# Spectral Progressive Diffusion for Efficient Image and Video Generation

arXiv: https://arxiv.org/abs/2605.18736 · HTML: https://mlsanity.com/paper/2605.18736/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 12 of its 96 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models](https://mlsanity.com/paper/2501.08453/) (2025)
- [Training-free Diffusion Acceleration with Bottleneck Sampling](https://mlsanity.com/paper/2503.18940/) (2025)
- [Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models](https://mlsanity.com/paper/2411.07126/) (2024)
- [FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching](https://mlsanity.com/paper/2510.08669/) (2025)
- [Bidirectional Sparse Attention for Faster Video Diffusion Training](https://mlsanity.com/paper/2509.01085/) (2025)
- [PixelGen: Improving Pixel Diffusion with Perceptual Supervision](https://mlsanity.com/paper/2602.02493/) (2026)
- [Flow Along the K-Amplitude for Generative Modeling](https://mlsanity.com/paper/2504.19353/) (2025)

## Built on by (most cited first, 5 of 5)

- [Parallel Decoding Distillation for Fast Image and Video Generation](https://mlsanity.com/paper/2607.26004/) (2026)
- [Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling](https://mlsanity.com/paper/2607.01642/) (2026)
- [When does training on downscaled images yield the same gradients?](https://mlsanity.com/paper/2608.04448/) (2026)
- [Level-of-Token Diffusion](https://mlsanity.com/paper/2610.05816/) (2026)
- [AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers](https://mlsanity.com/paper/2610.17227/) (2026)

## Abstract (arXiv)

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for efficient generation, as high-resolution computation on noise-dominated frequencies is largely redundant. We propose Spectral Progressive Diffusion, a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models. To this end, we develop a spectral noise expansion mechanism and derive an optimal resolution schedule from the model's power spectrum. Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality. We demonstrate significant speedups on state-of-the-art pretrained image and video generation models while preserving visual quality.