{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"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":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"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":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"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":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2203.06026","title":"The Role of ImageNet Classes in Fr\\'echet Inception Distance","created":"2022-03-11","cited_by_count":213},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2312.00777","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","created":"2023-12-01","cited_by_count":126},{"id":"2303.14412","title":"Freestyle Layout-to-Image Synthesis","created":"2023-03-25","cited_by_count":67},{"id":"2306.13754","title":"Zero-shot spatial layout conditioning for text-to-image diffusion models","created":"2023-06-23","cited_by_count":64},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45},{"id":"2410.14324","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","created":"2024-10-18","cited_by_count":41},{"id":"2312.02109","title":"ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation","created":"2023-12-04","cited_by_count":40},{"id":"2211.17084","title":"High-Fidelity Guided Image Synthesis with Latent Diffusion Models","created":"2022-11-30","cited_by_count":36},{"id":"2305.17431","title":"Towards Consistent Video Editing with Text-to-Image Diffusion Models","created":"2023-05-27","cited_by_count":34},{"id":"2308.10156","title":"SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation","created":"2023-08-20","cited_by_count":29},{"id":"2310.08872","title":"R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation","created":"2023-10-13","cited_by_count":29},{"id":"2407.16698","title":"Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions","created":"2024-07-23","cited_by_count":29},{"id":"2309.06933","title":"DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models","created":"2023-09-13","cited_by_count":27},{"id":"2403.17001","title":"VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation","created":"2024-03-25","cited_by_count":25},{"id":"2409.08240","title":"IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation","created":"2024-09-12","cited_by_count":18},{"id":"2407.13609","title":"Training-free Composite Scene Generation for Layout-to-Image Synthesis","created":"2024-07-18","cited_by_count":11},{"id":"2410.07763","title":"HARIVO: Harnessing Text-to-Image Models for Video Generation","created":"2024-10-10","cited_by_count":8},{"id":"2411.10495","title":"Training-Free Layout-to-Image Generation with Marginal Attention Constraints","created":"2024-11-15","cited_by_count":4}],"next_cursor":null}