Implicit Concept Removal of Diffusion Models | SpringerLink
Skip to main content

Implicit Concept Removal of Diffusion Models

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15079))

Included in the following conference series:

  • 74 Accesses

Abstract

Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed “implicit concepts”, can be unintentionally learned during training and then be generated uncontrollably during inference. Existing removal methods still struggle to eliminate implicit concepts primarily due to their dependency on the model’s ability to recognize concepts it actually can not discern. To address this, we utilize the intrinsic geometric characteristics of implicit concepts and present Geom-Erasing, a novel concept removal method based on geometric-driven control. Specifically, once an unwanted implicit concept is identified, we integrate the existence and geometric information of the concept into the text prompts with the help of an accessible classifier or detector model. Subsequently, the model is optimized to identify and disentangle this information, which is then adopted as negative prompts during generation. Moreover, we introduce the Implicit Concept Dataset (ICD), a novel image-text dataset imbued with three typical implicit concepts (QR codes, watermarks, and text), reflecting real-life situations where implicit concepts are easily injected. Geom-Erasing effectively mitigates the generation of implicit concepts, achieving state-of-the-art results on the Inappropriate Image Prompts (I2P) and our challenging Implicit Concept Dataset (ICD) benchmarks.

Z. Liu and K. Chen—Equal contribution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 8465
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 10581
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://huggingface.co/runwayml/stable-diffusion-v1-5.

  2. 2.

    https://github.com/LAION-AI/LAION-5B-WatermarkDetection.

References

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

  2. Birhane, A., Prabhu, V.U., Kahembwe, E.: Multimodal datasets: misogyny, pornography, and malignant stereotypes. arXiv preprint arXiv:2110.01963 (2021)

  3. Brack, M., Friedrich, F., Hintersdorf, D., Struppek, L., Schramowski, P., Kersting, K.: SEGA: instructing diffusion using semantic dimensions. arXiv preprint arXiv:2301.12247 (2023)

  4. Brack, M., Friedrich, F., Schramowski, P., Kersting, K.: Mitigating inappropriateness in image generation: can there be value in reflecting the world’s ugliness? arXiv preprint arXiv:2305.18398 (2023)

  5. Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: CVPR (2021)

    Google Scholar 

  6. Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)

    Google Scholar 

  7. Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. arXiv preprint arXiv:2303.07345 (2023)

  8. Gao, R., et al.: MagicDrive: street view generation with diverse 3D geometry control. arXiv preprint arXiv:2310.02601 (2023)

  9. 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 (2017)

    Google Scholar 

  10. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)

    Google Scholar 

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

  12. Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. In: NeurIPS (2021)

    Google Scholar 

  13. Kumari, N., Zhang, B., Wang, S.Y., Shechtman, E., Zhang, R., Zhu, J.Y.: Ablating concepts in text-to-image diffusion models. In: ICCV (2023)

    Google Scholar 

  14. Lee, T., et al.: Holistic evaluation of text-to-image models. arXiv preprint arXiv:2311.04287 (2023)

  15. Li, P., et al.: TrackDiffusion: multi-object tracking data generation via diffusion models. arXiv preprint arXiv:2312.00651 (2023)

  16. Nichol, A.: DALL.E 2 pre-training mitigations (2022). https://openai.com/research/dall-e-2-pre-training-mitigations

  17. Pinkney, J.N.M.: Pokemon blip captions (2022). https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions/

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

    Google Scholar 

  19. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  20. Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)

    Google Scholar 

  21. Schramowski, P., Brack, M., Deiseroth, B., Kersting, K.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: CVPR (2023)

    Google Scholar 

  22. Schuhmann, C., et al.: LAION-400M: open dataset of CLIP-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)

  23. Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)

    Google Scholar 

  24. Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)

  25. Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: NeurIPS (2017)

    Google Scholar 

  26. Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  27. Yang, Y., Gui, D., Yuan, Y., Ding, H., Hu, H., Chen, K.: GlyphControl: glyph conditional control for visual text generation. arXiv preprint arXiv:2305.18259 (2023)

  28. Zhang, E., Wang, K., Xu, X., Wang, Z., Shi, H.: Forget-me-not: learning to forget in text-to-image diffusion models. arXiv preprint arXiv:2211.08332 (2023)

  29. Zhang, Y., Hooi, B.: HiPA: enabling one-step text-to-image diffusion models via high-frequency-promoting adaptation. arXiv preprint arXiv:2311.18158 (2023)

  30. Zhang, Y., Zhou, D., Hooi, B., Wang, K., Feng, J.: Expanding small-scale datasets with guided imagination. In: NeurIPS (2023)

    Google Scholar 

Download references

Acknowledgment

We gratefully acknowledge the support of MindSpore, CANN (Compute Architecture for Neural Networks) and Ascend AI Processor used for this research. This work was partially supported by the Research Grants Council of the Hong Kong Special Administrative Region (Grants C7004-22G-1 and 16202523). This research has been made possible by funding support from the Research Grants Council of Hong Kong through the Research Impact Fund project R6003-21.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zhili Liu .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2815 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liu, Z. et al. (2025). Implicit Concept Removal of Diffusion Models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15079. Springer, Cham. https://doi.org/10.1007/978-3-031-72664-4_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72664-4_26

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72663-7

  • Online ISBN: 978-3-031-72664-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics