What it does
An n8n workflow that downloads an image from Google Drive and runs it through several local Ollama vision models. Each model writes a detailed markdown description, and the results are saved to a Google Doc so the team can compare them. It can pull out objects, spatial relations, visible text and context.
Use cases
- 01Compare vision models on the same product photos
- 02Extract visible text and objects from images
- 03Write image descriptions into a shared document
Connects
HTTP Request · Google Drive · Google Docs