VGGT (CVPR 2025)
Generate virtual camera views from input images
Enhance and dehaze images
Large Language Diffusion Models
Generate saliency maps and heatmaps from images
Generate saliency maps for images
Create top-quality 3D(.GLB) models from text or images
Execute custom code from environment variables
Image Super-resolution via Diffusion Inversion
Quickly edit the expression of a face
Voice conversion framework based on VITS
GPT 4o like bot.
Remove backgrounds from images
A game where you need to identify AI Generated insects
Generate high-fidelity audio from input audio waveforms
Upscale images to x4