Update model card and metadata

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +19 -5
README.md CHANGED
@@ -1,14 +1,28 @@
1
  ---
2
  license: apache-2.0
3
- pipeline_tag: text-to-image
4
  ---
5
 
6
  # Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
7
 
8
- This repository contains the weights for **Spectral Forcing**.
9
 
10
- - **Paper:** arxiv.org/abs/2606.15236
11
- - **Github Repository:** https://github.com/WeichenFan/Spectral_Forcing
12
 
13
  ## Introduction
14
- Spectral Forcing (SF) is a parameter-free, time-conditional low-pass operator that makes the coarse-to-fine structure of diffusion explicit at the input of a pixel-space model. It is based on the observation that under rectified-flow diffusion and natural-image power-law spectra, a moving frequency front separates a signal-bearing low-frequency region from a noise-dominated high-frequency region at each timestep, and that a standard denoiser wastes capacity outside this region by reproducing closed-form maps rather than modeling the data. SF imposes this boundary directly via a 2D-DCT mask whose cutoff expands with the diffusion time and becomes the identity at the data endpoint, showing the network the signal and hiding the noise.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ pipeline_tag: unconditional-image-generation
4
  ---
5
 
6
  # Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
7
 
8
+ This repository contains the weights for **Spectral Forcing**, a parameter-free, time-conditional low-pass operator that makes the coarse-to-fine structure of diffusion explicit at the input of a pixel-space model.
9
 
10
+ - **Paper:** [Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion](https://arxiv.org/abs/2606.15236)
11
+ - **Github Repository:** [https://github.com/WeichenFan/Spectral_Forcing](https://github.com/WeichenFan/Spectral_Forcing)
12
 
13
  ## Introduction
14
+ Spectral Forcing (SF) is based on the observation that under rectified-flow diffusion and natural-image power-law spectra, a moving frequency front separates a signal-bearing low-frequency region from a noise-dominated high-frequency region at each timestep. SF imposes this boundary directly via a 2D-DCT mask whose cutoff expands with the diffusion time and becomes the identity at the data endpoint, showing the network the signal and hiding the noise.
15
+
16
+ ## BibTex
17
+ ```bibtex
18
+ @misc{fan2026show,
19
+ title = {{Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion}},
20
+ author = {Fan, Weichen and Diao, Haiwen and Wu, Penghao and Liu, Ziwei},
21
+ year = {2026},
22
+ eprint = {2606.15236},
23
+ archivePrefix = {arXiv},
24
+ primaryClass = {cs.CV},
25
+ doi = {10.48550/arXiv.2606.15236},
26
+ url = {https://arxiv.org/abs/2606.15236}
27
+ }
28
+ ```