Submitted by akhaliq 18 Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions · 6 authors 1
Submitted by akhaliq 18 Boundary Attention: Learning to Find Faint Boundaries at Any Resolution · 6 authors
Submitted by akhaliq 12 En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data · 6 authors 9
Submitted by akhaliq 11 Multilingual Instruction Tuning With Just a Pinch of Multilinguality · 6 authors
Submitted by akhaliq 10 Taming Mode Collapse in Score Distillation for Text-to-3D Generation · 11 authors
Submitted by akhaliq 8 WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope · 13 authors