/2407.04842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04842"}},"official":{"repos":["MJ-Bench/MJ-Bench"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-personalized-text-to-image","slug":"efficient-personalized-text-to-image","title":"Efficient Personalized Text-to-image Generation by Leveraging Textual Subspace","date":"2024-06-30","arxiv_id":"2407.00608","repositories_listed":1,"syntology":null},{"url":"/paper/instantstyle-plus-style-transfer-with-content","slug":"instantstyle-plus-style-transfer-with-content","title":"InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation","date":"2024-06-30","arxiv_id":"2407.00788","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"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) · 4 unverified","sample_list":"/paper/instantstyle-plus-style-transfer-with-content#ran","syntology_url":"https://syntology.ai/paper/2407.00788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00788"}},"official":{"repos":["instantx-research/instantstyle-plus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm4gen-leveraging-semantic-representation-of","slug":"llm4gen-leveraging-semantic-representation-of","title":"LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation","date":"2024-06-30","arxiv_id":"2407.00737","repositories_listed":1,"syntology":null},{"url":"/paper/the-factuality-tax-of-diversity-intervened","slug":"the-factuality-tax-of-diversity-intervened","title":"The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention","date":"2024-06-29","arxiv_id":"2407.00377","repositories_listed":1,"syntology":null},{"url":"/paper/popalign-population-level-alignment-for-fair","slug":"popalign-population-level-alignment-for-fair","title":"PopAlign: Population-Level Alignment for Fair Text-to-Image Generation","date":"2024-06-28","arxiv_id":"2406.19668","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-refinement-with-image-pivot-for-text","slug":"prompt-refinement-with-image-pivot-for-text","title":"Prompt Refinement with Image Pivot for Text-to-Image Generation","date":"2024-06-28","arxiv_id":"2407.00247","repositories_listed":1,"syntology":null},{"url":"/paper/anycontrol-create-your-artwork-with-versatile","slug":"anycontrol-create-your-artwork-with-versatile","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation","date":"2024-06-27","arxiv_id":"2406.18958","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/anycontrol-create-your-artwork-with-versatile#ran","syntology_url":"https://syntology.ai/paper/2406.18958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18958"}},"official":{"repos":["open-mmlab/anycontrol"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evalalign-evaluating-text-to-image-models","slug":"evalalign-evaluating-text-to-image-models","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","date":"2024-06-24","arxiv_id":"2406.16562","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evalalign-evaluating-text-to-image-models#ran","syntology_url":"https://syntology.ai/paper/2406.16562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16562"}},"official":{"repos":["sais-fuxi/evalalign"],"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","unlocated"]}}},{"url":"/paper/fine-tuning-diffusion-models-for-enhancing","slug":"fine-tuning-diffusion-models-for-enhancing","title":"FaceScore: Benchmarking and Enhancing Face Quality in Human Generation","date":"2024-06-24","arxiv_id":"2406.17100","repositories_listed":1,"syntology":null},{"url":"/paper/aitti-learning-adaptive-inclusive-token-for","slug":"aitti-learning-adaptive-inclusive-token-for","title":"AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation","date":"2024-06-18","arxiv_id":"2406.12805","repositories_listed":1,"syntology":null},{"url":"/paper/generative-visual-instruction-tuning","slug":"generative-visual-instruction-tuning","title":"Generative Visual Instruction Tuning","date":"2024-06-17","arxiv_id":"2406.11262","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"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 0 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/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}},"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/star-scale-wise-text-to-image-generation-via","slug":"star-scale-wise-text-to-image-generation-via","title":"STAR: Scale-wise Text-to-image generation via Auto-Regressive representations","date":"2024-06-16","arxiv_id":"2406.10797","repositories_listed":1,"syntology":null},{"url":"/paper/make-it-count-text-to-image-generation-with","slug":"make-it-count-text-to-image-generation-with","title":"Make It Count: Text-to-Image Generation with an Accurate Number of Objects","date":"2024-06-14","arxiv_id":"2406.10210","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/make-it-count-text-to-image-generation-with#ran","syntology_url":"https://syntology.ai/paper/2406.10210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10210"}},"official":null}},{"url":"/paper/batch-instructed-gradient-for-prompt","slug":"batch-instructed-gradient-for-prompt","title":"Batch-Instructed Gradient for Prompt Evolution:Systematic Prompt Optimization for Enhanced Text-to-Image Synthesis","date":"2024-06-13","arxiv_id":"2406.08713","repositories_listed":1,"syntology":null},{"url":"/paper/cfg-manifold-constrained-classifier-free","slug":"cfg-manifold-constrained-classifier-free","title":"CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08070","repositories_listed":1,"syntology":null},{"url":"/paper/image-textualization-an-automatic-framework","slug":"image-textualization-an-automatic-framework","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","date":"2024-06-11","arxiv_id":"2406.07502","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 2 unverified","sample_list":"/paper/image-textualization-an-automatic-framework#ran","syntology_url":"https://syntology.ai/paper/2406.07502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07502"}},"official":{"repos":["sterzhang/image-textualization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ms-diffusion-multi-subject-zero-shot-image","slug":"ms-diffusion-multi-subject-zero-shot-image","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","date":"2024-06-11","arxiv_id":"2406.07209","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/ms-diffusion-multi-subject-zero-shot-image#ran","syntology_url":"https://syntology.ai/paper/2406.07209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07209"}},"official":{"repos":["MS-Diffusion/MS-Diffusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-visual-concepts-across-models","slug":"understanding-visual-concepts-across-models","title":"Understanding Visual Concepts Across Models","date":"2024-06-11","arxiv_id":"2406.07506","repositories_listed":1,"syntology":null},{"url":"/paper/regularized-training-with-generated-datasets","slug":"regularized-training-with-generated-datasets","title":"Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models","date":"2024-06-08","arxiv_id":"2406.05432","repositories_listed":1,"syntology":null},{"url":"/paper/pqpp-a-joint-benchmark-for-text-to-image","slug":"pqpp-a-joint-benchmark-for-text-to-image","title":"PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction","date":"2024-06-07","arxiv_id":"2406.04746","repositories_listed":1,"syntology":null},{"url":"/paper/genai-arena-an-open-evaluation-platform-for","slug":"genai-arena-an-open-evaluation-platform-for","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","date":"2024-06-06","arxiv_id":"2406.04485","repositories_listed":1,"syntology":null},{"url":"/paper/step-aware-preference-optimization-aligning","slug":"step-aware-preference-optimization-aligning","title":"Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization","date":"2024-06-06","arxiv_id":"2406.04314","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/step-aware-preference-optimization-aligning#ran","syntology_url":"https://syntology.ai/paper/2406.04314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04314"}},"official":{"repos":["rockeycoss/spo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/lumina-next-making-lumina-t2x-stronger-and","slug":"lumina-next-making-lumina-t2x-stronger-and","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","date":"2024-06-05","arxiv_id":"2406.18583","repositories_listed":1,"syntology":null},{"url":"/paper/stable-pose-leveraging-transformers-for-pose","slug":"stable-pose-leveraging-transformers-for-pose","title":"Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation","date":"2024-06-04","arxiv_id":"2406.02485","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":4,"n_no_contract":6,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 4 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stable-pose-leveraging-transformers-for-pose#ran","syntology_url":"https://syntology.ai/paper/2406.02485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02485"}},"official":{"repos":["ai-med/stablepose"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reflection-reinforced-self-training-for","slug":"reflection-reinforced-self-training-for","title":"Re-ReST: Reflection-Reinforced Self-Training for Language Agents","date":"2024-06-03","arxiv_id":"2406.01495","repositories_listed":1,"syntology":null},{"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/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/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/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/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}],"record_sha256":"93ee1e5c51fe1202b6af7d5c2377c313d073e34c3bf6eb24d1e393be8f87b6c8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}