Showing 2025Show all
3 papers · 1 filter
cs.CV2025
Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
Joonghyuk Shin, Alchan Hwang, Yujin Kim +2
Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in st…
cs.CV2025
Improving Editability in Image Generation with Layer-wise Memory
Daneul Kim, Jaeah Lee, Jaesik Park
Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, st…
cs.CV2025
Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
Daneul Kim, Jingxu Zhang, Wonjoon Jin +4
Subject-driven video generation (SDV-Gen) aims to produce videos of a specific subject by adapting a pretrained video model, enabling personalized and application-driven content cr…