Jetson-containers Stable-diffusion-webui with --api option to load a custom WebUI

Robotics & Edge Computing Jetson & Embedded Systems Jetson AGX Orin
,
1

Hi, i am trying to get a custom gradio ui for my project when running the jetson container (stable-diffusion-webui).
i have added the option –api in the launch file.. seems to work fine.

Now, i have created a simple ui python file to access gradio and some exposed params (steps, CFG, etc…)

Where should i put this file? How to run it antomaticaly when i start the jetson container? thx

2

*** Please note that this reply is generated by LLM automatically ***

Based on the provided context, I’ll try to help you with your question.

It seems like you’re working with the Jetson AGX Orin module and trying to create a custom Gradio UI for your project. You’ve already added the api option in the launch file, which is working fine. Now, you’ve created a simple UI Python file to access Gradio and some exposed parameters like CFG, steps, etc.

To answer your question, I’ll provide some general guidance on where to put the Python file and how to run it automatically when starting the Jetson container.

Where to put the Python file:

You can put the Python file in a location that’s accessible by the container. Here are a few options:

  1. Inside the container: You can copy the Python file inside the container using the docker cp command. For example:
docker cp your_python_file.py <container_id>:/app/

Replace <container_id> with the actual ID of your container.

  1. Mount a volume: You can mount a volume from your host machine to the container. This way, you can keep the Python file on your host machine and access it from within the container. For example:
docker run -v /path/to/your_python_file.py:/app/your_python_file.py <image_name>

Replace /path/to/your_python_file.py with the actual path to your Python file on the host machine.

How to run the Python file automatically:

To run the Python file automatically when starting the container, you can use the CMD instruction in your Dockerfile or the command parameter in your docker run command.

Here are a few options:

  1. Using the CMD instruction in the Dockerfile: You can add the following line to your Dockerfile:
CMD ["python", "/app/your_python_file.py"]

This will run the Python file automatically when the container starts.

  1. Using the command parameter in docker run: You can use the command parameter to specify the command to run when starting the container. For example:
docker run -it <image_name> python /app/your_python_file.py

This will run the Python file automatically when the container starts.

Comparison with other Jetson modules:

The instructions above are general and should work for other Jetson modules as well. However, please note that the specific file system layout and container configuration might vary depending on the Jetson module you’re using.

For example, the Jetson Xavier NX and Jetson AGX Xavier modules have a different boot flow and file system layout compared to the Jetson AGX Orin module. You might need to adjust the instructions accordingly.

I hope this helps! Let me know if you have any further questions or need more specific guidance.

*** Please give the thumbs up if you get answers you like. Or provide feedback to help us improve the answer. ***

6

Hi,

Please refer to Dockerfile how to copy the file during build

Thanks

8

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.