Personalized Postcard Designs with Generative AI

15

October

2023

4/5 (1)

Generative AI has immense potential to hyper-personalize many day-to-day applications since it is trained on vast amounts of data. Therefore, it can generate highly accurate and precise recommendations tailored to the individual, that can be further refined by prompting with more specific details. Personalized news based on preferences and interests, education based on learning style, customized chatbots (Dalghan, 2023) or personalized marketing are just a few examples of this (White, 2023).

I enjoy collecting postcards from places I visit. However, there have been a few places where I forgot to purchase a postcard as a memory. Although the act of purchasing it physically and abroad is the most memorable, creating one myself is better than nothing. Additionally, my hope is that I can generate a postcard that really matches with my experience and vibe of the city, as many postcards are very generic and show touristy hotspots that I might have not even visited.

To start off, I prompted to create a design of a postcard with a Christmas market in Düsseldorf using AppyPie (AppyPie, 2023) as I know very well how it looks like.

“Create a postcard image of Duesseldorf in Germany during Christmas season, showing a Christmas market”.

The image gets very close to the original, since I do not include that many details. The next step is to get very specific:

Create a postcard image of Duesseldorf in Germany during Christmas season, showing the Christmas market with an ice skating rink and mulled wine glasses”

The feeling is still matching to the reality but it seems like the ice rink and mulled wine glasses were too specific. Leaving out the ice rink this is the result, which is a great representation:

Another example:

“Create a postcard image of the han river in seoul with beer and fried chicken”

The picture of the Han River actually matches with the exact spot that I was visiting, giving a very nostalgic feeling. Neither the fried chicken nor the beer can be seen, which is a typical activity at the river in the summer. Rephrasing it resulted in this:

Specifying the atmosphere resulted in this prompt and image:

“Create a postcard image of the han river in seoul with a box of fried chicken and a bottle of beer with a darker romantic atmosphere”

This picture really reminds me of the time in Seoul when I was at the Han river. When I was in Seoul looking for postcards I did not remember seeing anything like that, personalized with fried chicken and beer. These experiments show that postcards can be designed very closely to the consumers preferences and help with niches albeit with some prompt engineering. Currently such features are not easily accessible as most of them are subscription-based.

Hyper-personalization with generative AI, useful in these scenarios, can possibly create ideological echo chambers and feedback loops, even more than social media nowadays (White, 2023). Biases can be reinforced, diverse viewpoints could be reduced due to the creation of a “filter bubble” and human touch could be lost, as recommendations and creation becomes mostly algorithm-driven and lacks personal touch from human interaction. Therefore it is very important to keep the human component involved in the decision-making process, so that the human can monitor the output and interfere if problems like biases arise e.g. during personalized marketing.

References

AppyPie. (2023). Retrieved from https://www.appypie.com/design/poster/maker

Dalghan, A. (2023). Retrieved from https://www.linkedin.com/pulse/5-practical-use-cases-generative-ai-everyday-office-work-alaa-dalghan/

White, M. (2023). Retrieved from https://matthewdwhite.medium.com/generative-ais-killer-app-hyper-personalization-ce24e77417a9

Please rate this

Hands-On Exploration of Deepfake Detection and Generation

9

October

2023

No ratings yet.

Generative AI has proven to be very effective in supporting a person’s everyday life but also in professional life by making vast amounts of knowledge easily digestible and summarized, e.g. with ChatGPT. Besides the known grave dangers like algorithmic bias, lack of transparency and accountability, Deepfakes have been addressed less lately even though there have been very realistic ones like with Morgan Freeman that created a large commotion.

A lot of research has focused on the detection of Deepfakes, with a few websites freely accessible online. Testing out the Deepware detector with a (from human eye perspective) worse deepfake and the well-known Morgan Freeman, the difference in quality is immediately visible:

The deepfake with Elon Musk (Deepware, 2023) is recognized with a high confidence with just one model, while for the deepfake of Morgan Freeman (Deepware, 2023) 5 models are used for detection with only one recognizing it as a deepfake.

Through the evolution of easily accessible Generative Adversarial Networks (GANs) deepfakes often are created with the intention to deceive or to spread misinformation and possibly conduct financial frauds. Their largest influence lies in social media as audio-visual content is most easily spread on these platforms. This could lead to an “infocalypse” (Westerlund, 2019), which would mean that people could only trust their own close social network including friends and family that reinforce the already existing beliefs. Deepfakes that align with the own view even though fake would seem more realistic.

Deepfake videos in particular can be categorized according to into the types i) face-swap, ii) lip-synching, iii) puppet-master, iv) face synthesis and v) audio-only (Masood, 2022) .

In this experiment, I tried to create a deepfake of Donald Trump stating something that he usually would not do. For this, first an audio-only deepfake is created and then using lip-synching matched with an image to create a video.

First, using ChatGPT I phrased a statement that would be unusual for Donald Trump to say.

Afterwards, I explored many different platforms and options to create Donald Trumps voice. One option was to train a TTS (Text-to-speech) voice cloner (Vocloner, 2023) with some audio data found on Kaggle.

Result:

The result was not very convincing, which is why other tools were explored. Fineshare, also a free voice changer website resulted in a poor audio as well. Speechify which is a common tool required a premium subscription for cloning voices that are not recorded by oneself.

Lastly, I used the website FakeYou and found a TTS model pre-trained (FakeYou, 2023) to generate the audio, which resulted in a much better audio. This shows that a more sophisticated and pre-trained model allows for better Deepfakes. With the lip sync function (FakeYou, 2023) an image and the audio of Donald Trump is merged to create a Deepfake.

This free Deepfake detector (Deepware, 2023) did not manage to flag this video as a Deepfake. This shows that detection is still a large problem, although Deepfake detection ideally should be integrated into any social media content post. Only this way I can see how social media is prevented from being flooded with Deepfakes. Having at least a system in place that can show the confidence with which a video is or is not identified as a Deepfake would help a lot, so that users are more aware of the informational value of the content. Social media platforms in context of AI Ethics must bear responsibility to protect the users from misinformation.

Finally, even though Deepfakes are mostly associated negatively, there are many constructive uses. One could be creating personalized and engaging content for Marketing purposes, depending on the user’s data and preferences different influencers can be used to endorse a product specifically for the viewer. It will be easier to create advertising campaigns without the influencers being present and ready. This even has the potential to disrupt how Marketing is done, as this is much more flexible, user-oriented, and possibly cheaper.

Where do you see opportunities for Deepfake? What do you think about its potential impact on social media and what do you think needs to happen to prevent malicious spread and use of Deepfakes?

References

Deepware. (2023). Retrieved from https://scanner.deepware.ai/result/edd37447f779cfc58f48b545f663184d3f6f21ef-1589885916/

Deepware. (2023). Retrieved from https://scanner.deepware.ai/result/2a6115c760da36ee44d757d9105eb1ba4fd66b9f-1629834054/

Deepware. (2023). Retrieved from https://scanner.deepware.ai/result/c53071331497a1da41e8a2b30506342a476c666d-1696428314/?

FakeYou. (2023). Retrieved from https://fakeyou.com/tts/TM:03690khwpsbz

FakeYou. (2023). Retrieved from https://fakeyou.com/face-animation

Masood, M. (2022). Retrieved from https://link.springer.com/article/10.1007/s10489-022-03766-z

Vocloner. (2023). Retrieved from https://vocloner.com/

Westerlund, M. (2019). Retrieved from https://timreview.ca/sites/default/files/article_PDF/TIMReview_November2019%20-%20D%20-%20Final.pdf

Please rate this