gencore/stable-diffusion-openvino repository overview

⁠Overview

A Docker command line utility to generate images based on Stable Diffusion⁠.

This Docker project is aimed at lower end computers that do not have access to a powerful graphics card (GPU) required for faster image generate. It is instead based on the OpenVINO⁠ toolkit that will work with Intel CPUs . This approach is slower than using a GPU and if you have a graphics card that can run Stable Diffusion then a different project will better suit your needs. The goal of this project is to enable image generation on lower performance computing hardware.

⁠Detail

This is a Docker project and requires Docker⁠ to be installed on your computer. In addition, the Docker image is very large at around 9GB in size. However, it contains all of the required dependencies and model files to run Stable Diffusion. No other dependencies are required.

This Docker image packages the bes-dev/stable_diffusion.openvino⁠ project and would not be possible without this project. Thanks to the developer bes-dev⁠ for creating this open source project.

⁠Example

To generate an image based on a prompt we can use the --prompt command. The following example will create an image of "kittens":

touch image.png
docker run --rm -v $PWD:/stable_diffusion.openvino/output -ti stable-diffusion-openvino:latest --output output/image.png --prompt "kittens"

Note; the Docker project runs as root for the moment and so the generated file will be owned by root. We are pre-creating the target file to avoid this issue.

We can use the --num-inference-steps command to control the number of iterations that will be used to create the image. More iterations will take more time, but will result in a more refined image.

touch image.png
docker run --rm -v $PWD:/stable_diffusion.openvino/output -ti stable-diffusion-openvino:latest --output output/image.png --num-inference-steps 50 --prompt "kittens"

⁠License

This project is licensed under Apache 2.0.

Use of this project is bound by the same restrictions as the original Stable Diffusion license⁠.

You agree not to use the Model or Derivatives of the Model:

• In any way that violates any applicable national, federal, state, local or international law or regulation.
• For the purpose of exploiting, harming or attempting to exploit or harm minors in any way.
• To generate or disseminate verifiably false information and/or content with the purpose of harming others.
• To generate or disseminate personal identifiable information that can be used to harm an individual.
• To defame, disparage or otherwise harass others.
• For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation.
• For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics.
• To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm.
• For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories.
• To provide medical advice and medical results interpretation.
• To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).