# f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation

Source: [f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation](<https://www.sota2.com/research/paper/68fa6da61e209131cea3b2b9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:39:21.820Z

Authors: Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Miguel Angel Bautista, Josh Susskind

Published: 2022-10-10T18:49:25.000Z

## Abstract

Diffusion models (DMs) have recently emerged as SoTA tools for generative modeling in various domains. Standard DMs can be viewed as an instantiation of hierarchical variational autoencoders (VAEs) where the latent variables are inferred from input-centered Gaussian distributions with fixed scales and variances. Unlike VAEs, this formulation limits DMs from changing the latent spaces and learning abstract representations. In this work, we propose f-DM, a generalized family of DMs which allows progressive signal transformation. More precisely, we extend DMs to incorporate a set of (hand-designed or learned) transformations, where the transformed input is the mean of each diffusion step. We propose a generalized formulation and derive the corresponding de-noising objective with a modified sampling algorithm. As a demonstration, we apply f-DM in image generation tasks with a range of functions, including down-sampling, blurring, and learned transformations based on the encoder of pretrained VAEs. In addition, we identify the importance of adjusting the noise levels whenever the signal is sub-sampled and propose a simple rescaling recipe. f-DM can produce high-quality samples on standard image generation benchmarks like FFHQ, AFHQ, LSUN, and ImageNet with better efficiency and semantic interpretation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Generation on ImageNet 256x256](<https://www.sota2.com/research/sota/image-generation-on-imagenet-256x256.md>): Image Generation; ImageNet 256x256; IS: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.04955>)

[PDF](<https://arxiv.org/pdf/2210.04955.pdf>)
