Wanted to share my work on containerizing/templating SVD deployment for runpod.io instances (or your local machine, does not matter)
Here's a Dockerhub image, it has all of the dependencies required to run SVD and automatically downloads the weights to /workspace directory if it can not find them there, you need to mount a directory there.
latest or svd-base-xt tag auto-downloads both models, if you only want a specific model use svd-base/svd-xt tags respectively
Wanted to share my work on containerizing/templating SVD deployment for runpod.io instances (or your local machine, does not matter)
Here's a Dockerhub image, it has all of the dependencies required to run SVD and automatically downloads the weights to /workspace directory if it can not find them there, you need to mount a directory there.
latest
orsvd-base-xt
tag auto-downloads both models, if you only want a specific model usesvd-base
/svd-xt
tags respectivelyhttps://hub.docker.com/repository/docker/mnb3000/runpod-stable-video-diffusion/ https://github.com/mnb3000/runpod-stable-video-diffusion
Detailed README with documentation/examples available on both Dockerhub/GitHub.
And here are automatic preconfigured templates for runpod instances:
Streamlit UI is available on port 3000 (configurable with
$PORT
env var) SVD-XT runs fine on RTX A6000 instances for $0.8/hr with discrete_t set to 8