AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method

Social media content creators find it hard to make thumbnails shine on Instagram, YouTube, and TikTok, where graphic design skills happen to be a significant bottleneck. To address this issue, scientists developed a text-based image generation model, PotionPix, that allows users to generate thumbna...

Full description

Saved in:
Bibliographic Details
Main Authors: Meivi Kartikasari, Hashfi Andira Putra, Mukhlis Amien
Format: Article
Language:English
Published: Center for Research and Community Service, Institut Informatika Indonesia Surabaya 2025-07-01
Series:Teknika
Subjects:
Online Access:https://ejournal.ikado.ac.id/index.php/teknika/article/view/1215
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849707265633812480
author Meivi Kartikasari
Hashfi Andira Putra
Mukhlis Amien
author_facet Meivi Kartikasari
Hashfi Andira Putra
Mukhlis Amien
author_sort Meivi Kartikasari
collection DOAJ
description Social media content creators find it hard to make thumbnails shine on Instagram, YouTube, and TikTok, where graphic design skills happen to be a significant bottleneck. To address this issue, scientists developed a text-based image generation model, PotionPix, that allows users to generate thumbnails on the fly based on text prompts and relevant images via a "Stacked ID Embedding" method. This method combines multiple identity embeddings—e.g., user interests, platform context, and content genre—into one vector representation to guide the AI to create more personalized and contextually appealing thumbnails. The system integrates a diffusion-based image generator with the stacked embedding vectors to enable dynamic adaptation to different user intents. In tests, it was observed that how relevant and good the generated thumbnails were very much a function of how specific the input image was and how clear the prompt was. However, since the AI model used was not fine-tuned on the task of thumbnail generation specifically, the visual outputs sometimes were generic and lacked the strong call-to-action elements usually found in high-performing thumbnails. Despite this constraint, the usability test conducted with 120 respondents showed promising results—83.8% of the participants confirmed that PotionPix was indeed assistive in the thumbnail design process, particularly in terms of time and effort savings. The findings show the promise of AI-driven tools in enabling the democratization of design tasks for social media content creators, as well as suggesting future work in model fine-tuning for more domain-specific outcome.
format Article
id doaj-art-c9c9cb6f46f2450281b45cdbe9fdfdd8
institution DOAJ
issn 2549-8037
2549-8045
language English
publishDate 2025-07-01
publisher Center for Research and Community Service, Institut Informatika Indonesia Surabaya
record_format Article
series Teknika
spelling doaj-art-c9c9cb6f46f2450281b45cdbe9fdfdd82025-08-20T03:15:57ZengCenter for Research and Community Service, Institut Informatika Indonesia SurabayaTeknika2549-80372549-80452025-07-0114210.34148/teknika.v14i2.1215AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding MethodMeivi KartikasariHashfi Andira PutraMukhlis Amien Social media content creators find it hard to make thumbnails shine on Instagram, YouTube, and TikTok, where graphic design skills happen to be a significant bottleneck. To address this issue, scientists developed a text-based image generation model, PotionPix, that allows users to generate thumbnails on the fly based on text prompts and relevant images via a "Stacked ID Embedding" method. This method combines multiple identity embeddings—e.g., user interests, platform context, and content genre—into one vector representation to guide the AI to create more personalized and contextually appealing thumbnails. The system integrates a diffusion-based image generator with the stacked embedding vectors to enable dynamic adaptation to different user intents. In tests, it was observed that how relevant and good the generated thumbnails were very much a function of how specific the input image was and how clear the prompt was. However, since the AI model used was not fine-tuned on the task of thumbnail generation specifically, the visual outputs sometimes were generic and lacked the strong call-to-action elements usually found in high-performing thumbnails. Despite this constraint, the usability test conducted with 120 respondents showed promising results—83.8% of the participants confirmed that PotionPix was indeed assistive in the thumbnail design process, particularly in terms of time and effort savings. The findings show the promise of AI-driven tools in enabling the democratization of design tasks for social media content creators, as well as suggesting future work in model fine-tuning for more domain-specific outcome. https://ejournal.ikado.ac.id/index.php/teknika/article/view/1215ThumbnailStacked ID EmbeddingArtificial IntelligenceContent CreatorText-to-image Generation
spellingShingle Meivi Kartikasari
Hashfi Andira Putra
Mukhlis Amien
AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
Teknika
Thumbnail
Stacked ID Embedding
Artificial Intelligence
Content Creator
Text-to-image Generation
title AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
title_full AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
title_fullStr AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
title_full_unstemmed AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
title_short AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
title_sort ai based personalization of social media thumbnails using the stacked id embedding method
topic Thumbnail
Stacked ID Embedding
Artificial Intelligence
Content Creator
Text-to-image Generation
url https://ejournal.ikado.ac.id/index.php/teknika/article/view/1215
work_keys_str_mv AT meivikartikasari aibasedpersonalizationofsocialmediathumbnailsusingthestackedidembeddingmethod
AT hashfiandiraputra aibasedpersonalizationofsocialmediathumbnailsusingthestackedidembeddingmethod
AT mukhlisamien aibasedpersonalizationofsocialmediathumbnailsusingthestackedidembeddingmethod