{"total":89,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431,"area":null},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991,"area":null},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179,"area":null},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141,"area":null},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128,"area":null},{"id":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107,"area":null},{"id":"2305.18247","title":"TaleCrafter: Interactive Story Visualization with Multiple Characters","created":"2023-05-29","cited_by_count":73,"area":null},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71,"area":null},{"id":"2304.01816","title":"Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation","created":"2023-04-04","cited_by_count":68,"area":null},{"id":"2107.02423","title":"Improving Text-to-Image Synthesis Using Contrastive Learning","created":"2021-07-06","cited_by_count":62,"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":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54,"area":null},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2104.00567","title":"Text to Image Generation with Semantic-Spatial Aware GAN","created":"2021-04-01","cited_by_count":53,"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":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47,"area":null},{"id":"2108.12141","title":"DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis","created":"2021-08-27","cited_by_count":45,"area":null},{"id":"2105.10026","title":"Improving Generation and Evaluation of Visual Stories via Semantic Consistency","created":"2021-05-20","cited_by_count":43,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2304.05818","title":"Gradient-Free Textual Inversion","created":"2023-04-12","cited_by_count":29,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2108.01361","title":"Cycle-Consistent Inverse GAN for Text-to-Image Synthesis","created":"2021-08-03","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":"2210.07883","title":"One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations","created":"2022-10-14","cited_by_count":24,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2403.18383","title":"Generative Multi-modal Models are Good Class-Incremental Learners","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2412.14456","title":"LEDiff: Latent Exposure Diffusion for HDR Generation","created":"2024-12-19","cited_by_count":22,"area":null},{"id":"2301.01413","title":"Attribute-Centric Compositional Text-to-Image Generation","created":"2023-01-04","cited_by_count":19,"area":null},{"id":"2311.15941","title":"Tell2Design: A Dataset for Language-Guided Floor Plan Generation","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2203.02104","title":"Interactive Image Synthesis with Panoptic Layout Generation","created":"2022-03-04","cited_by_count":17,"area":null},{"id":"2202.02713","title":"FEAT: Face Editing with Attention","created":"2022-02-06","cited_by_count":16,"area":null},{"id":"2208.05621","title":"ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design","created":"2022-08-11","cited_by_count":16,"area":null},{"id":"2308.11206","title":"DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment","created":"2023-08-22","cited_by_count":15,"area":null},{"id":"2112.01398","title":"TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation","created":"2021-12-02","cited_by_count":13,"area":null},{"id":"2209.01339","title":"DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation","created":"2022-09-03","cited_by_count":13,"area":null},{"id":"2103.13722","title":"AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style","created":"2021-03-25","cited_by_count":11,"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":"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":"2109.14845","title":"AffectGAN: Affect-Based Generative Art Driven by Semantics","created":"2021-09-30","cited_by_count":10,"area":null},{"id":"2204.07945","title":"DR-GAN: Distribution Regularization for Text-to-Image Generation","created":"2022-04-17","cited_by_count":10,"area":null},{"id":"2208.07022","title":"Memory-Driven Text-to-Image Generation","created":"2022-08-15","cited_by_count":10,"area":null},{"id":"2104.00356","title":"Exploiting Relationship for Complex-scene Image Generation","created":"2021-04-01","cited_by_count":9,"area":null},{"id":"2208.06162","title":"Layout-Bridging Text-to-Image Synthesis","created":"2022-08-12","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":"2208.12847","title":"Region-guided CycleGANs for Stain Transfer in Whole Slide Images","created":"2022-08-26","cited_by_count":8,"area":null},{"id":"2312.10718","title":"CogCartoon: Towards Practical Story Visualization","created":"2023-12-17","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":"2209.03160","title":"AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2209.14046","title":"Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2403.13589","title":"ReGround: Improving Textual and Spatial Grounding at No Cost","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2205.07301","title":"Conditional Vector Graphics Generation for Music Cover Images","created":"2022-05-15","cited_by_count":5,"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":"2203.09052","title":"DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training","created":"2022-03-17","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":"2208.08104","title":"Understanding Attention for Vision-and-Language Tasks","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2208.08493","title":"Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2304.06297","title":"ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis","created":"2023-04-13","cited_by_count":4,"area":null},{"id":"2205.00347","title":"LayoutBERT: Masked Language Layout Model for Object Insertion","created":"2022-04-30","cited_by_count":3,"area":null},{"id":"2207.06604","title":"Rethinking Super-Resolution as Text-Guided Details Generation","created":"2022-07-14","cited_by_count":3,"area":null},{"id":"2211.07289","title":"Learning to Model Multimodal Semantic Alignment for Story Visualization","created":"2022-11-14","cited_by_count":3,"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":"2106.15011","title":"Are conditional GANs explicitly conditional?","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2109.00907","title":"FA-GAN: Feature-Aware GAN for Text to Image Synthesis","created":"2021-09-02","cited_by_count":2,"area":null},{"id":"2110.08143","title":"Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2410.01816","title":"Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2411.19182","title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2507.17332","title":"PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2510.16791","title":"Personalized Image Filter: Mastering Your Photographic Style","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2102.00997","title":"Inferring spatial relations from textual descriptions of images","created":"2021-02-01","cited_by_count":1,"area":null},{"id":"2110.01659","title":"Cross-Modal Virtual Sensing for Combustion Instability Monitoring","created":"2021-10-04","cited_by_count":1,"area":null},{"id":"2204.12678","title":"Optimized latent-code selection for explainable conditional text-to-image GANs","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2205.11273","title":"GR-GAN: Gradual Refinement Text-to-image Generation","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2209.03953","title":"Text-Free Learning of a Natural Language Interface for Pretrained Face Generators","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2312.10854","title":"The Right Losses for the Right Gains: Improving the Semantic Consistency of Deep Text-to-Image Generation with Distribution-Sensitive Losses","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2401.14212","title":"Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2103.08475","title":"Deep Consensus Learning","created":"2021-03-15","cited_by_count":0,"area":null},{"id":"2106.03128","title":"MOC-GAN: Mixing Objects and Captions to Generate Realistic Images","created":"2021-06-06","cited_by_count":0,"area":null},{"id":"2205.02439","title":"Text to artistic image generation","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2205.12512","title":"Text-to-Face Generation with StyleGAN2","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2309.15516","title":"Teaching Text-to-Image Models to Communicate in Dialog","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2508.11153","title":"LEARN: A Story-Driven Layout-to-Image Generation Framework for STEM Instruction","created":"2025-08-15","cited_by_count":0,"area":null}],"next_cursor":null}