AutoTagger

[Stenis]

The more I use iMatch and AutoTagger I think this is a real game changer that will take metadata editing to a whole new level.
AutoTagger and OpenAI has a great potential being flexible enough to meet almost all my expectations and demands.
On the whole it is nothing but fantastic.
With the general and specific promting together I do with AutoTagger the quality of the results it is far more than good enough for me now.

I feel it is really a great relief with iMatch and AutoTagger, since adding metadata to thousands of images is no small feat - manually - even with efficient non-AI-driven tools like PhotoMechanic.
I value my time a lot - I just turned 75 - and who knows, I might even live longer not needing to spend so much time as I do and have done on metadata management.
... and I will have far more fun too.

I will still have some use for PhotoMechanic too, because PM is still the most efficient tool to use to batch and add basic static data - for me I see them a lot as complementary.
iMatch and PhotoMechanic works perfectly together after I have complemented the Default layout in iMatch with what it was lacking for me.
So I can definitely say now that I´ll migrate to iMatch when my 30-days copy will run out and use it as my main DAM.

I´m also looking forward to use iMatch even for my Office-documents and my PDF-files.
I have long tried to convince Camera Bits to add support even for textfiles but without any success.
Now I can leave that I guess and focus on the job that needs to be done.

Exiting time it is! I love it and it is very nice to learn a few new efficient tricks!

iMatch is one more example that proves that software often these days are far more interesting for me than new cameras and lenses.
... and it gives so much more for the money I spend than more hardware I don´t really need.
Strangely enough a majority of all these photo journalists and photo entusiasts seems to be overlooking the power of great softwares.

[Mario]

I will still have some use for PhotoMechanic too, because PM is still the most efficient tool to use to batch and add basic static data - for me I see them a lot as complementary.

Have you worked with Metadata Templates and especially AutoFill yet?

Running a Metadata Template when new (or updated) files are added to the database usually takes care of the stationary data like copyright notices, legals, artist/author etc.

And with AutoFill you can fill any number of tags with any amount of data very quickly.

So I can definitely say now that I´ll migrate to iMatch when my 30-days copy will run out and use it as my main DAM.

I'm happy to hear that IMatch does what you need. GIMME you money

Strangely enough a majority of all these photo journalists and photo entusiasts seems to be overlooking the power of great softwares.

The problem is marketing and awareness. Adobe spent 2 billion (!) US$ in 2023 for marketing, sales and endorsements.
Bidding for any DAM-related keyword on Google is insanely expensive, because many big companies bid against you. Unaffordable for me.

When I write to a blogger or photo web site and ask nicely to maybe have a look at IMatch or review it, I often get no answer or just a list with prices for ads on their site back.

Sending out one (!) press release through a renowned press service can now cost up to 1,000$, and the results are meager. They typically send out 30,000 press releases per day - and a press release of IMatch is just drowned out.

I do my best to get good search engine rankings. In many cases, when users with the right profile (actually in need for a good DAM and not a toy) try out IMatch, they purchase a license.

With the general and specific promting together I do with AutoTagger the quality of the results it is far more than good enough for me now.

It might not be perfect or always right. But it's much faster than writing descriptions and keywords oneself. And we can always read and improve them, when there is time. But using AI makes our images organized and searchable from day one.

[Stenis]

I made an update.
This seems to work for me generating flat nonstructured keywords in a form that works for me.

[[-c-]] Return five to ten keywords describing this image.
Use simple English, common words, factual language.
Only single word keywords.
Singular form
No geografic data or time info as keywords.
Never add keywords with only capital letters

[Stenis]

I will still have some use for PhotoMechanic too, because PM is still the most efficient tool to use to batch and add basic static data - for me I see them a lot as complementary.

Have you worked with Metadata Templates and especially AutoFill yet?

Running a Metadata Template when new (or updated) files are added to the database usually takes care of the stationary data like copyright notices, legals, artist/author etc.

And with AutoFill you can fill any number of tags with any amount of data very quickly.

So I can definitely say now that I´ll migrate to iMatch when my 30-days copy will run out and use it as my main DAM.

I'm happy to hear that IMatch does what you need. GIMME you money

Strangely enough a majority of all these photo journalists and photo entusiasts seems to be overlooking the power of great softwares.

The problem is marketing and awareness. Adobe spent 2 billion (!) US$ in 2023 for marketing, sales and endorsements.
Bidding for any DAM-related keyword on Google is insanely expensive, because many big companies bid against you. Unaffordable for me.

When I write to a blogger or photo web site and ask nicely to maybe have a look at IMatch or review it, I often get no answer or just a list with prices for ads on their site back.

Sending out one (!) press release through a renowned press service can now cost up to 1,000$, and the results are meager. They typically send out 30,000 press releases per day - and a press release of IMatch is just drowned out.

I do my best to get good search engine rankings. In many cases, when users with the right profile (actually in need for a good DAM and not a toy) try out IMatch, they purchase a license.

With the general and specific promting together I do with AutoTagger the quality of the results it is far more than good enough for me now.

It might not be perfect or always right. But it's much faster than writing descriptions and keywords oneself. And we can always read and improve them, when there is time. But using AI makes our images organized and searchable from day one.

I have looked into using Layout Templates and that will certainly work but I see a problem with it compared to what I´m used to from PM. In PM I design a form with all elements in my forms (one for a single record at the time amd one for batching). Unlike in iMatch it is much easier in PM to get a quick overview i PM which makes it much easier to avoid mistakes and to add variables is as simple as to add the IPTC-names with brackets like {event} {country} {location} in a field and run it. No scripting needed for me at all.

It is also possible to save this whole template as so called Snapshots with all the fields where just some active (checkboxes) and that is a very effectice way to do it that suits me very well. So from what I have seen I prefer to work the way PM Plus let me. I think I will create more update mistakes with the iMatch design. I´m sure some people prefer the way iMatch is designed but for now I´m not convinced. The way I do it in PM has served me very well the last four years plus. Autofill I have to study more closely in the documentation.

Don´t worry Mario, I will throw my money on you in a few weeks!
It will be my best spent money on photo gear for years, I think.

I´m very impressed by iMatch and it is constantly growing in front of my eyes the more I see of it.
.... and I´m very impressed over that you seem to do most of it or all of it by yourself and so successful that you really can give any of the competition a very hard match and succeed in being many users first choice today. That is impressive. I can only recall one example of anything like it in Hamerick´s Vuescan that is practically a standard application today for scanning far better than the crap the scanner manufacturers have managed på come up with. For example, Epson.

I think it is a shame how reviewers of photo gear is overlooking a lot of all this magnificent photosoftware there is out there when totally focusing on hardware. Maybe the reason is that it might be more demanding to write reviews on complex softwares like iMatch than for a lot of the hardware. It is also sad with the dominance of Google but very little really to do about it and their algoritms in a short run but I see very substantial support for iMatch  outside the Adobe sphere. I have seen a surprisingly strong support among DXO Photolab enthusiasts' and other users.

I have left the Adobe sphere since more than 10 years and today I feel I also like to support the European software industry. I use Capture One (which is Danish with som Swedish capital today), DXO Photolab is French and your iMatch is German and it is also nice to say that I have chosen these three not just because they are European but because I think they are the best there is in their respective market niches for me and many others.

I don´t know how you do it but it is hard to understand that your days has just 24 hours. You manage both to develop top notch software and conducting a support that is even better than the one they provice at Camera Bits with PhotoMechanic.

Good night! :-)

[sinus]

Stenis, 
thanks for your prompts.

Very helpful. 

[Mario]

I have looked into using Layout Templates and that will certainly work but I see a problem with it compared to what I´m used to from PM. In PM I design a form with all elements in my forms (one for a single record at the time amd one for batching). Unlike in iMatch it is much easier in PM to get a quick overview i PM which makes it much easier to avoid mistakes and to add variables is as simple as to add the IPTC-names with brackets like {event} {country} {location} in a field and run it. No scripting needed for me at all.

I haven't used PM in a decade, so I don't really follow what you mean with forms and variables and stuff.
Maybe show me a screen shot or a link to some documentation. I'm pretty sure IMatch has comparable features.

The features in IMatch to automatically file in metadata are Metadata Templates. They can add metadata, change metadata, delete metadata, copy metadata, assign collections and categories. Very powerful.

You can configure IMatch to apply Metadata Templates to new files, or updated files, which usually automates most of the initial tagging and captioning work.

You can also apply Metadata Templates via Favorites and run them, by clicking them in the Favorites Panel or via a keyboard shortcut. Or add them to the File Window ribbon for even quicker access.

To maintain large chunks of stationary data (think: Copyright & Legal, Author, Complete Location records, Darwin Core metadata sets, ...) AutoFill is unbeatable. Without ever leaving the Metadata Panel you can fill the entire location block, keywords, Artist info, large chunks of other metadata with minimal effort.

I think you also posted and hijacked another thread about how Copy & Paste works in the Metadata Panel (I have moved your unrelated post to a new post where it belongs: https://www.photools.com/community/index.php/topic,14940.msg104605.html#msg104605.

The Metadata Panel offers very sophisticated features to copy metadata between files, in a controlled fashion. And you can create any number of Metadata Panel layouts (PM forms?) to fit different stages in your workflow: Metadata Panel Layouts, it even supports the complex structured in modern IPTC metadata.

[Stenis]

The problem with the iMatch way to do it in the interface is  that I can't get an overview of the whole "Default"-layout I have copied and the data it contains for the moment without clicking on each and everyone of the dataelements.

In PM this whole strukture is unfolded and open så I direct can see what will get updated and not if I run it. Not so in iMatch. Even with the transparency in PM it has happened that I have done mistakes and I just not feel comfortable as it looks in iMatch as I so far have understood it is working.

I have no problem with using PM tools if they suit me better. I use DXO Photolab generally because of the superiour image quality but PL is just sooo ineffective and cumbersome when more detail work is needed. Then Capture One is a far better choise with its smart, effective AI-driven masking tools. The same job I might spend an hour with in PL kan take just a few seconds or a minute in Capture One.

I'm very pragmatic about the tools I use. I guess I'm pretty destroyed by working with improving IT-workflows for decades as a developer. It is not more complicated than it has been to use PhotoMechanic as a photo-DAM than using the pretty simple PictureLibrary in Photolab. When scaling is needed interoperability gets really important. PM and PL also integrates totally seaamlessly in a way Capture One and other converters with specific picture import processes can't do.

Today Photolab is pretty unique working straight on the files in the file system. iMatch can in some respects not integrate as seamless as PM does with PL. In fact I personally initiated  that by asking Kirk Baker at Camera Bits to help us solve these integration problems we had earlier and it has been very timesaving for us using it.

[Mario]

The problem with the iMatch way to do it in the interface is  that I can't get an overview of the whole "Default"-layout I have copied and the data it contains for the moment without clicking on each and everyone of the dataelements.

I don't understand this. What do you mean by Default layout or data element? A screen shot perhaps?

Of course use whatever tool works best for you. I just want to make sure you're not missing some features in IMatch which would save you time.

[Stenis]

I must say it is very rewarding to experiment thoroughly with the promptings.
There is a lot to gain there.

Another thing:

I´m surprise how cheap using Open AI with GPT 40 mini - model
I started with 10 US dollar plus tax 12,50 and I have used it for a couple of thousands of pictures and I have still just used one dollar.

I did not expect it to be so reasonable.

[Mario]

This is why I describe it as very affordable in the help, even for private use
10 bucks will get you a long way. I did all my implementation and testing since July for less than 10$.

Mistral AI is quality capable, about prices the same, handles multiple input and output languages and respects the strict European privacy regulations, which makes it a good choice for European citizens and privacy-concerned people from all over the world. Well worth a try.

[Stenis]

What is your opinion of using Landmarks together with OpenAI?

[Mario]

I have no opinion, I don't really have a need for such things. Why not give it a try with a couple of dozen photos and see what you get for your photos?

[Stenis]

I have no opinion, I don't really have a need for such things. Why not give it a try with a couple of dozen photos and see what you get for your photos?

I have had a lot of help using Google Lens earlier when adding metadata to my old pictuteres from all trips I have made since 1971. I was a back-packer for 15 years and have continued travelling since then and in some cases my memory has needed som help from the Internet to recall both places and environments.

In some cases my and others pictures have become historical when earthquakes have destroyed part of towns and villages or wars. Mostly places just changes over time, so "Landmarks" can be very helpful if it works properly. Some of my main intests is architecture and urban development so I will definitely give "Landmarks" a go.

[Mario]

Google does not provide access to the AI and systems running Google Lens.
They use it as a selling point for their smart phones and to feed their AIs with fresh images and user data collected while Lens is used.

If their Gemini model has similar capabilities is unknown to me. When I tested Gemini the last time, Mistral and OpenAI were much better for image recognition.

[Stenis]

Google does not provide access to the AI and systems running Google Lens.
They use it as a selling point for their smart phones and to feed their AIs with fresh images and user data collected while Lens is used.

If their Gemini model has similar capabilities is unknown to me. When I tested Gemini the last time, Mistral and OpenAI were much better for image recognition.

I know how Google Lens works and I have no problem if they want my help traning their AI as long as I use their service. I find Google Lens very good and useful. Would be nice to know how their AI works if used like I use OpenAI now.

We are not using the most powerful variant either. Seems pretty costly too.

[Mario]

We are not using the most powerful variant either. Seems pretty costly too.

What do you mean? OpenAI?
IMatch offers the base and the more expensive vision-enabled model. OpenAI offers more model, including their recent "reasoning" models (which can be very expensive), but these are not designed to analyze images.

[Stenis]

We are not using the most powerful variant either. Seems pretty costly too.

What do you mean? OpenAI?
IMatch offers the base and the more expensive vision-enabled model. OpenAI offers more model, including their recent "reasoning" models (which can be very expensive), but these are not designed to analyze images.

Yes OpenAI.

Seeing is believing. As I said I havn't tried Open AI on birds or "Landmarks" yet. I have seen little of environment or landmark recognition using "Description" with OpenAI yet.

When I used Google Lens to identify buildings, churches and old palaces in for example Paris it was very impressive. If OpenAI would top that I would definitely be impressed

[Stenis]

I´m finished my month-long testing of iMatch and am back after a trip to Morocco. So, finally I have just got the time to purchase the sharp version of iMatch and installing it!

I have to say that it was after really testing the auto-generation of Descriptions and Keywords that I made up my mind. It will absolutely improve my work flow and its efficiency. I´m also very pleased to finally getting a modern application fully supporting both XMP and IPTC. Not every metadata tool is doing so in the very flexible way iMatch is and very few is supporting the tagging of PDF and Office-files too. My handling of PDF-files and Office-files is for the moment a real mess and I´m looking forward to do something about that too.

I´m really thrilled to be on bord at last Mario :-) and finally to get up to full speed with my work.

Thank´s a lot also for all the help I have got so far.
I really appreciate your fantastic support too!

[Mario]

Excellent. Thank you for your business. Enjoy using IMatch.

Consider telling others about IMatch. Word-of-mouth is the best marketing for small ISPs like me.

[Stenis]

I have no opinion, I don't really have a need for such things. Why not give it a try with a couple of dozen photos and see what you get for your photos?

It is good now that it is so easy to switch between OpenAI and Gemma 3 since Gemma seems a little better on Landmarks, so maybe I will try that for a while of that reason.

Gemma 3 seems to use almost the same time for every picture and I hear it puts more load on the local GPU while that is not the case with OpenAI where it varies a little more.

[Mario]

Gemma 3 seems to use almost the same time for every picture and I hear it puts more load on the local GPU while that is not the case with OpenAI where it varies a little more.

Gemma 3 runs locally on your PC and is free.
When you use OpenAI, AutoTagger sends a query and your image to OpenAI in the cloud and you pay for each request. No GPU usage in that case.

[Stenis]

I think I have landed in Open AI for now of one really important reason:

With Open AI it seems like this service really is sticking to what I instruct it to do "mandatory" in a much more predictable way than Ollama Gemma. Gemma is living more of its own life.

Here an example:

"Moscow Soviet Union 1978 - The Pravda newspaper on typical public street signs - Ingrid Agneta Sändh is shown looking at a large newspaper displayed on a pole in a public area. The newspaper is easily visible and features articles and images.

I prompted this text ad hoc: "Moscow Soviet-Union 1978 - The Pravda paper on typical public street signs" and that was exactly what I got. Gemma is running much more of its own race and doesn´t really care what should be "mandatory" text in the first row. That is important to me and really disqualifies Gemma totally.

[Mario]

Gemma is running much more of its own race and d

Just reduce the creativity, say, 40% or less to make Gemma 3 stick more to the prompt. I use creativity at 60% for great results.
Also, prompting better often helps. When you report issues with a specific model, including the actual prompt may be useful for other users to help.

Also, mind the description of this board. I repeat this here for you:

Tips for how to use AutoTagger efficiently and how to to get the best results from locally installed or cloud-based AI. Useful prompts.

Each board has such a description. This board is for giving tips and sharing prompts. Not for comparing AIs, discussing AIs not supported by IMatch etc. If you have a question, post in General Discussion and questions.

I will split this FAQ thread and move most of it into general discussions.