{"list":"other","total":52,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"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":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"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},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2412.08629","title":"FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models","created":"2024-12-11","cited_by_count":217},{"id":"2504.20690","title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","created":"2025-04-29","cited_by_count":204},{"id":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171},{"id":"2312.04965","title":"Inversion-Free Image Editing with Natural Language","created":"2023-12-07","cited_by_count":106},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89},{"id":"2403.16990","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","created":"2024-03-25","cited_by_count":69},{"id":"2011.11731","title":"HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms","created":"2020-11-23","cited_by_count":64},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49},{"id":"2310.13165","title":"CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation","created":"2023-10-19","cited_by_count":41},{"id":"2312.03626","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","created":"2023-12-06","cited_by_count":40},{"id":"2504.13109","title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","created":"2025-04-17","cited_by_count":39},{"id":"2410.12669","title":"3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation","created":"2024-10-16","cited_by_count":37},{"id":"1804.04128","title":"Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation","created":"2018-04-11","cited_by_count":35},{"id":"2402.10855","title":"Control Color: Multimodal Diffusion-based Interactive Image Colorization","created":"2024-02-16","cited_by_count":33},{"id":"2407.07197","title":"ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement","created":"2024-07-09","cited_by_count":28},{"id":"2503.06746","title":"Color Alignment in Diffusion","created":"2025-03-09","cited_by_count":10},{"id":"2503.19034","title":"Color Conditional Generation with Sliced Wasserstein Guidance","created":"2025-03-24","cited_by_count":10},{"id":"2404.05661","title":"Automatic Controllable Colorization via Imagination","created":"2024-04-08","cited_by_count":7},{"id":"2503.09864","title":"Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models","created":"2025-03-12","cited_by_count":7},{"id":"2308.03059","title":"Language-based Photo Color Adjustment for Graphic Designs","created":"2023-08-06","cited_by_count":6},{"id":"2508.09131","title":"Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer","created":"2025-08-12","cited_by_count":5},{"id":"2409.02429","title":"Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis","created":"2024-09-04","cited_by_count":4},{"id":"2411.10232","title":"ColorEdit: Training-free Image-Guided Color editing with diffusion model","created":"2024-11-15","cited_by_count":4},{"id":"2508.08754","title":"Exploring Palette based Color Guidance in Diffusion Models","created":"2025-08-12","cited_by_count":4},{"id":"2509.13756","title":"Controllable-Continuous Color Editing in Diffusion Model via Color Mapping","created":"2025-09-17","cited_by_count":4},{"id":"2606.05031","title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","created":"2026-06-03","cited_by_count":4},{"id":"2510.20586","title":"GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models","created":"2025-10-23","cited_by_count":3},{"id":"2411.10800","title":"Test-time Conditional Text-to-Image Synthesis Using Diffusion Models","created":"2024-11-16","cited_by_count":2},{"id":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2},{"id":"2602.20672","title":"BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models","created":"2026-02-24","cited_by_count":2},{"id":"2605.12305","title":"Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation","created":"2026-05-12","cited_by_count":2},{"id":"2509.02000","title":"Palette Aligned Image Diffusion","created":"2025-09-02","cited_by_count":1},{"id":"2601.16836","title":"ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models","created":"2026-01-23","cited_by_count":1},{"id":"2603.13547","title":"NumColor: Precise Numeric Color Control in Text-to-Image Generation","created":"2026-03-13","cited_by_count":1},{"id":"2603.18466","title":"Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion","created":"2026-03-19","cited_by_count":1}],"next_cursor":null}