{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"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":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2206.00941","title":"Improving Diffusion Models for Inverse Problems using Manifold Constraints","created":"2022-06-02","cited_by_count":508},{"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":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2303.11305","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","created":"2023-03-20","cited_by_count":338},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"2305.18292","title":"Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models","created":"2023-05-29","cited_by_count":261},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2312.02133","title":"Style Aligned Image Generation via Shared Attention","created":"2023-12-04","cited_by_count":216},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175},{"id":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155},{"id":"2304.06027","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","created":"2023-04-12","cited_by_count":141},{"id":"2312.00777","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","created":"2023-12-01","cited_by_count":126},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","cited_by_count":124},{"id":"2212.08698","title":"Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models","created":"2022-12-16","cited_by_count":116},{"id":"2402.02583","title":"DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing","created":"2024-02-04","cited_by_count":88},{"id":"2305.13921","title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models","created":"2023-05-23","cited_by_count":83},{"id":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82},{"id":"2306.06638","title":"Face0: Instantaneously Conditioning a Text-to-Image Model on a Face","created":"2023-06-11","cited_by_count":78},{"id":"2312.06354","title":"PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization","created":"2023-12-11","cited_by_count":77},{"id":"2404.03575","title":"DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling","created":"2024-04-04","cited_by_count":72},{"id":"2403.06951","title":"DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations","created":"2024-03-11","cited_by_count":68},{"id":"2302.08908","title":"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation","created":"2023-02-16","cited_by_count":65},{"id":"2310.10769","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","created":"2023-10-16","cited_by_count":59},{"id":"2305.02567","title":"LayoutDM: Transformer-based Diffusion Model for Layout Generation","created":"2023-05-04","cited_by_count":57},{"id":"2211.10682","title":"DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization","created":"2022-11-19","cited_by_count":45},{"id":"1705.10762","title":"Generative Models of Visually Grounded Imagination","created":"2017-05-30","cited_by_count":44},{"id":"2312.14820","title":"How Smooth Is Attention?","created":"2023-12-22","cited_by_count":44},{"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":"2405.08246","title":"Compositional Text-to-Image Generation with Dense Blob Representations","created":"2024-05-14","cited_by_count":38},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30},{"id":"2406.08431","title":"Diffusion Soup: Model Merging for Text-to-Image Diffusion Models","created":"2024-06-12","cited_by_count":26},{"id":"2312.05849","title":"InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models","created":"2023-12-10","cited_by_count":13},{"id":"2306.00914","title":"Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation","created":"2023-06-01","cited_by_count":9},{"id":"2312.06116","title":"Stellar: Systematic Evaluation of Human-Centric Personalized Text-to-Image Methods","created":"2023-12-11","cited_by_count":6}],"next_cursor":null}