Diffusion Mental Averages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thawatdamrongkit, Phonphrm, Seripanitkarn, Sukit, Suwajanakorn, Supasorn
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910088240824320
author Thawatdamrongkit, Phonphrm
Seripanitkarn, Sukit
Suwajanakorn, Supasorn
author_facet Thawatdamrongkit, Phonphrm
Seripanitkarn, Sukit
Suwajanakorn, Supasorn
contents Can a diffusion model produce its own "mental average" of a concept-one that is as sharp and realistic as a typical sample? We introduce Diffusion Mental Averages (DMA), a model-centric answer to this question. While prior methods aim to average image collections, they produce blurry results when applied to diffusion samples from the same prompt. These data-centric techniques operate outside the model, ignoring the generative process. In contrast, DMA averages within the diffusion model's semantic space, as discovered by recent studies. Since this space evolves across timesteps and lacks a direct decoder, we cast averaging as trajectory alignment: optimize multiple noise latents so their denoising trajectories progressively converge toward shared coarse-to-fine semantics, yielding a single sharp prototype. We extend our approach to multimodal concepts (e.g., dogs with many breeds) by clustering samples in semantically-rich spaces such as CLIP and applying Textual Inversion or LoRA to bridge CLIP clusters into diffusion space. This is, to our knowledge, the first approach that delivers consistent, realistic averages, even for abstract concepts, serving as a concrete visual summary and a lens into model biases and concept representation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29239
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diffusion Mental Averages
Thawatdamrongkit, Phonphrm
Seripanitkarn, Sukit
Suwajanakorn, Supasorn
Computer Vision and Pattern Recognition
Can a diffusion model produce its own "mental average" of a concept-one that is as sharp and realistic as a typical sample? We introduce Diffusion Mental Averages (DMA), a model-centric answer to this question. While prior methods aim to average image collections, they produce blurry results when applied to diffusion samples from the same prompt. These data-centric techniques operate outside the model, ignoring the generative process. In contrast, DMA averages within the diffusion model's semantic space, as discovered by recent studies. Since this space evolves across timesteps and lacks a direct decoder, we cast averaging as trajectory alignment: optimize multiple noise latents so their denoising trajectories progressively converge toward shared coarse-to-fine semantics, yielding a single sharp prototype. We extend our approach to multimodal concepts (e.g., dogs with many breeds) by clustering samples in semantically-rich spaces such as CLIP and applying Textual Inversion or LoRA to bridge CLIP clusters into diffusion space. This is, to our knowledge, the first approach that delivers consistent, realistic averages, even for abstract concepts, serving as a concrete visual summary and a lens into model biases and concept representation.
title Diffusion Mental Averages
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.29239