# EP-CFG: Energy-Preserving Classifier-Free Guidance

arXiv: https://arxiv.org/abs/2412.09966 · HTML: https://mlsanity.com/paper/2412.09966/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 3 of its 6 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Placed in

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

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

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models](https://mlsanity.com/paper/2410.02416/) (2024)

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

- [AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models](https://mlsanity.com/paper/2509.25162/) (2025)
- [Self-Evaluation Unlocks Any-Step Text-to-Image Generation](https://mlsanity.com/paper/2512.22374/) (2025)

## Abstract (arXiv)

Classifier-free guidance (CFG) is widely used in diffusion models but often introduces over-contrast and over-saturation artifacts at higher guidance strengths. We present EP-CFG (Energy-Preserving Classifier-Free Guidance), which addresses these issues by preserving the energy distribution of the conditional prediction during the guidance process. Our method simply rescales the energy of the guided output to match that of the conditional prediction at each denoising step, with an optional robust variant for improved artifact suppression. Through experiments, we show that EP-CFG maintains natural image quality and preserves details across guidance strengths while retaining CFG's semantic alignment benefits, all with minimal computational overhead.