Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancementby Zhiyuan Chang, Mingyang Li, Junjie…
Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Modelsby…
Holistic Evaluation for Interleaved Text-and-Image Generationby Minqian Liu, Zhiyang Xu, Zihao Lin, Trevor Ashby, Joy…
Make It Count: Text-to-Image Generation with an Accurate Number of Objectsby Lital Binyamin, Yoad Tewel,…
Batch-Instructed Gradient for Prompt Evolution:Systematic Prompt Optimization for Enhanced Text-to-Image Synthesisby Xinrui Yang, Zhuohan Wang,…
Coherent Zero-Shot Visual Instruction Generationby Quynh Phung, Songwei Ge, Jia-Bin HuangFirst submitted to arxiv on:…
TexIm FAST: Text-to-Image Representation for Semantic Similarity Evaluation using Transformersby Wazib Ansar, Saptarsi Goswami, Amlan…
DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarksby Haokun Zhou, Yipeng…
GenAI Arena: An Open Evaluation Platform for Generative Modelsby Dongfu Jiang, Max Ku, Tianle Li,…
The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noiseby Yuanhao Ban,…