-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature] Improve AI Photo Captions with Optional Context Input or Metadata #7
Comments
As an alternative to an optional text box, it would be useful to transmit existing metadata (existing keywords, geoinformation, etc.), since it is not possible, at least in the case of Gemini, to extract this information directly from the image |
This sounds like a better plan, since it would require less user interaction while the plugin is running. And most importantly it would improve my personal workflow. ;-) |
As it turned out I tried it immediately... ;-) In the referenced git branch is a candidate that transmits the GPS coordinates from the analyzed photo to Gemini. Results vary from being astonishing specific and correct to being very general. If checking out a branch is possible for you, you might want to give it a try.. to be continued |
incredible! I have been following the development of LLMs for a long time, I believe that time is working for us here as far as the quality of the results is concerned, the development has increased massively in speed in the last 2 years |
Thanks. I added support for sending pre-existing keywords with the request. It doesn't affect the results much. |
Would it be possible to add an optional text box to the AI photo recognition process? Users could type in extra details like location names or words related to the photo's content to help the AI understand the image better. This would make the captions more accurate, especially for ambiguous images. This text box could be added either before or after the AI processes the photo, allowing users to provide context upfront or correct mistakes afterward by resending to AI.
Alternatively, the plugin could automatically extract location information from the photo's metadata, if available. This would provide context to the AI without requiring manual input from the user.
The text was updated successfully, but these errors were encountered: