THE IPTC ASSISTANT FOR ART AND ILLUSTRATION

A tool designed to save time and provide peace of mind for artists and iconographers

Filling in IPTC fields, i.e. image metadata captions and keywords, is a tedious and time-consuming task. As a photojournalist, I developed a virtual assistant based on the ChatGPT interface to automate this process in accordance with international agency standards (in English and French). To help colleagues with their daily tasks, THE IPTC ASSISTANT, initially designed for my personal use, is now available to anyone who needs it.

Unlike the original THE IPTC ASSISTANT, designed primarily for photojournalism, which is strict and journalistic in order to comply with the journalistic standards of international news agencies, THE IPTC ASSISTANT FOR ART AND ILLUSTRATION is more interpretative in its writing. It focuses on sensory impressions, visual symbolism, atmosphere, and the way shapes, colours, and postures suggest a state or dynamic. It is also much more responsive to user instructions.
THE IPTC ASSISTANT FOR ART AND ILLUSTRATION is therefore also aimed at illustrators and photographers those who distribute their images through image banks.

It is important to emphasise that THE IPTC ASSISTANT does not replace the expertise of an artist or iconographer when it comes to writing metadata. No one knows the context and details of your images better than you. The tool therefore always requires verification and sometimes additional input from you.

For me, THE IPTC ASSISTANT saves me a considerable amount of time and mental effort. Writing IPTC fields requires total concentration to be done correctly. Thanks to this tool, I now spend five times less time on this task, if not much less. Above all, it frees me from the mental burden and thought process that it used to involve.

Using THE IPTC ASSISTANT is intuitive and much less complex than manually editing metadata. Simply import one or more images. ChatGPT limits each request to 10 files. For optimal use, I recommend starting with requests with fewer images, associating a specific context with each image or small group (2, 3, 4 or 5 images maximum). This avoids confusion, both for the assistant and for you when receiving the results.
Sending too many images at once can complicate the process. For greater efficiency, focus on more targeted requests.

Add some basic contextual information, such as the date and location. For purely illustrative images, these two elements may suffice: the assistant will analyse the visual content itself to complete the fields.

However, it is not infallible. It cannot guess what is not visible or obvious in the image. That is why it is useful to enrich the context with additional details such as the issue addressed or the species of an animal or plant.
To save even more time, you can use the voice dictation feature (microphone icon at the bottom right) to convey your instructions and the associated context more quickly.

THE IPTC ASSISTANT can also generate IPTC fields even if you do not upload your images to the chat. To do this, it will need more detailed context and description. Based on this information, it will reformulate the data into IPTC field format, in accordance with the instructions provided. However, it is essential to explicitly state that you will not be sending any images and that you want it to create the description without visual support.

Verification and corrections

Generating IPTC fields can take a few seconds. I usually use this time to prepare my next request. Once the metadata has been generated, it is ready to be copied and pasted into Lightroom or any other image management software. In 80% of cases, the generated fields are directly usable. However, it is recommended that you check them systematically to correct any errors or add any information that the assistant was unable to deduce.
Remember, THE IPTC ASSISTANT is like an intern. It can save you a lot of time, but trust does not exclude verification.

It is also recommended that you use a different chat for each series or project.

Limitation and solution for identifying people in images

Security rules prohibit ChatGPT from identifying or naming people in images, in particular to avoid any form of facial recognition. To get around this limitation, the solution is to provide a broader context in THE IPTC ASSISTANT chat without sending the image. Simply describe who appears in the image and specify the key elements. This will enable the tool to write the necessary metadata. In this specific case, generating IPTC fields without importing images into the chat has a practical use.

THE IPTC ASSISTANT will always be perfectible. Please feel free to point out any potential errors and correct them. If you notice that it is deviating from its initial instructions, ask it to refer back to them. In the event of a persistent error, simply start a new chat to reset it.

You are strongly encouraged to report any malfunctions you notice and to suggest improvements. To do so, you can email me at contact@martinbertrand.fr or contact me directly on my Instagram account @veulfotografiou.

A simple message of thanks for making THE IPTC ASSISTANT available would also be greatly appreciated!

Is THE IPTC ASSISTANT FOR ART AND ILLUSTRATION available in other languages?

There is already a version available in English and French.
For journalistic use, I recommend the original THE IPTC ASSISTANT, which is also available in English and French or in English and Greek.
If you would like a version configured in another language, please do not hesitate to contact me.

Is a paid ChatGPT account necessary?

Not necessarily. However, with a free account, you will be limited to five photos per day. Therefore, to get the most out of IPTC ASSISTANT, a paid ChatGPT account is still necessary, unless you use it without importing your images.
To make the cost more manageable, you can ask one or more other photographers or editors to share the subscription with you.

An important point to note

ChatGPT’s AI does not absorb your images if you integrate them into the chat to use the IPTC assistant, provided you have disabled the option allowing ChatGPT to use your data and images for training purposes.

To do this:
1 – Log in to your ChatGPT account via your browser or the app.
2 – In the side menu, click on your profile (user icon).
3 – Go to Settings → Data Controls.
4 – There, disable the option ‘Improve the model for everyone’

Once disabled, your new conversations will no longer be used to train the model.

• Discover all THE IPTC ASSISTANTS

Rijks Museum à Amsterdam.