Skip to content
Kyutai · 音视频模型· kyutai·· 2026-09-29AI score22

Kyutai Releases OVIE-ft DL3DV Fine-Tuned Version: A Monocular Novel View Synthesis Model

kyutai/ovie-ft-dl3dv

AI briefing

Kyutai fine-tuned OVIE for 50,000 steps on the DL3DV dataset and released kyutai/ovie-ft-dl3dv, which shares the same architecture as the base model with only the weights differing.

Open original huggingface.co