Expressive Zeroshot TTS
Remove background from images
Describe objects in webcam feed
Generates a podcast about today's top trending paper.
Use the FLUX-Pro model as much as you want.
image2mesh
Generate 3D models and videos from images
Translate text into different languages
Generate depth estimation map from images
Create 3D reconstructions from videos or images
Generate music from text and melody
VGGT (CVPR 2025)
Generate music from text descriptions