Imagen de Portada

The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaofeng, Zhang, Courville, Aaron, Drozdzal, Michal, Romero-Soriano, Adriana
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving Text-to-Image Consistency via Automatic Prompt Optimization
por: Mañas, Oscar, et al.
Publicado: (2024)

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
por: Hall, Melissa, et al.
Publicado: (2023)

PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
por: Assouel, Rim, et al.
Publicado: (2026)

Increasing the Utility of Synthetic Images through Chamfer Guidance
por: Dall'Asen, Nicola, et al.
Publicado: (2025)

Entropy Rectifying Guidance for Diffusion and Flow Models
por: Ifriqi, Tariq Berrada, et al.
Publicado: (2025)

Object-centric Binding in Contrastive Language-Image Pretraining
por: Assouel, Rim, et al.
Publicado: (2025)

Consistency-diversity-realism Pareto fronts of conditional image generative models
por: Astolfi, Pietro, et al.
Publicado: (2024)

Inference-time Physics Alignment of Video Generative Models with Latent World Models
por: Yuan, Jianhao, et al.
Publicado: (2026)

Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
por: Hall, Melissa, et al.
Publicado: (2024)

Feedback-guided Data Synthesis for Imbalanced Classification
por: Hemmat, Reyhane Askari, et al.
Publicado: (2023)

Improving the Physics of Video Generation with VJEPA-2 Reward Signal
por: Yuan, Jianhao, et al.
Publicado: (2025)

Multi-Modal Language Models as Text-to-Image Model Evaluators
por: Chen, Jiahui, et al.
Publicado: (2025)

Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance
por: Hemmat, Reyhane Askari, et al.
Publicado: (2024)

Boosting Latent Diffusion with Perceptual Objectives
por: Berrada, Tariq, et al.
Publicado: (2024)

Controlling Multimodal LLMs via Reward-guided Decoding
por: Mañas, Oscar, et al.
Publicado: (2025)

Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency
por: Sun, Shangkun, et al.
Publicado: (2025)

Bias Analysis in Unconditional Image Generative Models
por: Zhang, Xiaofeng, et al.
Publicado: (2025)

On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
por: Ifriqi, Tariq Berrada, et al.
Publicado: (2024)

DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models
por: Teotia, Revant, et al.
Publicado: (2025)

Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
por: Lavoie, Samuel, et al.
Publicado: (2025)

EvalGIM: A Library for Evaluating Generative Image Models
por: Hall, Melissa, et al.
Publicado: (2024)

Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning
por: Ma, Xu, et al.
Publicado: (2026)

ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation
por: Mazuz, Yohai, et al.
Publicado: (2025)

Modeling Caption Diversity in Contrastive Vision-Language Pretraining
por: Lavoie, Samuel, et al.
Publicado: (2024)

Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts
por: Liu, Qin, et al.
Publicado: (2024)

Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains
por: Ran, Wu, et al.
Publicado: (2024)

Consistency-guided Prompt Learning for Vision-Language Models
por: Roy, Shuvendu, et al.
Publicado: (2023)

FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
por: Yang, Kaixing, et al.
Publicado: (2025)

SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning
por: Nguyen, Bac, et al.
Publicado: (2024)

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions
por: Urbanek, Jack, et al.
Publicado: (2023)

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation
por: Ren, Weiming, et al.
Publicado: (2024)

Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
por: Zhao, Xiaoqi, et al.
Publicado: (2024)

MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
por: Yang, Kaixing, et al.
Publicado: (2025)

Cross-modal Prompting for Balanced Incomplete Multi-modal Emotion Recognition
por: He, Wen-Jue, et al.
Publicado: (2025)

OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
por: Zhang, Jinlu, et al.
Publicado: (2025)

Augmented Conditioning Is Enough For Effective Training Image Generation
por: Chen, Jiahui, et al.
Publicado: (2025)

Cross Prompting Consistency with Segment Anything Model for Semi-supervised Medical Image Segmentation
por: Miao, Juzheng, et al.
Publicado: (2024)

Consistency-Preserving Diverse Video Generation
por: Liu, Xinshuang, et al.
Publicado: (2026)

DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models
por: Park, Mingue, et al.
Publicado: (2025)

Diversity Covariance-Aware Prompt Learning for Vision-Language Models
por: Dong, Songlin, et al.
Publicado: (2025)