Skip to content
SPECIFICTION
Get listed

Stable Video Diffusion

stability.ai

Free plan Open source APISelf-hosted
Visit stability.ai
Spec score 8.7 #32 of 242 in AI video generators

What it is

Stable Video Diffusion is a model for generating video from Stable Diffusion. It supports text-to-video and image-to-video generation, including image-based animation. The product page describes outputs of 14 or 25 frames at customizable rates from 3 to 30 frames per second, with video creation stated as taking two minutes or less. Listed model versions include 14-frame, 25-frame, and 1.1 variants. Stability AI provides self-hosting instructions that involve downloading model weights and running the reference implementation locally or on your own infrastructure. Hosted API endpoints were deprecated on July 24, 2025, and API access is unavailable. Stability AI says its foundation models are available on Amazon Bedrock and Amazon SageMaker JumpStart. The Community License is listed at free for users below $1M in annual revenue, subject to model-specific terms. Businesses above that threshold are directed to Enterprise licensing with custom pricing.

Spec sheet

What it does
Stable Video Diffusion is a Stability AI model for generating video from Stable Diffusion technology.Read 21 Oct 2026 · stability.ai
Purpose
Stable Video Diffusion is a model for generating video based on Stable Diffusion.Read 9 Oct 2026 · stability.ai
Deployment
Stability AI says Stable Video Diffusion can be deployed on your own infrastructure with a self-hosted license.Read 9 Oct 2026 · stability.ai
Free plan
YesRead 19 Sep 2026 · stability.ai
Support
The self-hosting instructions say users can create a support ticket for help setting up the model.Read 9 Oct 2026 · kb.stability.ai
Headquarters
London, United KingdomRead 28 Sep 2026 · stability.ai
API access
NoRead 19 Sep 2026 · stability.ai
API status
The hosted Stable Video API was deprecated on July 24, 2025 and its endpoints are unavailable.Read 21 Oct 2026 · kb.stability.ai
Capterra praise
The single Capterra reviewer praises realistic detailed images, the Relight feature and value for money.Read 21 Oct 2026 · capterra.com
Commercial threshold
Commercial use above USD $1M annual revenue requires an Enterprise license.Read 21 Oct 2026 · stability.ai
Commercial use
YesRead 19 Sep 2026 · stability.ai
Company founded
CB Insights lists Stability AI as founded in 2019.Read 21 Oct 2026 · cbinsights.com
Company headquarters
LinkedIn lists headquarters in Los Angeles, California.Read 21 Oct 2026 · linkedin.com
Company legal name
Crunchbase identifies the maker’s legal name as Stability AI Ltd.Read 21 Oct 2026 · crunchbase.com
Company size
LinkedIn lists Stability AI in the 51–200 employee range.Read 21 Oct 2026 · linkedin.com
Data use
The privacy policy says users can opt out of use of their Inputs and Outputs for model training through Account Settings.Read 9 Oct 2026 · stability.ai
Developer code
The public Generative-Models repository contains scripts, configs, requirements, tests and sampling utilities for local use.Read 21 Oct 2026 · github.com
Frame counts
The product page says the model can generate 14 or 25 frames.Read 21 Oct 2026 · stability.ai
Frame rates
The product page says it can generate 14 or 25 frames at customizable frame rates between 3 and 30 frames per second.Read 9 Oct 2026 · stability.ai
Frame-rate control
Frame rates can be selected from 3 through 30 frames per second.Read 21 Oct 2026 · stability.ai
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.Read 21 Oct 2026 · docs.clore.ai
Image-to-video
YesRead 19 Sep 2026 · stability.ai
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.Read 21 Oct 2026 · crfm.stanford.edu
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.Read 21 Oct 2026 · thundercompute.com
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.Read 21 Oct 2026 · thundercompute.com
Integration
Stability AI says its foundation models are available on Amazon Bedrock and Amazon SageMaker JumpStart.Read 9 Oct 2026 · stability.ai
License threshold
The license page describes Community licensing for users below $1M in annual revenue and directs businesses above that threshold to Enterprise licensing.Read 9 Oct 2026 · stability.ai
Limit: generation defects
G2 reviewers mention slow generation, malformed hands and feet, off-center compositions and incoherent text.Read 21 Oct 2026 · g2.com
Limit: missing first-party interface
A G2 reviewer says Stable Diffusion lacks its own unified user interface and relies on third-party tools.Read 21 Oct 2026 · g2.com
Limit: setup complexity
G2 reviewers report installation errors, confusing setup for ordinary users and high resource consumption.Read 21 Oct 2026 · g2.com
Model architecture
The reference implementation uses the SD 2.1 image encoder and a temporally aware deflickering decoder.Read 21 Oct 2026 · github.com
Model license
SVD 1.1 weights use Stability AI’s Community License, which permits free research, non-commercial use and limited commercial use below USD $1M annual revenue.Read 21 Oct 2026 · huggingface.co
Model variants
The reference repository describes SVD as a 14-frame image-to-video model and SVD-XT as a 25-frame finetuned variant, both at 576x1024 resolution.Read 21 Oct 2026 · github.com
Model versions
The Core Models page lists Stable Video Diffusion 14-frame, 25-frame, and 1.1 versions.Read 9 Oct 2026 · stability.ai
Notable news
Stability AI’s repository records the Stable Video Diffusion release on November 21, 2023 for research purposes.Read 21 Oct 2026 · github.com
Praise: openness and flexibility
G2 reviewers praise open-source access, local deployment, many models and interfaces, and integration into experiments.Read 21 Oct 2026 · g2.com
Praise: output quality
G2 reviewers repeatedly praise high image quality, realism, prompt results and creative usefulness.Read 21 Oct 2026 · g2.com
Privacy and security
Stability AI says it uses technical and organizational measures designed to protect personal data from loss, misuse, and unauthorized access or disclosure.Read 9 Oct 2026 · stability.ai
Processing
The product page says videos are created in 2 minutes or less.Read 9 Oct 2026 · stability.ai
Processing speed
Stability AI claims videos can be created in two minutes or less.Read 21 Oct 2026 · stability.ai
Rating on Capterra
Stable Diffusion XL listing: 5.0 out of 5 from 1 review.Read 21 Oct 2026 · capterra.com
Rating on G2
Stable Diffusion listing: 4.3 out of 5 from 10 reviews.Read 21 Oct 2026 · g2.com
Rating on Trustpilot
Stable Diffusion Online listing: 3.6 out of 5 from 29 reviews.Read 21 Oct 2026 · trustpilot.com
Repository license
The Generative-Models source repository is marked MIT licensed on GitHub.Read 21 Oct 2026 · github.com
Sampling script
The documented local inference script is generative-models/scripts/sampling/simple_video_sample.py.Read 21 Oct 2026 · kb.stability.ai
SDK and pipeline support
The Hugging Face model card provides Diffusers installation and StableVideoDiffusionPipeline examples, plus Colab and Kaggle links.Read 21 Oct 2026 · huggingface.co
Self-hosting
The official deployment option is running Stable Video Diffusion on the customer’s own infrastructure.Read 21 Oct 2026 · stability.ai
Self-hosting setup
Stability AI directs users to download SVD weights from Hugging Face and use its Generative-Models GitHub repository.Read 21 Oct 2026 · kb.stability.ai
Text-to-video
The official product page describes text-prompt video generation.Read 21 Oct 2026 · stability.ai
Trustpilot praise
Positive Trustpilot reviewers praise free access, quality and not requiring payment or an account.Read 21 Oct 2026 · trustpilot.com

Plans and prices

Community License Free Community users; listed as free; Stable Video Diffusion access is subject to model-specific license terms Read 9 Oct 2026 · stability.ai
Community self-hosted license Free Free Research, non-commercial and limited commercial use · organizations under USD $1M annual revenue Read 21 Oct 2026 · huggingface.co
Enterprise License Priced on request For enterprise, API providers, and businesses with annual revenue exceeding $1M; commercial use and implementation support; custom pricing Read 9 Oct 2026 · stability.ai
Enterprise self-hosted license Priced on request Custom Pricing Commercial use · organizations exceeding USD $1M annual revenue · implementation support Read 21 Oct 2026 · stability.ai

Every Stable Video Diffusion plan and price →

Strong points and limits

Strong points

  • Text-to-video and image-to-video generation
  • 14- or 25-frame outputs
  • Frame rates from 3 to 30 fps
  • Self-hosted deployment option
  • Commercial use listed

Limits

  • Hosted API access is unavailable
  • Self-hosting requires downloading model weights

Who it suits

Stable Video Diffusion suits developers or organizations able to run a self-hosted video model. Community licensing targets users below $1M in annual revenue, while larger businesses are directed to Enterprise licensing.

Verdict

Stable Video Diffusion provides self-hosted video generation with configurable frame counts and rates. Plan around local deployment and the applicable license tier because hosted API endpoints are no longer available.

Where Specifiction places it

Alternatives to Stable Video DiffusionAll alternatives →