Hi everyone,
I’m working on a fun automation project and would love some advice on the best way to structure it in n8n.
My Goal:
I want to create a workflow that automatically removes logos from my product photos. The plan is to:
-
Grab a specific product image from Google Drive.
-
Send that image, along with a pre-made black and white “mask” image, to my local AUTOMATIC1111 server using the img2img API endpoint.
-
The API will then use the image and mask to inpaint the logo area and remove it.
My Setup:
n8n Version: 1.103.2 (Self-hosted)
Image Source: Google Drive Search/Download nodes.
API: AUTOMATIC1111 Stable Diffusion WebUI (running locally, accessed via ngrok).
My Question:
I’m not sure about the correct way to handle the two images (the main image and the mask) in the HTTP Request node . As you can see from the workflow I shared, I entered the Base64 code in the JSON. I tried following Gemini’s instructions to set this all up, it worked well up to this point, but got stuck trying to solve this issue. Thank you for any help!