{"list":"other","total":100,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"1703.00848","title":"Unsupervised Image-to-Image Translation Networks","created":"2017-03-02","cited_by_count":603},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"1704.03915","title":"Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution","created":"2017-04-12","cited_by_count":453},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2302.07121","title":"Universal Guidance for Diffusion Models","created":"2023-02-14","cited_by_count":437},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"1705.08086","title":"Universal Style Transfer via Feature Transforms","created":"2017-05-23","cited_by_count":354},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"1704.02510","title":"DualGAN: Unsupervised Dual Learning for Image-to-Image Translation","created":"2017-04-08","cited_by_count":310},{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2303.09833","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","created":"2023-03-17","cited_by_count":294},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2304.06140","title":"An Edit Friendly DDPM Noise Space: Inversion and Manipulations","created":"2023-04-12","cited_by_count":244},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2307.06949","title":"HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models","created":"2023-07-13","cited_by_count":225},{"id":"2312.02133","title":"Style Aligned Image Generation via Shared Attention","created":"2023-12-04","cited_by_count":216},{"id":"2007.00653","title":"Swapping Autoencoder for Deep Image Manipulation","created":"2020-07-01","cited_by_count":215},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199},{"id":"1812.02342","title":"Arbitrary Style Transfer with Style-Attentional Networks","created":"2018-12-06","cited_by_count":198},{"id":"2312.09008","title":"Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer","created":"2023-12-11","cited_by_count":196},{"id":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187},{"id":"2211.13752","title":"Sketch-Guided Text-to-Image Diffusion Models","created":"2022-11-24","cited_by_count":180},{"id":"2108.03647","title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","created":"2021-08-08","cited_by_count":178},{"id":"2207.06635","title":"EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations","created":"2022-07-14","cited_by_count":172},{"id":"2404.02733","title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","created":"2024-04-03","cited_by_count":170},{"id":"2004.04467","title":"Adversarial Latent Autoencoders","created":"2020-04-09","cited_by_count":155},{"id":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155},{"id":"2311.12092","title":"Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models","created":"2023-11-20","cited_by_count":153},{"id":"2209.15264","title":"Diffusion-based Image Translation using Disentangled Style and Content Representation","created":"2022-09-30","cited_by_count":149},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135},{"id":"1802.06474","title":"A Closed-form Solution to Photorealistic Image Stylization","created":"2018-02-19","cited_by_count":133},{"id":"2004.13324","title":"Learning Feature Descriptors using Camera Pose Supervision","created":"2020-04-28","cited_by_count":104},{"id":"2205.09542","title":"Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning","created":"2022-05-19","cited_by_count":93},{"id":"2402.02583","title":"DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing","created":"2024-02-04","cited_by_count":88},{"id":"2009.08003","title":"Arbitrary Video Style Transfer via Multi-Channel Correlation","created":"2020-09-17","cited_by_count":84},{"id":"2306.14544","title":"A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis","created":"2023-06-26","cited_by_count":78},{"id":"1805.04103","title":"Arbitrary Style Transfer with Deep Feature Reshuffle","created":"2018-05-10","cited_by_count":75},{"id":"2403.06951","title":"DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations","created":"2024-03-11","cited_by_count":68},{"id":"2104.00854","title":"The Spatially-Correlative Loss for Various Image Translation Tasks","created":"2021-04-02","cited_by_count":66},{"id":"2402.12974","title":"Visual Style Prompting with Swapping Self-Attention","created":"2024-02-20","cited_by_count":63},{"id":"2311.01410","title":"The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing","created":"2023-11-02","cited_by_count":62},{"id":"1712.06861","title":"End-to-end weakly-supervised semantic alignment","created":"2017-12-19","cited_by_count":60},{"id":"1904.01810","title":"SFNet: Learning Object-aware Semantic Correspondence","created":"2019-04-03","cited_by_count":60},{"id":"2303.08622","title":"Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer","created":"2023-03-15","cited_by_count":59},{"id":"1804.10469","title":"Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders","created":"2018-04-27","cited_by_count":49},{"id":"2207.04808","title":"CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer","created":"2022-07-11","cited_by_count":46},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44},{"id":"1905.01744","title":"Towards Instance-level Image-to-Image Translation","created":"2019-05-05","cited_by_count":36},{"id":"2211.17084","title":"High-Fidelity Guided Image Synthesis with Latent Diffusion Models","created":"2022-11-30","cited_by_count":36},{"id":"2108.00211","title":"Multi-scale Matching Networks for Semantic Correspondence","created":"2021-07-31","cited_by_count":32},{"id":"1808.02128","title":"Attentive Semantic Alignment with Offset-Aware Correlation Kernels","created":"2018-08-06","cited_by_count":31},{"id":"2311.11919","title":"An Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesis","created":"2023-11-20","cited_by_count":31},{"id":"2309.06933","title":"DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models","created":"2023-09-13","cited_by_count":27},{"id":"2311.16491","title":"$Z^*$: Zero-shot Style Transfer via Attention Rearrangement","created":"2023-11-25","cited_by_count":17},{"id":"2304.11335","title":"Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers","created":"2023-04-22","cited_by_count":12},{"id":"2210.05176","title":"Fine-Grained Image Style Transfer with Visual Transformers","created":"2022-10-11","cited_by_count":11},{"id":"2401.02126","title":"Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance","created":"2024-01-04","cited_by_count":7}],"next_cursor":null}