Object-level Visual Prompts for Compositional Image Generation
We introduce a method for composing object-level visual prompts within a text-to-image
diffusion model. Our approach addresses the task of generating semantically coherent …
diffusion model. Our approach addresses the task of generating semantically coherent …
Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
Representing the cutting-edge technique of text-to-image models, the latest Multimodal
Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous …
Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous …
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Open-vocabulary part segmentation (OVPS) is an emerging research area focused on
segmenting fine-grained entities based on diverse and previously unseen vocabularies. Our …
segmenting fine-grained entities based on diverse and previously unseen vocabularies. Our …
Harnessing Multimodal AI for Creative Design: Performance Evaluation of Stable Diffusion and DALL-E 3 in Fashion Apparel and Typography
KN Sai, U Wable, A Singh, N Koundinya… - 2024 International …, 2024 - ieeexplore.ieee.org
In recent years, multimodal AI (Artificial Intelligence) models have exhibited promising
capabilities in generating diverse forms of creative content. This review paper critically …
capabilities in generating diverse forms of creative content. This review paper critically …
Video Diffusion Models Learn the Structure of the Dynamic World
Diffusion models have demonstrated significant progress in visual perception tasks due to
their ability to capture fine-grained, object-centric features through large-scale vision …
their ability to capture fine-grained, object-centric features through large-scale vision …