Running
on
L40S
136
โจ
SVFR Demo
Unified Framework for Generalized Video Face Restoration
Unified Framework for Generalized Video Face Restoration
Scalable and Versatile 3D Generation from images
FitDiT is a high-fidelity virtual try-on model.
Upgraded to v1.0!
Gaze detection using Moondream
A demo of Indic Parler-TTS
Generate anime-style multi-view images from texts
Create top-quality 3D(.GLB) models from text or images
Optical illusions and style transfer with FLUX