Stable Video Diffusion
Stable Video Diffusion is a video-generation model based on Stable Diffusion.
What Stable Video Diffusion is
Stable Video Diffusion is a video-generation model based on Stable Diffusion. It can generate video from text or images, with image-to-video animation also listed. The product page describes output of 14 or 25 frames at customizable rates from 3 to 30 frames per second, and says videos are created in two minutes or less. Listed model versions include 14-frame, 25-frame, and 1.1. The model is offered for self-hosted use: Stability AI’s instructions describe downloading model weights and running them locally with the reference implementation. Hosted Stable Video Diffusion API endpoints were deprecated on July 24, 2025, and API access is no longer available. Stability AI says its foundation models are available on Amazon Bedrock and Amazon SageMaker JumpStart. The Community License is free for users below $1M in annual revenue, subject to model-specific terms; businesses above that threshold are directed to Enterprise licensing, which has custom pricing. The maker is based in London, United Kingdom.
Good
- Free Community License below $1M annual revenue
- Supports text-to-video and image-to-video
- Customizable frame rates from 3 to 30 fps
- Can be run locally with its reference implementation
Watch out
- Hosted API endpoints are no longer available
- Enterprise license has custom pricing
- Self-hosting requires downloading model weights
Who it suits
It may suit people or organizations seeking a self-hosted model for generating video from text or images. Businesses above $1M in annual revenue are directed to Enterprise licensing.
Verdict
Stable Video Diffusion offers video generation for self-hosted deployment, with listed options for frame count and rate. Check the applicable model license, particularly if your business exceeds the Community License revenue threshold.
Plans and prices
From Stable Video Diffusion's own pricing page, checked 9 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Community License | Free | Community users; listed as free; Stable Video Diffusion access is subject to model-specific license terms |
| Community self-hosted license | Free | Research, non-commercial and limited commercial use · organizations under USD $1M annual revenue · Free |
| Enterprise License | Priced on request | For enterprise, API providers, and businesses with annual revenue exceeding $1M; commercial use and implementation support; custom pricing |
| Enterprise self-hosted license | Priced on request | Commercial use · organizations exceeding USD $1M annual revenue · implementation support · Custom Pricing |
The facts
Each one read from Stable Video Diffusion's own pages, with the date it was checked.
What it does
- API access
- Nochecked 19 Sep 2026
- API status
- The hosted Stable Video API was deprecated on July 24, 2025 and its endpoints are unavailable.checked 21 Oct 2026
- Capterra praise
- The single Capterra reviewer praises realistic detailed images, the Relight feature and value for money.checked 21 Oct 2026
- Commercial threshold
- Commercial use above USD $1M annual revenue requires an Enterprise license.checked 21 Oct 2026
- Commercial use
- Yeschecked 19 Sep 2026
- Data use
- The privacy policy says users can opt out of use of their Inputs and Outputs for model training through Account Settings.checked 9 Oct 2026
- Deployment
- Stability AI says Stable Video Diffusion can be deployed on your own infrastructure with a self-hosted license.checked 9 Oct 2026
- Developer code
- The public Generative-Models repository contains scripts, configs, requirements, tests and sampling utilities for local use.checked 21 Oct 2026
- Frame counts
- The product page says the model can generate 14 or 25 frames.checked 21 Oct 2026
- Frame-rate control
- Frame rates can be selected from 3 through 30 frames per second.checked 21 Oct 2026
- Frame rates
- The product page says it can generate 14 or 25 frames at customizable frame rates between 3 and 30 frames per second.checked 9 Oct 2026
- Hardware guidance
- Clore’s deployment guide lists 16GB VRAM for 14-frame SVD and 24GB for 25-frame SVD-XT, recommending RTX 4090 or A100 hardware.checked 21 Oct 2026
- Image-to-video
- Yeschecked 19 Sep 2026
- Independent output limit
- An independent evaluation describes SVD clips as no longer than about four seconds, with possible low motion, imperfect photorealism, poor text rendering and problematic faces.checked 21 Oct 2026
- Independent quality limit
- The same guide says newer models have surpassed SVD in motion quality and offer features such as native audio that SVD lacks.checked 21 Oct 2026
- Independent technical limit
- A 2026 technical guide says SVD is image-to-video and does not natively accept text prompts, despite the current official product page advertising text-to-video.checked 21 Oct 2026
- Integration
- Stability AI says its foundation models are available on Amazon Bedrock and Amazon SageMaker JumpStart.checked 9 Oct 2026
- License threshold
- The license page describes Community licensing for users below $1M in annual revenue and directs businesses above that threshold to Enterprise licensing.checked 9 Oct 2026
The company
- Company founded
- CB Insights lists Stability AI as founded in 2019.checked 21 Oct 2026
- Company headquarters
- LinkedIn lists headquarters in Los Angeles, California.checked 21 Oct 2026
- Company legal name
- Crunchbase identifies the maker’s legal name as Stability AI Ltd.checked 21 Oct 2026
- Company size
- LinkedIn lists Stability AI in the 51–200 employee range.checked 21 Oct 2026
- Headquarters
- London, United Kingdomchecked 28 Sep 2026
Money
- Free plan
- Yeschecked 19 Sep 2026
Alternatives to Stable Video Diffusion
- 1
HeyGen
Free planAndroidiOSWebAPI9.1From $24 a month - 2
PixVerse
Free planAndroidiOSWebAPI9.1From $8 a month - 3
Kling AI
Free planAndroidiOSWebAPI9.0From $6.99 a month - 4
InVideo AI
Free planAndroidiOSWebAPI9.0From $4 a month - 5
Pollo AI
Free planAndroidiOSWebAPI9.0Free plan - 6
Visla AI Video Agent
Free planAndroidiOSWebAPI8.9Free plan