Stable Video Diffusion

Open weights Stability AI November 2023

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
25 November 2023
Authors
Andreas Blattmann, Tim Dockhorn, Sumith Kulal, Daniel Mendelevitch, Maciej Kilian, Dominik Lorenz, Yam Levi, Zion English, Vikram Voleti, Adam Letts, Varun Jampani, Robin Rombach

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Image generation, Video
Task
Image generation, Video generation, Text-to-video, Image-to-video

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

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
6.7 × 10²² FLOP

312000000000000 FLOP / GPU / sec [bf16 assumed] * 200000 GPU-hours * 3600 sec / hour * 0.3 [assumed utilization] = 6.7392e+22 FLOP

How it was established
Hardware

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
384
Chip-hours
200,000
Power draw
304.6 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
Open (non-commercial)

https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt 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

Hugging Face
stabilityai

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
Last updated
28 November 2025

What the numbers mean

About this model

Stable Video Diffusion was published by Stability AI, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during November 2023. The category the publisher falls under is industry.

It works in the domain of Image generation, Video, and is recorded as performing the task of image generation, Video generation, Text-to-video, Image-to-video.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. On Hugging Face it is published under the organisation stabilityai.

Training and provenance

Training it took a computation budget of roughly 6.7 × 10²² 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 Diffusion — common questions

01

Stable Video Diffusion— what is it used for?

It works in the domain of Image generation, Video, and is recorded as handling the task of image generation, Video generation, Text-to-video, Image-to-video. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

Stable Video Diffusion— 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.

03

Stable Video Diffusion— how much compute was used to train it?

Training consumed around 6.7 × 10²² 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.

04

Stable Video Diffusion— 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.

05

Stable Video Diffusion— 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.

06

Stable Video Diffusion— 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.

07

Stable Video Diffusion— who created it?

It was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

08

Stable Video Diffusion— when was it released?

It was published in November 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 28 November 2025

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.