{"list":"other","total":67,"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":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"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":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313},{"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":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"2307.06949","title":"HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models","created":"2023-07-13","cited_by_count":225},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"1810.10510","title":"Neighbourhood Consensus Networks","created":"2018-10-24","cited_by_count":174},{"id":"2303.05125","title":"Cones: Concept Neurons in Diffusion Models for Customized Generation","created":"2023-03-09","cited_by_count":150},{"id":"2312.16272","title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","created":"2023-12-26","cited_by_count":143},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136},{"id":"1903.00834","title":"Image Super-Resolution by Neural Texture Transfer","created":"2019-03-03","cited_by_count":120},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2310.02992","title":"Kosmos-G: Generating Images in Context with Multimodal Large Language Models","created":"2023-10-04","cited_by_count":105},{"id":"2406.07547","title":"Zero-shot Image Editing with Reference Imitation","created":"2024-06-11","cited_by_count":65},{"id":"2403.10701","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","created":"2024-03-15","cited_by_count":64},{"id":"2309.16668","title":"RealFill: Reference-Driven Generation for Authentic Image Completion","created":"2023-09-28","cited_by_count":59},{"id":"2103.15982","title":"TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations","created":"2021-03-29","cited_by_count":48},{"id":"2305.18286","title":"Photoswap: Personalized Subject Swapping in Images","created":"2023-05-29","cited_by_count":47},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46},{"id":"2310.05590","title":"Perceptual Artifacts Localization for Image Synthesis Tasks","created":"2023-10-09","cited_by_count":43},{"id":"2405.16785","title":"PromptFix: You Prompt and We Fix the Photo","created":"2024-05-27","cited_by_count":40},{"id":"2303.00262","title":"Collage Diffusion","created":"2023-03-01","cited_by_count":33},{"id":"1808.02128","title":"Attentive Semantic Alignment with Offset-Aware Correlation Kernels","created":"2018-08-06","cited_by_count":31},{"id":"2207.05385","title":"Controllable Shadow Generation Using Pixel Height Maps","created":"2022-07-12","cited_by_count":22},{"id":"2303.10787","title":"Diffusion-based Document Layout Generation","created":"2023-03-19","cited_by_count":21},{"id":"2403.05053","title":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering","created":"2024-03-08","cited_by_count":20},{"id":"2403.16276","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","created":"2024-03-24","cited_by_count":18},{"id":"2404.14715","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","created":"2024-04-23","cited_by_count":17},{"id":"2408.10453","title":"Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation","created":"2024-08-19","cited_by_count":16},{"id":"2303.00137","title":"PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing","created":"2023-02-28","cited_by_count":15},{"id":"2307.09693","title":"GlobalMapper: Arbitrary-Shaped Urban Layout Generation","created":"2023-07-19","cited_by_count":15},{"id":"2402.18068","title":"SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model","created":"2024-02-28","cited_by_count":15},{"id":"2409.08520","title":"GroundingBooth: Grounding Text-to-Image Customization","created":"2024-09-13","cited_by_count":13},{"id":"2312.14985","title":"UniHuman: A Unified Model for Editing Human Images in the Wild","created":"2023-12-22","cited_by_count":12},{"id":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12},{"id":"2408.12009","title":"CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion","created":"2024-08-21","cited_by_count":12},{"id":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10},{"id":"2407.11294","title":"COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation","created":"2024-07-16","cited_by_count":10},{"id":"2409.03644","title":"RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images","created":"2024-09-05","cited_by_count":10},{"id":"2212.09581","title":"Reference-based Image and Video Super-Resolution via C2-Matching","created":"2022-12-19","cited_by_count":8},{"id":"2406.07008","title":"Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models","created":"2024-06-11","cited_by_count":8},{"id":"2407.15351","title":"LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation","created":"2024-07-22","cited_by_count":8}],"next_cursor":null}