跳到正文
𝕏 ModelScope(x.com)·· 6 天前精選品質評分66
重點導讀

讓 AI 角色跟著語音說話時,嘴型、表情和身體動作有時不夠自然,影片變長後也可能逐漸失去一致性。

  • LongCat-Video-Avatar 1.6 改善語音和嘴型同步、臉部與身體動作,也降低說話時嘴巴動作過大的情況,並讓影片延續到超過 10 分鐘時更能維持角色樣貌和畫面連貫。
  • 它支援單人與多人角色影片,也能從音訊、文字、圖片或既有影片開始生成。
  • 在 33,051 張投票、共 6 個系統的評比中,它排名第二。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

推薦理由

LongCat-Video-Avatar 1.6 在 33,051 張投票的偏好評比中排名第二,也主打改善長影片延續時的角色一致性,提供了比較表現與長片能力的參考。

ModelScope
ModelScope@ModelScope2022
·6 天前
𝕏

LongCat-Video-Avatar 1.6 is out, pushing audio-driven avatar video past 10 minutes with more natural speech motion and stronger long-form consistency. 📜 MIT License.
🤖 https://t.co/y37J1ZheP0

🏆 Ranks #2 in human preference: It places second among six evaluated systems in a 33,051-vote Arena, ahead of LongCat-Video-Avatar 1.5, HeyGen, OmniHuman-1.5, and Kling Avatar 2.0.

🗣️ More natural talking avatars: The update improves lip-audio sync, facial and body motion, and reduces exaggerated mouth artifacts during speech.

🎬 Built for long-form video: It reduces error accumulation during autoregressive continuation to preserve identity, visual quality, and temporal coherence beyond 10 minutes.

🧩 More than a single portrait workflow: Supports single- and multi-character audio-driven video generation, including audio-text-to-video, audio-image-to-video, and video continuation.

⚡ Optimized for serving: Includes end-to-end inference improvements, task-specific LoRAs, and an optional weight-only INT8 DiT checkpoint.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論