STUDI KASUS PENGGUNAAN KECERDASAN BUATAN DALAM PEMBUATAN GAMBAR DIGITAL: ANALISIS KEMAMPUAN DAN KETERBATASAN MODEL GENERATIF ARTIFICIAL INTELLIGENCE
DOI:
https://doi.org/10.31849/784v0g58Keywords:
Generative AI, Stable Diffusion, Dall-E, Leonardo AI, Mufa.AIAbstract
Perkembangan teknologi Generative Artificial Intelligence (AI) telah membuka peluang bagi proses pembuatan gambar digital berbasis teks (text-to-image) untuk dilakukan secara otomatis dengan kualitas visual yang terus meningkat. Berbagai model AI seperti DALL·E 2, Nano Banana, dan Stable Diffusion masing-masing memiliki karakteristik yang berbeda dalam menghasilkan gambar berdasarkan masukan teks prompt. Penelitian ini bertujuan untuk menganalisis kemampuan dan keterbatasan model mufa.ai melalui studi komparatif dengan DALL·E 2, Nano Banana, dan Stable Diffusion, sekaligus mengkaji implementasinya pada platform berbasis web. Penelitian ini menggunakan metode deskriptif komparatif dengan cara menguji setiap model AI menggunakan sejumlah prompt yang sama. Gambar yang dihasilkan kemudian dianalisis berdasarkan lima indikator dengan menggunakan skala Likert 1–5. Model mufa.ai diimplementasikan ke dalam platform web melalui integrasi API Hugging Face, sehingga sistem mampu menghasilkan gambar digital secara otomatis melalui antarmuka berbasis web. Hasil penelitian mengidentifikasi bahwa model mufa.ai unggul pada aspek visual quality dan aesthetic, serta memiliki keselarasan prompt yang sebanding dengan model benchmark, namun masih memiliki keterbatasan pada konsistensi dan orisinalitas.
References
[1] L. Yang et al., “Diffusion Models: A Comprehensive Survey of Methods and Applications,” ACM Comput. Surv., vol. 56, no. 4, 2024, doi: 10.1145/3626235.
[2] J. Cho, A. Zala, and M. Bansal, “DALL-EVAL: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models,” in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, Oct. 2023, pp. 3020–3031. doi: 10.1109/ICCV51070.2023.00283.
[3] F. Bie et al., “RenAIssance: A Survey Into AI Text-to-Image Generation in the Era of Large Model,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 3, pp. 2212–2231, Mar. 2025, doi: 10.1109/TPAMI.2024.3522305.
[4] T. Wolf et al., “Transformers : State-of-the-Art Natural Language Processing,” pp. 38–45, 2020.
[5] “No Title”, doi: doi.org/10.48550/arXiv.2204.06125.
[6] R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2022, pp. 10674–10685. doi: 10.1109/CVPR52688.2022.01042.
[7] “No Title”, doi: doi.org/10.48550/arXiv.2006.11239.
[8] Gemini Team et al., “Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context,” pp. 1–154, 2024, [Online]. Available: http://arxiv.org/abs/2403.05530
[9] B. Biggs et al., “Diffusion Soup: Model Merging for Text-to-Image Diffusion Models,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) , vol. 15121 LNCS, pp. 257–274, 2025, doi: 10.1007/978-3-031-73036-8_15.
[10] T. Wolf et al., “Transformers: State-of-the-Art Natural Language Processing,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Stroudsburg, PA, USA: Association for Computational Linguistics, 2020, pp. 38–45. doi: 10.18653/v1/2020.emnlp-demos.6.
[11] S. Amershi et al., “Guidelines for Human-AI Interaction,” p. 9, 2019.
[12] Y. Tian, Y. Liu, S. Wang, and S. Kwong, “Quality Assessment for Text-to-Image Generation: A Survey,” IEEE Multimed., vol. 32, no. 2, pp. 44–52, 2025, doi: 10.1109/MMUL.2025.3538862.
[13] K. Huang, C. Duan, K. Sun, E. Xie, Z. Li, and X. Liu, “T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 5, pp. 3563–3579, 2025, doi: 10.1109/TPAMI.2025.3531907.
[14] L. South, D. Saffo, O. Vitek, C. Dunne, and M. A. Borkin, “Effective Use of Likert Scales in Visualization Evaluations: A Systematic Review,” Comput. Graph. Forum, vol. 41, no. 3, pp. 43–55, Jun. 2022, doi: 10.1111/cgf.14521.
[15] M. Bervar, T. Bertoncel, and M. Pejić Bach, “Generative Artificial Intelligence and the Creative Industries: A Bibliometric Review and Research Agenda,” Systems, vol. 14, no. 2, pp. 1–25, 2026, doi : 10.3390/systems14020138.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ZONAsi: Jurnal Sistem Informasi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
CC BY-SA 4.0
Attribution-ShareAlike 4.0
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
