Stable Video 3D (SV3D)
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
- Organisation type
- Industry
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 18 March 2024
- Authors
- Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, 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
"All three models (SV3Du, SV3Dc, SV3Dp) are trained for 105k iterations in total (SV3Dp is trained unconditionally for 55k iterations and conditionally for 50k iterations), with an effective batch size of 64 on 4 nodes of 8 80GB A100 GPUs for around 6 days."
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 5.2 × 10²⁰ FLOP
- How it was established
- Hardware
4 nodes * 8 GPUs * 144 hours * 3600 sec / hour * 312000000000000 FLOP / GPU / hour * 0.3 [assumed utilization] / 3 models = 5.1757056e+20 FLOP
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 A100 SXM4 80 GB
- Chips used
- 32
- Wall-clock time
- 144 hours
- Power draw
- 25.3 kW
"on 4 nodes of 8 80GB A100 GPUs for around 6 days." 6*24 = 144 hours
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 (non-commercial)
- Training code
- Unreleased
- Hugging Face
- stabilityai
License: Stability AI Community License. NC https://huggingface.co/stabilityai/sv3d
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
Stable Video 3D (SV3D) was published by Stability AI, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during March 2024. It comes out of an organisation categorised as industry.
It works in the domain of Vision, 3D modeling, and is recorded as performing the task of 3D reconstruction.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. On Hugging Face it is published under the organisation stabilityai.
Training and provenance
Training it took a computation budget of roughly 5.2 × 10²⁰ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Answers
Stable Video 3D (SV3D) — common questions
Stable Video 3D (SV3D)— how much compute was used to train it?
Training consumed around 5.2 × 10²⁰ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
Stable Video 3D (SV3D)— what GPU do I need to run it?
We cannot say. It 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.
Stable Video 3D (SV3D)— is it open source?
Its weights are published, so it 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.
Stable Video 3D (SV3D)— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Stable Video 3D (SV3D)— who created it?
It was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.
Stable Video 3D (SV3D)— when was it released?
It was published in March 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Stable Video 3D (SV3D)— what is it used for?
It works in the domain of Vision, 3D modeling, and is recorded as handling the task of 3D reconstruction. These are the areas it was designed around; they describe intent rather than a hard boundary.
Stable Video 3D (SV3D)— where can I download it?
Its weights are published on Hugging Face, under the organisation stabilityai. We do not host model files — this site calculates what hardware is needed to run them.
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.