lipgans
PublicLipGANs is a text-to-viseme GAN framework that generates realistic mouth movements directly from text, without requiring audio. It maps phonemes → visemes, predicts phoneme durations, and uses per-viseme 3D GANs to synthesize photorealistic frames that can be exported as PNG sequences, GIFs, or MP4 videos.
accessibilitycomputer-visiondeep-learninggangenerative-adversarial-networkskeraslip-syncphonemepythonspeech-synthesis
Creat：2025-05-02T14:19:53
Update：2025-09-06T23:16:23
0
Stars
0
Stars Increase