Nepotistically Trained Generative Image Models Collapse
Abstract
Trained on massive amounts of human-generated content, AI-generated image synthesis is capable of reproducing semantically coherent images that match the visual appearance of its training data. We show that when retrained on even small amounts of their own creation, these generative-AI models produce highly distorted images. We also show that this distortion extends beyond the text prompts used in retraining, and that once affected, the models struggle to fully heal even after retraining on only real images.
Cite
Text
Bohacek and Farid. "Nepotistically Trained Generative Image Models Collapse." ICLR 2025 Workshops: Data_Problems, 2025.Markdown
[Bohacek and Farid. "Nepotistically Trained Generative Image Models Collapse." ICLR 2025 Workshops: Data_Problems, 2025.](https://mlanthology.org/iclrw/2025/bohacek2025iclrw-nepotistically/)BibTeX
@inproceedings{bohacek2025iclrw-nepotistically,
title = {{Nepotistically Trained Generative Image Models Collapse}},
author = {Bohacek, Maty and Farid, Hany},
booktitle = {ICLR 2025 Workshops: Data_Problems},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/bohacek2025iclrw-nepotistically/}
}