playgroundai/playground-v2.5-1024px-aesthetic
Text-to-Image
•
Updated
•
173k
•
•
702
Audio Conditioned LipSync with Latent Diffusion Models
Detect and annotate poses in images and videos
Upgraded to v1.0!
FitDiT is a high-fidelity virtual try-on model.
Unified Framework for Generalized Video Face Restoration