#dit2 articles

2 articles

AIBullisharXiv – CS AI · 5d ago6/103

🧠

SounDiT: Geo-Contextual Soundscape-to-Landscape Generation

Researchers introduce SounDiT, a new AI model that generates realistic landscape images from environmental soundscapes using geo-contextual data. The model uses diffusion transformer technology and is trained on two large-scale datasets pairing environmental sounds with real-world landscape images.

AIBullisharXiv – CS AI · 5d ago6/104

🧠

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing

DragFlow introduces the first framework to leverage FLUX's DiT priors for drag-based image editing, addressing distortion issues that plagued earlier Stable Diffusion-based approaches. The system uses region-based editing with affine transformations instead of point-based supervision, achieving state-of-the-art results on benchmarks.