This is a highly stable digital human video generation application based on LTX 2.3.
Simply upload a portrait image + an audio clip to generate a "talking video" with lip-sync and natural movements.
Built-in VBVR video inference enhancement LoRA significantly improves motion stability and semantic consistency, effectively preventing issues such as screen jitter and lip-sync mismatch.
Suitable for scenarios such as digital humans, AI narration, virtual anchors, and content production.
🎁Claim RH Coins first, then go try out the workflow! Click the avatar in the top right corner → Invitation Code → Enter 【rh-v1111】 to instantly get 1000 RH Coins. Log in daily to claim another 100 coins~ For more ComfyUI workflows, tutorials, and gameplay, please follow our official WeChat account (AIKSK), with simultaneous updates on Douyin / Bilibili / Xiaohongshu / YouTube (AI-KSK) ✨