- Home
- AI video generators
- Stable Video Diffusion
Stable Video Diffusion
Stable Video Diffusion · London, United Kingdom · founded 2019
What it is
Stable Video Diffusion is a model for generating video from Stable Diffusion. It supports text-to-video and image-to-video creation, including image animation, and is offered for self-hosted deployment. The model generates 14 or 25 frames at customizable rates from 3 to 30 frames per second; the product page says videos are created in two minutes or less. Listed model versions include 14-frame, 25-frame, and 1.1 releases. Stability AI’s instructions describe downloading model weights and running the reference implementation locally on your own infrastructure. Hosted Stable Video Diffusion API endpoints were deprecated on July 24, 2025, and API access is unavailable. Stability AI also lists its foundation models on Amazon Bedrock and Amazon SageMaker JumpStart. Community licensing is free for users below $1M in annual revenue, subject to model-specific terms. Businesses above that threshold are directed to an Enterprise License with custom pricing, commercial use, and implementation support.
For and against
For
- Supports text-to-video generation
- Supports image-to-video animation
- Customizable 3–30 frames-per-second rates
- Self-hosted deployment option
- Free Community License below $1M revenue
Against
- Hosted API endpoints are unavailable
- Self-hosting requires local model setup
- License terms vary by model
The verdict
Stable Video Diffusion provides configurable text- and image-driven video generation for self-hosted environments. Users should plan around unavailable hosted APIs and select Community or Enterprise licensing based on revenue and use.
Who it suits
Stable Video Diffusion suits developers and organizations able to run a self-hosted video model. Licensing depends on annual revenue and the intended commercial use.
Plans and prices
Community self-hosted license
Research, non-commercial and limited commercial use · organizations under USD $1M annual revenue
Read 21 Oct 2026 · huggingface.co
Community License
Community users; listed as free; Stable Video Diffusion access is subject to model-specific license terms
Read 9 Oct 2026 · stability.ai
Enterprise self-hosted license
Commercial use · organizations exceeding USD $1M annual revenue · implementation support
Read 21 Oct 2026 · stability.ai
Enterprise License
For enterprise, API providers, and businesses with annual revenue exceeding $1M; commercial use and implementation support; custom pricing
Read 9 Oct 2026 · stability.ai
On the record
- API access
- Nostability.ai · read 19 Sep 2026
- API status
- The hosted Stable Video API was deprecated on July 24, 2025 and its endpoints are unavailable.kb.stability.ai · read 21 Oct 2026
- Capterra praise
- The single Capterra reviewer praises realistic detailed images, the Relight feature and value for money.capterra.com · read 21 Oct 2026
- Commercial threshold
- Commercial use above USD $1M annual revenue requires an Enterprise license.stability.ai · read 21 Oct 2026
- Commercial use
- Yesstability.ai · read 19 Sep 2026
- Company founded
- CB Insights lists Stability AI as founded in 2019.cbinsights.com · read 21 Oct 2026
- Company headquarters
- LinkedIn lists headquarters in Los Angeles, California.linkedin.com · read 21 Oct 2026
- Company legal name
- Crunchbase identifies the maker’s legal name as Stability AI Ltd.crunchbase.com · read 21 Oct 2026
- Company size
- LinkedIn lists Stability AI in the 51–200 employee range.linkedin.com · read 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 · read 9 Oct 2026
- Deployment
- Stability AI says Stable Video Diffusion can be deployed on your own infrastructure with a self-hosted license.stability.ai · read 9 Oct 2026
- Developer code
- The public Generative-Models repository contains scripts, configs, requirements, tests and sampling utilities for local use.github.com · read 21 Oct 2026
- Frame counts
- The product page says the model can generate 14 or 25 frames.stability.ai · read 21 Oct 2026
- Frame-rate control
- Frame rates can be selected from 3 through 30 frames per second.stability.ai · read 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 · read 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.docs.clore.ai · read 21 Oct 2026
- Image-to-video
- Yesstability.ai · read 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.crfm.stanford.edu · read 21 Oct 2026
