{"total":164,"rows":[{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585,"area":"diffusion"},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611,"area":"diffusion"},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106,"area":"diffusion"},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906,"area":null},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702,"area":"diffusion"},{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539,"area":"diffusion"},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506,"area":null},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489,"area":"diffusion"},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432,"area":"mllm"},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291,"area":"diffusion"},{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217,"area":"diffusion"},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203,"area":null},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2212.04489","title":"SINE: SINgle Image Editing with Text-to-Image Diffusion Models","created":"2022-12-08","cited_by_count":159,"area":"diffusion"},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158,"area":"diffusion"},{"id":"2306.13455","title":"DreamEditor: Text-Driven 3D Scene Editing with Neural Fields","created":"2023-06-23","cited_by_count":155,"area":null},{"id":"2211.11208","title":"Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars","created":"2022-11-21","cited_by_count":124,"area":null},{"id":"2212.08698","title":"Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models","created":"2022-12-16","cited_by_count":116,"area":"diffusion"},{"id":"2312.02432","title":"Orthogonal Adaptation for Modular Customization of Diffusion Models","created":"2023-12-05","cited_by_count":70,"area":"diffusion"},{"id":"2307.01944","title":"Text + Sketch: Image Compression at Ultra Low Rates","created":"2023-07-04","cited_by_count":67,"area":null},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62,"area":null},{"id":"2305.18203","title":"Concept Decomposition for Visual Exploration and Inspiration","created":"2023-05-29","cited_by_count":61,"area":null},{"id":"2203.00386","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","created":"2022-03-01","cited_by_count":60,"area":null},{"id":"2212.03241","title":"P{\\O}DA: Prompt-driven Zero-shot Domain Adaptation","created":"2022-12-06","cited_by_count":60,"area":null},{"id":"2211.02408","title":"Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis","created":"2022-11-04","cited_by_count":59,"area":"safety"},{"id":"2303.08622","title":"Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer","created":"2023-03-15","cited_by_count":59,"area":"diffusion"},{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59,"area":null},{"id":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54,"area":null},{"id":"2112.11641","title":"JoJoGAN: One Shot Face Stylization","created":"2021-12-22","cited_by_count":49,"area":null},{"id":"2306.07969","title":"GeneCIS: A Benchmark for General Conditional Image Similarity","created":"2023-06-13","cited_by_count":47,"area":null},{"id":"2210.09477","title":"UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image","created":"2022-10-17","cited_by_count":42,"area":"diffusion"},{"id":"2110.12427","title":"Image-Based CLIP-Guided Essence Transfer","created":"2021-10-24","cited_by_count":39,"area":null},{"id":"2211.16927","title":"3D GAN Inversion with Facial Symmetry Prior","created":"2022-11-30","cited_by_count":39,"area":null},{"id":"2212.02802","title":"Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding","created":"2022-12-06","cited_by_count":39,"area":null},{"id":"2303.08767","title":"Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion","created":"2023-03-15","cited_by_count":39,"area":"diffusion"},{"id":"2403.13044","title":"Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos","created":"2024-03-19","cited_by_count":38,"area":null},{"id":"2202.12211","title":"Self-Distilled StyleGAN: Towards Generation from Internet Photos","created":"2022-02-24","cited_by_count":37,"area":null},{"id":"2405.01536","title":"Customizing Text-to-Image Models with a Single Image Pair","created":"2024-05-02","cited_by_count":36,"area":null},{"id":"2401.06105","title":"PALP: Prompt Aligned Personalization of Text-to-Image Models","created":"2024-01-11","cited_by_count":35,"area":null},{"id":"2111.13333","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","created":"2021-11-26","cited_by_count":34,"area":"mllm"},{"id":"2405.09882","title":"DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection","created":"2024-05-16","cited_by_count":32,"area":"diffusion"},{"id":"2203.07931","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","created":"2022-03-15","cited_by_count":30,"area":null},{"id":"2209.13360","title":"Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion","created":"2022-09-27","cited_by_count":30,"area":"diffusion"},{"id":"2404.12154","title":"StyleBooth: Image Style Editing with Multimodal Instruction","created":"2024-04-18","cited_by_count":28,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2304.03119","title":"Zero-shot Generative Model Adaptation via Image-specific Prompt Learning","created":"2023-04-06","cited_by_count":27,"area":null},{"id":"2207.02363","title":"SNeRF: Stylized Neural Implicit Representations for 3D Scenes","created":"2022-07-05","cited_by_count":26,"area":null},{"id":"2302.03900","title":"Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models","created":"2023-02-08","cited_by_count":26,"area":"diffusion"},{"id":"2207.14288","title":"Rewriting Geometric Rules of a GAN","created":"2022-07-28","cited_by_count":25,"area":null},{"id":"2405.00672","title":"TexSliders: Diffusion-Based Texture Editing in CLIP Space","created":"2024-05-01","cited_by_count":23,"area":"diffusion"},{"id":"2307.03190","title":"Text-Guided Synthesis of Eulerian Cinemagraphs","created":"2023-07-06","cited_by_count":22,"area":null},{"id":"2401.15636","title":"FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models","created":"2024-01-28","cited_by_count":22,"area":"diffusion"},{"id":"2304.14630","title":"Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model","created":"2023-04-28","cited_by_count":21,"area":null},{"id":"2209.11224","title":"VToonify: Controllable High-Resolution Portrait Video Style Transfer","created":"2022-09-22","cited_by_count":20,"area":null},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2305.05947","title":"iEdit: Localised Text-guided Image Editing with Weak Supervision","created":"2023-05-10","cited_by_count":20,"area":"diffusion"},{"id":"2306.12570","title":"Local 3D Editing via 3D Distillation of CLIP Knowledge","created":"2023-06-21","cited_by_count":20,"area":null},{"id":"2306.16894","title":"PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing","created":"2023-06-28","cited_by_count":20,"area":"diffusion"},{"id":"2212.02024","title":"Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models","created":"2022-12-05","cited_by_count":18,"area":"diffusion"},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2309.04399","title":"MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask","created":"2023-09-08","cited_by_count":17,"area":"diffusion"},{"id":"2202.02713","title":"FEAT: Face Editing with Attention","created":"2022-02-06","cited_by_count":16,"area":null},{"id":"2302.07979","title":"PRedItOR: Text Guided Image Editing with Diffusion Prior","created":"2023-02-15","cited_by_count":16,"area":"diffusion"},{"id":"2303.15893","title":"VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2406.13393","title":"Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images","created":"2024-06-19","cited_by_count":16,"area":"diffusion"},{"id":"2503.19557","title":"Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion","created":"2025-03-25","cited_by_count":16,"area":null},{"id":"2211.14554","title":"DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains","created":"2022-11-26","cited_by_count":15,"area":null},{"id":"2303.01311","title":"Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2306.14153","title":"DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data","created":"2023-06-25","cited_by_count":15,"area":"diffusion"},{"id":"2403.11395","title":"Automated data processing and feature engineering for deep learning and big data applications: a survey","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2302.10167","title":"Cross-domain Compositing with Pretrained Diffusion Models","created":"2023-02-20","cited_by_count":13,"area":"diffusion"},{"id":"2308.06097","title":"RIGID: Recurrent GAN Inversion and Editing of Real Face Videos","created":"2023-08-11","cited_by_count":13,"area":null},{"id":"2410.05259","title":"GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2206.12396","title":"Text-Driven Stylization of Video Objects","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2305.17489","title":"Text-to-image Editing by Image Information Removal","created":"2023-05-27","cited_by_count":12,"area":"diffusion"},{"id":"2306.16805","title":"CLIPAG: Towards Generator-Free Text-to-Image Generation","created":"2023-06-29","cited_by_count":12,"area":null},{"id":"2409.13591","title":"Portrait Video Editing Empowered by Multimodal Generative Priors","created":"2024-09-20","cited_by_count":12,"area":null},{"id":"2311.02820","title":"Mesh Neural Cellular Automata","created":"2023-11-06","cited_by_count":11,"area":null},{"id":"2403.00437","title":"LoMOE: Localized Multi-Object Editing via Multi-Diffusion","created":"2024-03-01","cited_by_count":11,"area":"diffusion"},{"id":"2505.11934","title":"iSegMan: Interactive Segment-and-Manipulate 3D Gaussians","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2211.07818","title":"AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging","created":"2022-11-15","cited_by_count":10,"area":null},{"id":"2311.02826","title":"InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image","created":"2023-11-06","cited_by_count":10,"area":null},{"id":"2401.11094","title":"TypeDance: Creating Semantic Typographic Logos from Image through Personalized Generation","created":"2024-01-20","cited_by_count":10,"area":null},{"id":"2402.16267","title":"Infrared and Visible Image Fusion with Language-Driven Loss in CLIP Embedding Space","created":"2024-02-26","cited_by_count":10,"area":null},{"id":"2210.06642","title":"What's in a Decade? Transforming Faces Through Time","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2211.07751","title":"Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation","created":"2022-11-14","cited_by_count":9,"area":"diffusion"},{"id":"2304.11818","title":"Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2306.08226","title":"CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration","created":"2023-06-14","cited_by_count":9,"area":"mllm"},{"id":"2308.06027","title":"Masked-Attention Diffusion Guidance for Spatially Controlling Text-to-Image Generation","created":"2023-08-11","cited_by_count":9,"area":"diffusion"},{"id":"2404.14007","title":"Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting","created":"2024-04-22","cited_by_count":9,"area":"diffusion"},{"id":"2502.03621","title":"DynVFX: Augmenting Real Videos with Dynamic Content","created":"2025-02-05","cited_by_count":9,"area":null},{"id":"2212.04412","title":"Task Bias in Vision-Language Models","created":"2022-12-08","cited_by_count":8,"area":"mllm"},{"id":"2306.04865","title":"MyStyle++: A Controllable Personalized Generative Prior","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2311.18328","title":"Advances in 3D Neural Stylization: A Survey","created":"2023-11-30","cited_by_count":8,"area":null},{"id":"2501.15562","title":"CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary","created":"2025-01-26","cited_by_count":8,"area":"diffusion"},{"id":"2210.03116","title":"Content-Based Search for Deep Generative Models","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2411.04724","title":"Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation","created":"2024-11-07","cited_by_count":7,"area":"diffusion"},{"id":"2202.04040","title":"Self-Conditioned Generative Adversarial Networks for Image Editing","created":"2022-02-08","cited_by_count":6,"area":null},{"id":"2208.08092","title":"Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing","created":"2022-08-17","cited_by_count":6,"area":null}],"next_cursor":"100"}