Authors
- Vikash Sehwag
- Xianghao Kong
- Jingtao Li
- Michael Spranger
- Lingjuan Lyu
Venue
- CVPR-25
Date
- 2025
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
Xianghao Kong
Jingtao Li
CVPR-25
2025
Abstract
As scaling laws in generative AI push performance, they simultaneously concentrate the development of these models among actors with large computational resources. With a focus on text-to-image (T2I) generative models, we aim to unlock this bottleneck by demonstrating very low-cost training of large-scale T2I diffusion transformer models. As the computational cost of transformers increases with the number of patches in each image, we propose randomly masking up to 75% of the image patches during training. We propose a deferred masking strategy that preprocesses all patches using a patch-mixer before masking, thus significantly reducing the performance degradation with masking, making it superior to model downscaling in reducing computational cost. We also incorporate the latest improvements in transformer architecture, such as the use of mixture-of-experts layers, to improve performance and further identify the critical benefit of using synthetic images in micro-budget training. Finally, using only 37M publicly available real and synthetic images, we train a 1.16 billion parameter sparse transformer with only 1,890 USD economical cost and achieve a 12.7 FID in zero-shot generation on the COCO dataset. Notably, our model achieves competitive performance across both automated and human-centric evaluations, as well as high-quality generations, while incurring 118$\times$ lower costs than Stable Diffusion models and 14$\times$ lower costs than the current state-of-the-art approach, which costs \$28,400. We also further investigate the influence of synthetic images on performance and demonstrate that micro-budget training on only synthetic images is sufficient for achieving high-quality data generation.
Related Publications
The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking r…
Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be exploited for malicious purposes, suc…
With the rapid advancement of generative AI, it is now pos-sible to synthesize high-quality images in a few seconds.Despite the power of these technologies, they raise signif-icant concerns regarding misuse. Current efforts to dis-tinguish between real and AI-generated image…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.