How far can we go with ImageNet for Text-to-Image generation?
nicolas-dufour
Abstract
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.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation (2025)
- Augmented Conditioning Is Enough For Effective Training Image Generation (2025)
- Generating Multi-Image Synthetic Data for Text-to-Image Customization (2025)
- End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings (2025)
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling (2025)
- Decoder-Only LLMs are Better Controllers for Diffusion Models (2025)
- Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper