# Rethinking Timesteps Samplers and Prediction Types

arXiv: https://arxiv.org/abs/2502.01990 · HTML: https://mlsanity.com/paper/2502.01990/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- First posted on arXiv 4 Feb 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Abstract (arXiv)

Diffusion models suffer from the huge consumption of time and resources to train. For example, diffusion models need hundreds of GPUs to train for several weeks for a high-resolution generative task to meet the requirements of an extremely large number of iterations and a large batch size. Training diffusion models become a millionaire's game. With limited resources that only fit a small batch size, training a diffusion model always fails. In this paper, we investigate the key reasons behind the difficulties of training diffusion models with limited resources. Through numerous experiments and demonstrations, we identified a major factor: the significant variation in the training losses across different timesteps, which can easily disrupt the progress made in previous iterations. Moreover, different prediction types of x0 exhibit varying effectiveness depending on the task and timestep. We hypothesize that using a mixed-prediction approach to identify the most accurate x0 prediction type could potentially serve as a breakthrough in addressing this issue. In this paper, we outline several challenges and insights, with the hope of inspiring further research aimed at tackling the limitations of training diffusion models with constrained resources, particularly for high-resolution tasks.