# Step Saver: Predicting Minimum Denoising Steps for Diffusion Model Image Generation

arXiv: https://arxiv.org/abs/2408.02054 · HTML: https://mlsanity.com/paper/2408.02054/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 3 of its 3 references that are in the map.
- First posted on arXiv 4 Aug 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 3 of 3)

- [Parallel Sampling of Diffusion Models](https://mlsanity.com/paper/2305.16317/) (2023)
- [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020)
- [A Hitchhiker's Guide to Structural Similarity](https://mlsanity.com/paper/2101.06354/) (2021)

## Built on by (most cited first, 2 of 2)

- [BADiff: Bandwidth Adaptive Diffusion Model](https://mlsanity.com/paper/2510.21366/) (2025)
- [Accelerated AI Inference via Dynamic Execution Methods](https://mlsanity.com/paper/2411.00853/) (2024)

## Abstract (arXiv)

In this paper, we introduce an innovative NLP model specifically fine-tuned to determine the minimal number of denoising steps required for any given text prompt. This advanced model serves as a real-time tool that recommends the ideal denoise steps for generating high-quality images efficiently. It is designed to work seamlessly with the Diffusion model, ensuring that images are produced with superior quality in the shortest possible time. Although our explanation focuses on the DDIM scheduler, the methodology is adaptable and can be applied to various other schedulers like Euler, Euler Ancestral, Heun, DPM2 Karras, UniPC, and more. This model allows our customers to conserve costly computing resources by executing the fewest necessary denoising steps to achieve optimal quality in the produced images.