Freedom251 › AI video generators
Stable Video Diffusion

What Stable Video Diffusion is
Stable Video Diffusion is a model for generating video from text or images, based on Stable Diffusion. It is offered for self-hosted use: Stability AI describes downloading the model weights and running them locally with its reference implementation. The model can generate 14 or 25 frames at customizable rates between 3 and 30 frames per second, and the product page says video creation takes two minutes or less. Listed versions include 14-frame, 25-frame, and 1.1 models.
The hosted Stable Video Diffusion API endpoints were deprecated on July 24, 2025, and are no longer available. Stability AI says its foundation models are available through 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 revenue threshold are directed to the Enterprise License, which has custom pricing and includes commercial use and implementation support. The maker is based in London, United Kingdom; setup help is available through support tickets.
Who it suits
It suits people who want to generate short videos from text or images and can run the model on their own infrastructure. Businesses above $1M in annual revenue are directed to the Enterprise License.
What it does well
- Generates video from text or images
- Supports 14 or 25 frames
- Customizable frame rates from 3 to 30 fps
- Community License is free below $1M annual revenue
- Commercial use is available under license terms
What to know first
- Self-hosting requires running the model locally
- Hosted API endpoints are no longer available
- Enterprise License pricing is custom
Limits
Community licensing is described for users below $1M in annual revenue. Businesses above that threshold are directed to the Enterprise License, which uses custom pricing. Hosted API endpoints are no longer available.
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Community License | Community users; listed as free; Stable Video Diffusion access is subject to model-specific license terms | Free |
| Community self-hosted license | Free · Research, non-commercial and limited commercial use · organizations under USD $1M annual revenue | Free |
| Enterprise License | For enterprise, API providers, and businesses with annual revenue exceeding $1M; commercial use and implementation support; custom pricing | On request |
| Enterprise self-hosted license | Custom Pricing · Commercial use · organizations exceeding USD $1M annual revenue · implementation support | On request |
As stability.ai lists them, read 9 Oct 2026. The maker's own page has the final word.
Getting started
- Visit the Stable Video Diffusion website.
- Review the Community or Enterprise License for your organization.
- Download the model weights using the maker’s self-hosting instructions.
- Run the model locally with its reference implementation, or deploy it on your own infrastructure.
- Create a support ticket if you need help setting up the model.
Verdict
Stable Video Diffusion offers local video generation with configurable frame counts and rates. Check the applicable model license, especially if your business exceeds the Community License revenue threshold.
Questions
Is Stable Video Diffusion free?
The Community License is listed as free for users below $1M in annual revenue, subject to model-specific license terms.
Can it be used commercially?
Commercial use is available subject to the applicable model-specific license terms. Businesses above $1M in annual revenue are directed to Enterprise licensing.
Does it have API access?
No. Its hosted API endpoints were deprecated on July 24, 2025, and are no longer available.
How is the model run?
The maker’s instructions describe downloading the model weights and running Stable Video Diffusion locally with its reference implementation. It can also be deployed on your own infrastructure under a self-hosted license.
What video output does it support?
It can generate 14 or 25 frames at customizable rates from 3 to 30 frames per second. The listed versions include 14-frame, 25-frame, and 1.1 models.
What are the licensing options for businesses above $1M in annual revenue?
They are directed to the Enterprise License, which has custom pricing and includes commercial use and implementation support.
Facts from Stable Video Diffusion's own pages
- API access
- No · stability.ai, 19 Sept 2026
- API status
- The hosted Stable Video API was deprecated on July 24, 2025 and its endpoints are unavailable. · kb.stability.ai, 21 Oct 2026
- Capterra praise
- The single Capterra reviewer praises realistic detailed images, the Relight feature and value for money. · capterra.com, 21 Oct 2026
- Commercial threshold
- Commercial use above USD $1M annual revenue requires an Enterprise license. · stability.ai, 21 Oct 2026
- Commercial use
- Yes · stability.ai, 19 Sept 2026
- Company founded
- CB Insights lists Stability AI as founded in 2019. · cbinsights.com, 21 Oct 2026
- Company headquarters
- LinkedIn lists headquarters in Los Angeles, California. · linkedin.com, 21 Oct 2026
- Company legal name
- Crunchbase identifies the maker’s legal name as Stability AI Ltd. · crunchbase.com, 21 Oct 2026
- Company size
- LinkedIn lists Stability AI in the 51–200 employee range. · linkedin.com, 21 Oct 2026
- Data use
- The privacy policy says users can opt out of use of their Inputs and Outputs for model training through Account Settings. · stability.ai, 9 Oct 2026
- Deployment
- Stability AI says Stable Video Diffusion can be deployed on your own infrastructure with a self-hosted license. · stability.ai, 9 Oct 2026
- Developer code
- The public Generative-Models repository contains scripts, configs, requirements, tests and sampling utilities for local use. · github.com, 21 Oct 2026
- Frame counts
- The product page says the model can generate 14 or 25 frames. · stability.ai, 21 Oct 2026
- Frame-rate control
- Frame rates can be selected from 3 through 30 frames per second. · stability.ai, 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. · stability.ai, 9 Oct 2026
- Free plan
- Yes · stability.ai, 19 Sept 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. · docs.clore.ai, 21 Oct 2026
- Headquarters
- London, United Kingdom · stability.ai, 28 Sept 2026
- Image-to-video
- Yes · stability.ai, 19 Sept 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. · crfm.stanford.edu, 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. · thundercompute.com, 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. · thundercompute.com, 21 Oct 2026
- Integration
- Stability AI says its foundation models are available on Amazon Bedrock and Amazon SageMaker JumpStart. · stability.ai, 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. · stability.ai, 9 Oct 2026
Where Stable Video Diffusion stands on Freedom251
- AI video generators#1 of 242
- AI Photo Animation Tools#1 of 25
- Image-to-Video Generators#1 of 23
- Text-to-Video Generators#1 of 23