Skip to content

Latest commit

 

History

History
32 lines (21 loc) · 2.45 KB

config_img_srv.md

File metadata and controls

32 lines (21 loc) · 2.45 KB

Configure the Image Generation Service

This step covers how to configure the image generation service with the ComfyUI Graph generated from the previous section.

Running ComfyUI Locally as an Example Service

To quickly reproduce the demo functionalities, we have provided you with an example ComfyUI graph,latest_example.json, which you downloaded in the section ComfyUI Requirements & Installation.

  1. Import the json file into your ComfyUI.

  2. Click on Save (API Format) or in newer versions it may view as EXPORT (API) option in the Workflow Tab.

    Note: You may need to enable 'Dev mode Options' in the Settings in the bottom left corner of the screen.

  3. Export to overwrite the file located in your app at {kit-app-template/kit-streamer/source/extensions/omni.ai.viewport.core/workflows/realtime_workflow_v3.json}.



>

In the image above, we are referring to latest_workflow.json instead of latest_example.json graph. It is important to note the difference in how the image input is set up in these graphs. In the image above, the image inputs are hooked up to the nodes on right that receive image data from the Kit application.
Please do not edit this file, it is only included in the blueprint as a workflow example.

❗ If you have added/modified/removed input text nodes or image loaders, you should make corresponding changes manually to the .spec file located in your app at {kit-app-template/kit-streamer/source/extensions/omni.ai.viewport.core/workflows/realtime_workflow_v3.spec} to hook up the Kit application and the image generation service.

← Back to Guide ___________________________________________________________________________ Next (Assigning Models and References) →