Stable Video 4D 2.0 (SV4D 2.0)
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Stability AI,Northeastern University
- Organisation type
- Industry,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland, United States of America
- Published
- 25 March 2025
- Authors
- Chun-Han Yao, Yiming Xie, Vikram Voleti, Huaizu Jiang, Varun Jampani
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Video, 3D modeling
- Task
- 3D reconstruction
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- tokens
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA H100 SXM5 80GB
- Chips used
- 16
- Power draw
- 22.0 kW
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (restricted use)
- Training code
- Unreleased
- Hugging Face
- stabilityai
stabilityai-ai-community https://huggingface.co/stabilityai/sv4d2.0 Community License: Free for research, non-commercial, and commercial use by organizations and individuals generating annual revenue of US $1,000,000 (or local currency equivalent) or less, regardless of the source of that revenue. https://github.com/Stability-AI/generative-models
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
Stable Video 4D 2.0 (SV4D 2.0) was published by Stability AI,Northeastern University, in United Kingdom of Great Britain and Northern Ireland, in March 2025. It comes out of industry,Academia.
It works in Vision, Video, 3D modeling, and is recorded as doing 3D reconstruction.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the stabilityai organisation on Hugging Face.
Answers
Stable Video 4D 2.0 (SV4D 2.0) — common questions
When was Stable Video 4D 2.0 (SV4D 2.0) released?
Stable Video 4D 2.0 (SV4D 2.0) was published in March 2025.
What is Stable Video 4D 2.0 (SV4D 2.0) used for?
Stable Video 4D 2.0 (SV4D 2.0) works in Vision, Video, 3D modeling, and is recorded as handling 3D reconstruction. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download Stable Video 4D 2.0 (SV4D 2.0)?
Its weights are published under the stabilityai organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
What GPU do I need to run Stable Video 4D 2.0 (SV4D 2.0)?
We cannot say. Stable Video 4D 2.0 (SV4D 2.0) has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is Stable Video 4D 2.0 (SV4D 2.0) open source?
Its weights are published, so Stable Video 4D 2.0 (SV4D 2.0) can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does Stable Video 4D 2.0 (SV4D 2.0) have?
No parameter count has been published for Stable Video 4D 2.0 (SV4D 2.0), which is why no memory or speed figure appears on this page.
Who created Stable Video 4D 2.0 (SV4D 2.0)?
Stable Video 4D 2.0 (SV4D 2.0) was published by Stability AI,Northeastern University, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry,Academia.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.