AI Image Captioning Workflow with DeepSeek API - Help for a Newbie

Help me Build my Workflow
1

Hello n8n community!

I’m new to n8n and trying to create a workflow that does the following:

  1. Takes an image input from a user
  2. Sends it to an AI for processing
  3. Gets back a caption for that image
  4. Specifically using the DeepSeek API

Is this possible in n8n? My knowledge about n8n tools is very limited, so I’m not sure which nodes or components I should be using for this kind of workflow.

If this is doable, could someone guide me through the basic steps or components I’d need to set up? Even just pointing me to the right nodes would be extremely helpful.

I’m completely new to this, so any beginner-friendly tips or examples would be greatly appreciated!

Thanks in advance,

2

This is an example of what you need.
Check if deepseek API are able to do image processing

3

Thank you. I will try it.

Update: There is an error when resize the image:

n8n version

1.85.4 (Self Hosted) Using npm install method

Stack trace

Error: Stream yields empty buffer at Socket.<anonymous> (/root/.nvm/versions/node/v20.18.0/lib/node_modules/n8n/node_modules/gm/lib/command.js:56:21) at Socket.emit (node:events:531:35) at endReadableNT (node:internal/streams/readable:1696:12) at processTicksAndRejections (node:internal/process/task_queues:82:21)

Log in pm2:
0|n8n | Could not execute GraphicsMagick/ImageMagick: gm “identify” “-ping” “-verbose” “-” this most likely means the gm/convert binaries can’t be found

Do you know how to fix this? Thanks

UPDATE:

Thanks its working after install GraphicsMagick in my server

1 Like
4

Glad to read that.

If my message helped, plead add “solved” status.