Stable Video 4D (SV4D)

Published

Jul 24, 2024

Stable Video 4D (SV4D) is an AI model developed by Stability AI and Northeastern University (United Kingdom and United States), first published in July 2024. It works in the vision, video and 3d modeling domain, on tasks such as 3d reconstruction.

Epoch AI has no training-compute estimate for this model. Training ran on 8 NVIDIA H100 SXM5 80GB.

Access: Open weights (restricted use). Its weights are openly available.

Full record

Organization: Stability AI, Northeastern University
Country of organization: United Kingdom, United States
Domain: Vision, Video, 3D modeling
Task: 3D reconstruction
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 8
Training power draw: 11.0 kW
Model accessibility: Open weights (restricted use)
Open weights: Yes

More from Stability AI,Northeastern University

Stable Video 4D 2.0 (SV4D 2.0)

SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.

← All ai models