Free unlimited use of InfiniteTalk. Generate fast. Online training coming soon.
免费使用InfiniteTalk不限次，快速生成，在线训练即将支持。
InfiniteTalkを無料で無制限に利用可能。高速生成。オンライントレーニングはまもなく対応予定。
Uso ilimitado y gratuito de InfiniteTalk. Generación rápida. Entrenamiento en línea muy pronto.
InfiniteTalk 무제한 무료 사용. 빠른 생성. 온라인 학습 곧 지원 예정.
InfiniteTalk का असीमित और मुफ्त उपयोग करें। तेज़ जनरेशन। ऑनलाइन प्रशिक्षण जल्द ही उपलब्ध होगा।
Gunakan InfiniteTalk tanpa batas secara gratis. Hasil cepat. Pelatihan online segera hadir.
We propose InfiniteTalk, a novel sparse-frame video dubbing framework. Given an input video and audio track, InfiniteTalk synthesizes a new video with accurate lip synchronization while simultaneously aligning head movements, body posture, and facial expressions with the audio. Unlike traditional dubbing methods that focus solely on lips, InfiniteTalk enables infinite-length video generation with accurate lip synchronization and consistent identity preservation. Beside, InfiniteTalk can also be used as an image-audio-to-video model with an image and an audio as input.
💬 Sparse-frame Video Dubbing – Synchronizes not only lips, but aslo head, body, and expressions
⏱️ Infinite-Length Generation – Supports unlimited video duration
✨ Stability – Reduces hand/body distortions compared to MultiTalk
🚀 Lip Accuracy – Achieves superior lip synchronization to MultiTalk
This repository hosts the model weights for InfiniteTalk. For installation, usage instructions, and further documentation, please visit our GitHub repository.