正在加载视频...
视频加载失败
Alibaba just announced FantasyTalking on Hugging Face Realistic Talking Portrait Generation via Coherent Motion Synthesis
10 条评论
AK1 年前
discuss with author:
AssemblyAI1 年前
Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇
Samruddhi | AI Agents 🤖1 年前
Talking portraits + coherent motion = serious potential for sales avatars, customer support agents and even legacy content revival. Watching this space closely.
Lunaris1 年前
Man this looks so realistic 😮
Shashank Ashtikar1 年前
Celebrated too early. I thought the model is on HF😂
Adam Dorf1 年前
That’s ridiculously good
Arpit Sharma1 年前
You could literally have Einstein explain relativity himself.
Kat Yu1 年前
deepfake videos for everyone on your device 👌 but seriously speaking, looks outstanding
DataEatsWorld1 年前
@AlibabaGroup GOAT
an1 年前
Looks like regressed tech lol.
