Future? TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models Paper • 2506.03099 • Published Jun 3, 2025 • 20 moonshotai/Kimi-K2-Instruct Text Generation • 1T • Updated Apr 23 • 354k • • 2.37k Running 570 InferenceSupport 💥 570 Discussions about the Inference Providers feature on the Hub
TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models Paper • 2506.03099 • Published Jun 3, 2025 • 20
Future? TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models Paper • 2506.03099 • Published Jun 3, 2025 • 20 moonshotai/Kimi-K2-Instruct Text Generation • 1T • Updated Apr 23 • 354k • • 2.37k Running 570 InferenceSupport 💥 570 Discussions about the Inference Providers feature on the Hub
TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models Paper • 2506.03099 • Published Jun 3, 2025 • 20
