“Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models” by Chefer, Alaluf, Vinker, Wolf and Cohen-Or

  • ©Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, and Daniel Cohen-Or




    Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models

Session/Category Title: Neural Image Generation and Editing




    Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt. Moreover, we find that in some cases the model also fails to correctly bind attributes (e.g., colors) to their corresponding subjects. To help mitigate these failure cases, we introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness of the generated images. Using an attention-based formulation of GSN, dubbed Attend-and-Excite, we guide the model to refine the cross-attention units to attend to all subject tokens in the text prompt and strengthen — or excite — their activations, encouraging the model to generate all subjects described in the text prompt. We compare our approach to alternative approaches and demonstrate that it conveys the desired concepts more faithfully across a range of text prompts. Code is available at our project page: https://attendandexcite.github.io/Attend-and-Excite/.


    1. Samira Abnar and Willem Zuidema. 2020. Quantifying Attention Flow in Transformers. ArXiv abs/2005.00928 (2020).
    2. Oron Ashual and Lior Wolf. 2019. Specifying object attributes and relations in interactive scene generation. In Proceedings of the IEEE/CVF international conference on computer vision. 4561–4569.
    3. Omri Avrahami, Ohad Fried, and Dani Lischinski. 2022a. Blended Latent Diffusion. arXiv preprint arXiv:2206.02779 (2022).
    4. Omri Avrahami, Thomas Hayes, Oran Gafni, Sonal Gupta, Yaniv Taigman, Devi Parikh, Dani Lischinski, Ohad Fried, and Xi Yin. 2022b. SpaText: Spatio-Textual Representation for Controllable Image Generation. arXiv preprint arXiv:2211.14305 (2022).
    5. Yogesh Balaji, Seungjun Nah, Xun Huang, Arash Vahdat, Jiaming Song, Karsten Kreis, Miika Aittala, Timo Aila, Samuli Laine, Bryan Catanzaro, Tero Karras, and Ming-Yu Liu. 2022. eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers. ArXiv abs/2211.01324 (2022).
    6. Sourav Banerjee. 2022. Animal Image Dataset. https://www.kaggle.com/datasets/iamsouravbanerjee/animal-image-dataset-90-different-animals.
    7. David Bau, Alex Andonian, Audrey Cui, YeonHwan Park, Ali Jahanian, Aude Oliva, and Antonio Torralba. 2021. Paint by word. arXiv preprint arXiv:2103.10951 (2021).
    8. Tim Brooks, Aleksander Holynski, and Alexei A Efros. 2022. InstructPix2Pix: Learning to Follow Image Editing Instructions. arXiv preprint arXiv:2211.09800 (2022).
    9. Hila Chefer, Sagie Benaim, Roni Paiss, and Lior Wolf. 2022a. Image-Based CLIP-Guided Essence Transfer. (2022).
    10. Hila Chefer, Shir Gur, and Lior Wolf. 2021. Generic Attention-Model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 397–406.
    11. Hila Chefer, Idan Schwartz, and Lior Wolf. 2022b. Optimizing Relevance Maps of Vision Transformers Improves Robustness. In Thirty-Sixth Conference on Neural Information Processing Systems. https://openreview.net/forum?id=upuYKQiyxa_
    12. Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord. 2022. DiffEdit: Diffusion-based semantic image editing with mask guidance.
    13. Katherine Crowson, Stella Biderman, Daniel Kornis, Dashiell Stander, Eric Hallahan, Louis Castricato, and Edward Raff. 2022. Vqgan-clip: Open domain image generation and editing with natural language guidance. In European Conference on Computer Vision. Springer, 88–105.
    14. Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2022. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis. arXiv preprint arXiv:2212.05032 (2022).
    15. Oran Gafni, Adam Polyak, Oron Ashual, Shelly Sheynin, Devi Parikh, and Yaniv Taigman. 2022. Make-a-scene: Scene-based text-to-image generation with human priors. arXiv preprint arXiv:2203.13131 (2022).
    16. Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022a. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022).
    17. Rinon Gal, Or Patashnik, Haggai Maron, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022b. Stylegan-nada: Clip-guided domain adaptation of image generators. ACM Transactions on Graphics (TOG) 41, 4 (2022), 1–13.
    18. Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022).
    19. Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33 (2020), 6840–6851.
    20. Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022).
    21. Justin Johnson, Agrim Gupta, and Li Fei-Fei. 2018. Image generation from scene graphs. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1219–1228.
    22. Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, and Michal Irani. 2022. Imagic: Text-based real image editing with diffusion models. arXiv preprint arXiv:2210.09276 (2022).
    23. Nupur Kumari, Bingliang Zhang, Richard Zhang, Eli Shechtman, and Jun-Yan Zhu. 2022. Multi-Concept Customization of Text-to-Image Diffusion. arXiv preprint arXiv:2212.04488 (2022).
    24. Gihyun Kwon and Jong Chul Ye. 2022. Clipstyler: Image style transfer with a single text condition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 18062–18071.
    25. Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. arXiv preprint arXiv:2201.12086 (2022).
    26. Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. arXiv preprint arXiv:2203.02053 (2022).
    27. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In European conference on computer vision. Springer, 740–755.
    28. Nan Liu, Shuang Li, Yilun Du, Antonio Torralba, and Joshua B Tenenbaum. 2022. Compositional Visual Generation with Composable Diffusion Models. arXiv preprint arXiv:2206.01714 (2022).
    29. Vivian Liu and Lydia B Chilton. 2022. Design Guidelines for Prompt Engineering Text-to-Image Generative Models. In CHI Conference on Human Factors in Computing Systems. 1–23.
    30. Gary Marcus, Ernest Davis, and Scott Aaronson. 2022. A very preliminary analysis of DALL-E 2. arXiv preprint arXiv:2204.13807 (2022).
    31. Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021).
    32. Roni Paiss, Hila Chefer, and Lior Wolf. 2022. No token left behind: Explainability-aided image classification and generation. In European Conference on Computer Vision. Springer, 334–350.
    33. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748–8763.
    34. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. ArXiv (2022). https://arxiv.org/abs/2204.06125
    35. Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821–8831.
    36. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10684–10695.
    37. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.
    38. Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2022. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. arXiv preprint arXiv:2208.12242 (2022).
    39. Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L. Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, Seyedeh Sara Mahdavi, Raphael Gontijo Lopes, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. ArXiv abs/2205.11487 (2022).
    40. Shelly Sheynin, Oron Ashual, Adam Polyak, Uriel Singer, Oran Gafni, Eliya Nachmani, and Yaniv Taigman. 2022. KNN-Diffusion: Image Generation via Large-Scale Retrieval. ArXiv abs/2204.02849 (2022).
    41. Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning. PMLR, 2256–2265.
    42. Ming Tao, Hao Tang, Fei Wu, Xiao-Yuan Jing, Bing-Kun Bao, and Changsheng Xu. 2022. DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16515–16525.
    43. Dani Valevski, Matan Kalman, Yossi Matias, and Yaniv Leviathan. 2022. Unitune: Text-driven image editing by fine tuning an image generation model on a single image. arXiv preprint arXiv:2210.09477 (2022).
    44. Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2022. DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models. arXiv preprint arXiv:2210.14896 (2022).
    45. Sam Witteveen and Martin Andrews. 2022. Investigating Prompt Engineering in Diffusion Models. arXiv preprint arXiv:2211.15462 (2022).
    46. Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xiaodong He. 2018. Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1316–1324.
    47. Hui Ye, Xiulong Yang, Martin Takac, Rajshekhar Sunderraman, and Shihao Ji. 2021. Improving text-to-image synthesis using contrastive learning. arXiv preprint arXiv:2107.02423 (2021).
    48. Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022).
    49. Han Zhang, Jing Yu Koh, Jason Baldridge, Honglak Lee, and Yinfei Yang. 2021. Cross-modal contrastive learning for text-to-image generation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 833–842.
    50. Bo Zhao, Lili Meng, Weidong Yin, and Leonid Sigal. 2019. Image Generation from Layout. In CVPR.
    51. Minfeng Zhu, Pingbo Pan, Wei Chen, and Yi Yang. 2019. Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5802–5810.

Additional Images:

©Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, and Daniel Cohen-Or

ACM Digital Library Publication:

Overview Page: