{"total":105,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670,"area":"diffusion"},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2309.06380","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","created":"2023-09-12","cited_by_count":395,"area":"diffusion"},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260,"area":null},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259,"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":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212,"area":"diffusion"},{"id":"2301.09515","title":"StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis","created":"2023-01-23","cited_by_count":212,"area":null},{"id":"2212.09611","title":"Optimizing Prompts for Text-to-Image Generation","created":"2022-12-19","cited_by_count":207,"area":null},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2303.11306","title":"Localizing Object-level Shape Variations with Text-to-Image Diffusion Models","created":"2023-03-20","cited_by_count":142,"area":"diffusion"},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116,"area":"diffusion"},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108,"area":null},{"id":"2308.05095","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","created":"2023-08-09","cited_by_count":92,"area":"diffusion"},{"id":"2405.05967","title":"Distilling Diffusion Models into Conditional GANs","created":"2024-05-09","cited_by_count":78,"area":"diffusion"},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72,"area":null},{"id":"2203.14622","title":"Towards Implicit Text-Guided 3D Shape Generation","created":"2022-03-28","cited_by_count":68,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2303.14412","title":"Freestyle Layout-to-Image Synthesis","created":"2023-03-25","cited_by_count":67,"area":"diffusion"},{"id":"2304.09337","title":"Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models","created":"2023-04-18","cited_by_count":67,"area":null},{"id":"2403.11614","title":"CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Model","created":"2024-03-18","cited_by_count":55,"area":"diffusion"},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2208.11296","title":"Semi-Supervised and Unsupervised Deep Visual Learning: A Survey","created":"2022-08-24","cited_by_count":52,"area":null},{"id":"2406.07546","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","created":"2024-06-11","cited_by_count":52,"area":null},{"id":"2309.00810","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","created":"2023-09-02","cited_by_count":47,"area":"diffusion"},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2305.13308","title":"If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection","created":"2023-05-22","cited_by_count":40,"area":"diffusion"},{"id":"2305.03302","title":"High-Fidelity 3D Face Generation from Natural Language Descriptions","created":"2023-05-05","cited_by_count":33,"area":null},{"id":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31,"area":"lr"},{"id":"2208.04441","title":"Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks","created":"2022-08-08","cited_by_count":30,"area":null},{"id":"2312.06573","title":"ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems","created":"2023-12-11","cited_by_count":30,"area":"diffusion"},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2309.02455","title":"RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model","created":"2023-09-03","cited_by_count":29,"area":"diffusion"},{"id":"2209.04145","title":"ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2022-09-09","cited_by_count":27,"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":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2303.08225","title":"Graph Transformer GANs for Graph-Constrained House Generation","created":"2023-03-14","cited_by_count":19,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2203.11242","title":"A survey on GANs for computer vision: Recent research, analysis and taxonomy","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2212.05056","title":"Testing Human Ability To Detect Deepfake Images of Human Faces","created":"2022-12-07","cited_by_count":15,"area":null},{"id":"2203.09554","title":"CoGS: Controllable Generation and Search from Sketch and Style","created":"2022-03-17","cited_by_count":14,"area":null},{"id":"2305.15753","title":"T2TD: Text-3D Generation Model based on Prior Knowledge Guidance","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2402.04504","title":"Text2Street: Controllable Text-to-image Generation for Street Views","created":"2024-02-07","cited_by_count":13,"area":"diffusion"},{"id":"2407.08061","title":"Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Views","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2204.10482","title":"Recurrent Affine Transformation for Text-to-image Synthesis","created":"2022-04-22","cited_by_count":11,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2107.13516","title":"CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"2502.14779","title":"DC-ControlNet: Decoupling Inter- and Intra-Element Conditions in Image Generation with Diffusion Models","created":"2025-02-20","cited_by_count":10,"area":"diffusion"},{"id":"2102.03141","title":"CharacterGAN: Few-Shot Keypoint Character Animation and Reposing","created":"2021-02-05","cited_by_count":9,"area":null},{"id":"2107.04240","title":"Deep Image Synthesis from Intuitive User Input: A Review and Perspectives","created":"2021-07-09","cited_by_count":8,"area":null},{"id":"2203.00047","title":"Local and Global GANs with Semantic-Aware Upsampling for Image Generation","created":"2022-02-28","cited_by_count":8,"area":null},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2107.01869","title":"Towards Better Adversarial Synthesis of Human Images from Text","created":"2021-07-05","cited_by_count":7,"area":null},{"id":"2111.09267","title":"DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation","created":"2021-11-17","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2112.00800","title":"Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text","created":"2021-12-01","cited_by_count":6,"area":null},{"id":"2210.05147","title":"Markup-to-Image Diffusion Models with Scheduled Sampling","created":"2022-10-11","cited_by_count":6,"area":"diffusion"},{"id":"2302.08706","title":"Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis","created":"2023-02-17","cited_by_count":6,"area":null},{"id":"2208.09596","title":"Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2211.15352","title":"Interactive Image Manipulation with Complex Text Instructions","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2309.03815","title":"T2IW: Joint Text to Image & Watermark Generation","created":"2023-09-07","cited_by_count":5,"area":"safety"},{"id":"2401.07721","title":"Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2401.11631","title":"Text-to-Image Cross-Modal Generation: A Systematic Review","created":"2024-01-21","cited_by_count":5,"area":null},{"id":"2111.13282","title":"Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2204.02035","title":"DT2I: Dense Text-to-Image Generation from Region Descriptions","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2205.00804","title":"Seeding Diversity into AI Art","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2208.12752","title":"T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2209.02136","title":"Facial Expression Translation using Landmark Guided GANs","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2303.15181","title":"DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2306.02083","title":"Efficient Text-Guided 3D-Aware Portrait Generation with Score Distillation Sampling on Distribution","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2501.09042","title":"CookingDiffusion: Cooking Procedural Image Generation with Stable Diffusion","created":"2025-01-15","cited_by_count":4,"area":"diffusion"},{"id":"2107.12579","title":"Remember What You have drawn: Semantic Image Manipulation with Memory","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2108.08955","title":"CIGLI: Conditional Image Generation from Language & Image","created":"2021-08-20","cited_by_count":3,"area":null},{"id":"2505.04347","title":"CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion","created":"2025-05-07","cited_by_count":3,"area":"diffusion"},{"id":"2104.02925","title":"Pretrained equivariant features improve unsupervised landmark discovery","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2104.09757","title":"Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2104.12663","title":"CAGAN: Text-To-Image Generation with Combined Attention GANs","created":"2021-04-26","cited_by_count":2,"area":null},{"id":"2106.13933","title":"Inverting and Understanding Object Detectors","created":"2021-06-26","cited_by_count":2,"area":null},{"id":"2310.17451","title":"Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings","created":"2023-10-26","cited_by_count":2,"area":"lr"},{"id":"2404.14676","title":"DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidance","created":"2024-04-23","cited_by_count":2,"area":"diffusion"},{"id":"2102.00997","title":"Inferring spatial relations from textual descriptions of images","created":"2021-02-01","cited_by_count":1,"area":null},{"id":"2107.07397","title":"Level generation and style enhancement -- deep learning for game development overview","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2109.11749","title":"Fine-Grained Image Generation from Bangla Text Description using Attentional Generative Adversarial Network","created":"2021-09-24","cited_by_count":1,"area":null},{"id":"2112.04928","title":"Self-Supervised Image-to-Text and Text-to-Image Synthesis","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2112.15541","title":"on the effectiveness of generative adversarial network on anomaly detection","created":"2021-12-31","cited_by_count":1,"area":null},{"id":"2311.13960","title":"Human Machine Co-Creation. A Complementary Cognitive Approach to Creative Character Design Process Using GANs","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2409.11689","title":"GUNet: A Graph Convolutional Network United Diffusion Model for Stable and Diversity Pose Generation","created":"2024-09-18","cited_by_count":1,"area":"diffusion"},{"id":"2410.01638","title":"Data Extrapolation for Text-to-image Generation on Small Datasets","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2502.01507","title":"End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2507.09441","title":"RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling","created":"2025-07-13","cited_by_count":1,"area":"diffusion"},{"id":"2102.07360","title":"Generating Structured Adversarial Attacks Using Frank-Wolfe Method","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2106.06321","title":"ViT-Inception-GAN for Image Colourising","created":"2021-06-11","cited_by_count":0,"area":null},{"id":"2106.13590","title":"Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2110.02404","title":"3D-MOV: Audio-Visual LSTM Autoencoder for 3D Reconstruction of Multiple Objects from Video","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2208.01265","title":"Explicit Use of Fourier Spectrum in Generative Adversarial Networks","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2303.01555","title":"Counterfactual Edits for Generative Evaluation","created":"2023-03-02","cited_by_count":0,"area":null}],"next_cursor":"100"}