How far can we go with ImageNet for Text-to-Image generation?

Lucas Degeorge, Arijit Ghosh, Nicolas Dufour, D. Picard, V. Kalogeiton

How far can we go with ImageNet for Text-to-Image generation?: 26 upvotes on Hugging Face Daily Papers, #5 of 18 papers on 2025-03-03. Day-by-day upvote history.

Recent text-to-image (T2I) generation models have achieved remarkable results by training on billion-scale datasets, following a `bigger is better' paradigm that prioritizes data quantity over quality. We challenge this established paradigm by demonstrating that strategic data augmentation of small, well-curated datasets can match or outperform models trained on massive web-scraped collections. Using only ImageNet enhanced with well-designed text and image augmentations, we achieve a +2 overall score over SD-XL on GenEval and +5 on DPGBench while using just 1/10th the parameters and 1/1000th the training images. Our results suggest that strategic data augmentation, rather than massive datasets, could offer a more sustainable path forward for T2I generation.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.