Top

Published in:

2025 | OriginalPaper | Chapter

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis

Authors : Linjiang Huang, Rongyao Fang, Aiping Zhang, Guanglu Song, Si Liu, Yu Liu, Hongsheng Li

Published in: Computer Vision – ECCV 2024

Publisher: Springer Nature Switzerland

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond their trained resolutions. To address this issue, we introduce an innovative, training-free approach FouriScale from the perspective of frequency domain analysis. We replace the original convolutional layers in pre-trained diffusion models by incorporating a dilation technique along with a low-pass operation, intending to achieve structural consistency and scale consistency across resolutions, respectively. Further enhanced by a padding-then-crop strategy, our method can flexibly handle text-to-image generation of various aspect ratios. By using the FouriScale as guidance, our method successfully balances the structural integrity and fidelity of generated images, achieving arbitrary-size, high-resolution, and high-quality generation. With its simplicity and compatibility, our method can provide valuable insights for future explorations into the synthesis of ultra-high-resolution images. The source code is available at https://github.com/LeonHLJ/FouriScale.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

previous chapter RoadPainter: Points Are Ideal Navigators for Topology TransformER

next chapter Can OOD Object Detectors Learn from Foundation Models?

Available only for authorised users

For simplicity, we assume equal down-sampling scales for height and width. Our method can also accommodate different down-sampling scales in this context through our padding-then-cropping strategy (Sect. 3.4).

Balaji, Y., et al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)

Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. arXiv preprint arXiv:2302.08113 (2023)

Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: International Conference on Learning Representations (2018)

Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: CVPR, pp. 22563–22575 (2023)

Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: MasaCtrl: tuning-free mutual self-attention control for consistent image synthesis and editing. arXiv preprint arXiv:2304.08465 (2023)

Chen, T.: On the importance of noise scheduling for diffusion models. arXiv preprint arXiv:2301.10972 (2023)

Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS 34, pp. 8780–8794 (2021)

Stable Diffusion: Stable diffusion 2-1 base (2022). https://huggingface.co/stabilityai/stable-diffusion-2-1-base/blob/main/v2-1_512-ema-pruned.ckpt

Ding, M., et al.: CogView: mastering text-to-image generation via transformers. In: NeurIPS 34, pp. 19822–19835 (2021)

10.

Du, R., Chang, D., Hospedales, T., Song, Y.Z., Ma, Z.: DemoFusion: democratising high-resolution image generation with no $$\$. In: CVPR, pp. 6159–6168 (2024)

11.

Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986 (2023)

12.

Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS 27 (2014)

13.

Haji-Ali, M., Balakrishnan, G., Ordonez, V.: ElasticDiffusion: training-free arbitrary size image generation through global-local content separation. In: CVPR, pp. 6603–6612 (2024)

14.

He, Y., et al.: ScaleCrafter: tuning-free higher-resolution visual generation with diffusion models. arXiv preprint arXiv:2310.07702 (2023)

15.

He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity video generation with arbitrary lengths. arXiv preprint arXiv:2211.13221 (2022)

16.

Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: ICLR (2022)

17.

Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NeurIPS 30 (2017)

18.

Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS 33, pp. 6840–6851 (2020)

19.

Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249–2281 (2022)MathSciNet

20.

Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)

21.

Hoogeboom, E., Heek, J., Salimans, T.: Simple diffusion: end-to-end diffusion for high resolution images. arXiv preprint arXiv:2301.11093 (2023)

22.

Jiménez, Á.B.: Mixture of diffusers for scene composition and high resolution image generation. arXiv preprint arXiv:2302.02412 (2023)

23.

Jin, Z., Shen, X., Li, B., Xue, X.: Training-free diffusion model adaptation for variable-sized text-to-image synthesis. arXiv preprint arXiv:2306.08645 (2023)

24.

Lee, Y., Kim, K., Kim, H., Sung, M.: SyncDiffusion: coherent montage via synchronized joint diffusions. In: NeurIPS 36 (2024)

25.

Liu, H., et al.: AudioLDM: text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503 (2023)

26.

Lu, Z., et al.: FiT: flexible vision transformer for diffusion model. arXiv preprint arXiv:2402.12376 (2024)

27.

Midjourney (2024). https://www.midjourney.com. Accessed 17 Jan 2024

28.

Pattichis, M.S., Bovik, A.C.: Analyzing image structure by multidimensional frequency modulation. IEEE TPAMI 29(5), 753–766 (2007)CrossRef

29.

Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195–4205 (2023)

30.

Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)

31.

Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821–8831. PMLR (2021)

32.

Riad, R., Teboul, O., Grangier, D., Zeghidour, N.: Learning strides in convolutional neural networks. In: ICLR (2021)

33.

Rippel, O., Snoek, J., Adams, R.P.: Spectral representations for convolutional neural networks. In: NeurIPS 28 (2015)

34.

Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684–10695 (2022)

35.

Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS 35, pp. 36479–36494 (2022)

36.

Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models (2022)

37.

Si, C., Huang, Z., Jiang, Y., Liu, Z.: FreeU: free lunch in diffusion U-Net. arXiv preprint arXiv:2309.11497 (2023)

38.

Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)

39.

Teng, J., et al.: Relay diffusion: unifying diffusion process across resolutions for image synthesis. arXiv preprint arXiv:2309.03350 (2023)

40.

Wang, J., et al.: Diffusion model is secretly a training-free open vocabulary semantic segmenter. arXiv preprint arXiv:2309.02773 (2023)

41.

Xiao, C., Yang, Q., Zhou, F., Zhang, C.: From text to mask: localizing entities using the attention of text-to-image diffusion models. arXiv preprint arXiv:2309.04109 (2023)

42.

Zeng, X., et al.: LION: latent point diffusion models for 3D shape generation. arXiv preprint arXiv:2210.06978 (2022)

43.

Zhang, R.: Making convolutional networks shift-invariant again. In: ICML, pp. 7324–7334. PMLR (2019)

44.

Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: ECCV, pp. 286–301 (2018)

45.

Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. In: ICCV (2023)

46.

Zheng, Q., et al.: Any-size-diffusion: toward efficient text-driven synthesis for any-size HD images. arXiv preprint arXiv:2308.16582 (2023)

47.

Zhu, Q., et al.: FouriDown: factoring down-sampling into shuffling and superposing. In: NeurIPS (2023)

Title: FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
Authors: Linjiang Huang
Rongyao Fang
Aiping Zhang
Guanglu Song
Si Liu
Yu Liu
Hongsheng Li
Publisher: Springer Nature Switzerland
Book: Computer Vision – ECCV 2024
Print ISBN: 978-3-031-73253-9

Electronic ISBN: 978-3-031-73254-6

Copyright Year: 2025
DOI: https://doi.org/10.1007/978-3-031-73254-6_12

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"