Stable Video 3D (SV3D) is an AI model developed by Stability AI (United Kingdom), first published in March 2024. It works in the vision and 3d modeling domain, on tasks such as 3d reconstruction.
Training it took an estimated 5.2×10²⁰ FLOP of compute (estimation method: hardware). Training ran on 32 NVIDIA A100 SXM4 80 GB for about 144 hours.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.