Share Examples?

[Mario]

I would be great to see some examples of results you produced with AutoTagger, including

• a small version of the image
• the AI used
• your prompt
• your results (keywords, description, landmarks, traits)

Most people, me included, learn best from examples, and if you are satisfied with your AutoTagger results, let others know how you did it.
Note: Please do not upload images of persons, or blur their faces before uploading.

[Jingo]

Great idea!

Here is mine: 


OpenAI Prompts:

Description prompt:

[[-c-]] Describe this image in a style to make it easily searchable. Use simple English, common words, factual language, and simple sentences.
Avoid describing anything not directly observable from the image.
{File.MD.city|hasvalue:This image was taken in {File.MD.city},}{File.MD.country|hasvalue: {File.MD.country}.}

Keyword prompt:

[[-c-]] Return ten to fifteen keywords describing this image.
{File.MD.hierarchicalkeywords|hasvalue:This image has the following keywords: {File.MD.hierarchicalkeywords}.}


Results:

AI Description:
This image shows a white-throated sparrow on the ground among leaves. The bird has brown and gray feathers, with a distinctive striped head. It is in a natural outdoor setting, surrounded by fallen leaves. The sparrow appears to be foraging for food.

AI Keywords:
AI|American Sparrow; AI|Brown Feathers; AI|Foraging; AI|Ground; AI|Songbird; AI|Striped Head; Animals|Bird; Animals|Bird|White-throated Sparrow; colorful; Habitat; Objects|Leaves; outdoors; Places|Nature; small bird; wildlife

I haven't yet set up 1:1 keywords mapping for some of the returned hierarchical keywords.. but will be doing that next.

[Stenis]

Thanks for your input Jingo and god to have an explicit headline for the prompt examples Mario. I´ll contribute a little later.

One thing I didn´t understand is this:

{File.MD.city|hasvalue:This image was taken in {File.MD.city},}{File.MD.country|hasvalue: {File.MD.country}.}

Were there no data in these "Location"-elements of yours?

[Mario]

One thing I didn´t understand is this:

{File.MD.city|hasvalue:This image was taken in {File.MD.city},}{File.MD.country|hasvalue: {File.MD.country}.}

Were there no data in these "Location"-elements of yours?

This variable checks if the city tag has a value. If yes, it outputs something like "This image was taken in London, United Kingdom". If there is no city value, the variable outputs nothing.

Not all files in a database may have location data when the prompt runs. The hasvalue check ensures that the phrase is only added to the prompt when there is data.

[Stenis]

Thanks for your reply Mario.

Below you can see my basic "static configuration" I have landed in for now and a few F7 prompt examples



I use all three static prompts the "Description", "Keyword" and "Landmark" now and never changes that data.
Landmarks are written (if they are found) to merge with the data in "Description" with a variable.
I always use flat keywords
I even think the "Landmark" works surprisingly well :-)

One other important condition for my workflow is that I still use PhotoMechanic to batch update about 20 data-elements in iMatch.
For me it is much faster than doing it in iMatch.
AutoTagger updates the "Description" and "Keyword"-elements with AI.
Compared to my earlier process, this is extremely much faster and fare more efficient due to I don´t have to write descriptions manually. It is like a stone has fallen from my shoulders and work has got so much easier.

I just have to read the ready-made texts now and adjust a few things sometimes but most of the time it is much more than good enough as it is
I´m also very happy with the job OpenAI is doing there in the background.
What a change this has brought to my processes!
It feels like getting a whole new photo archiving life!

Fantastic job you have done Mario!
I was afraid the system should be Beta and not flexible enough but it really is very well engineered and solid already.
Frankly, I did not really expect that I think and am glad I´m proven wrong.



At Description prompt (static)

[[-c-]]
Always priority for gepgrafic data, the year and peoples names.
Always write text inside quotes but without the quote signs.
Describe this image in a style to make it easily searchable.
Use simple English, common words, factual language, and simple sentences.
Avoid describing anything not directly observable from the image.
Write the geografic data and year in the beginning of the text together with names



At Keyword prompt (static) (Presumption: Only non-hierarchic keywords)

[[-c-]]
Keywords never in plural form
Return five to seven keywords describing this image.
Use simple English, common words, factual language.
Max one word in each keyword.
No geografic data or time info as keywords.
No words with only capital letters.


At Landmark prompt (static) (Presumption: Merge with existing target (Description) values

[[-c-]] Return the names of known landmarks and tourist spots in this image to  {File.MD.description}
If you cannot detect any landmarks or tourist spots, return ''.



At the F7-prompt (non-static)

Template

Keywords never in plural form
Always write text inside quotes but without the quote signs.

Mandatory text: "Place Country Year" - "motif"
In foreground "Name"


Examples


1.

Keywords never in plural form
Always write text inside quotes but without the quote signs.

Mandatory text: Essaouria Morocco 2025 -
"Essaouria Fishing Harbor"

2.

Keywords never in plural form
Always write text inside quotes but without the quote signs.

Mandatory text: Eze Sur Mer Provence France 2012 -
"Bye the sea"
Ingrid Sändh in the foreground

[Mario]

To attach files, use the Attach command available bellow the full post editor. If you use Quick Reply instead, click "Preview" once to see all controls for adding attachments.
Copying and pasting images from somewhere does not work.