StyleGAN-NADA: CLIP-guided domain adaptation of image generators
The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Can a generative model be trained to produce images from a specific domain, guided only by a text prompt, without seeing any image? In other words: can an image generator be trained "blindly"? Leveraging the semantic power of large scale Contrastive-Language-Image-Pre-training (CLIP) models, we present a text-driven method that allows shifting a generative model to new domains, without having to collect even a single image. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains characterized by diverse styles and shapes. Notably, many of these modifications would be difficult or infeasible to reach with existing methods. We conduct an extensive set of experiments across a wide range of domains. These demonstrate the effectiveness of our approach, and show that our models preserve the latent-space structure that makes generative models appealing for downstream tasks. Code and videos available at: stylegan-nada.github.io/
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The unreasonable effectiveness of deep features as a perceptual metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · arXiv · doi:10.48550/arxiv.1801.03924 · Cited by 24,812 · cited 2×
“[35] by clustering the data and computing an average LPIPS [63] distance within the clusters.”
MethodLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
LIII. On lines and planes of closest fit to systems of points in space
Pearson, K. (1901) · The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science · doi:10.1080/14786440109462720 · Cited by 11,934
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 3×
“We transform an FFHQ [22] model into doctors and nurses.”
MethodPerceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1912.04958 · Cited by 6,332
Cited by
Adding Conditional Control to Text-to-Image Diffusion Models
Zhang, L., Rao, A., & Agrawala, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00355 · Cited by 4,547
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2022) · arXiv · doi:10.48550/arxiv.2208.12242 · Cited by 2,442
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02155 · Cited by 2,295
Hierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511
“[19, 36, 32, 18] guide GANs using gradients from a CLIP model.”
MethodInstructpix2pix: Learning to follow image editing instructions
Brooks, T., Holynski, A., & Efros, A. A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01764 · Cited by 1,466
Multi-Concept Customization of Text-to-Image Diffusion
Kumari, N., Zhang, B., Zhang, R., Shechtman, E., & Zhu, J.-Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00192 · Cited by 674
Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
Tumanyan, N., Geyer, M., Bagon, S., & Dekel, T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00191 · Cited by 609
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
Kim, G., Kwon, T., & Ye, J. C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00246 · Cited by 570
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., & Cohen-Or, D. (2023) · ACM Transactions on Graphics · doi:10.1145/3592116 · Cited by 461
“In the context of image editing, while most methods are generally limited to global edits [Chefer et al. 2022a; Crowson et al. 2022; Gal et al. 2022b; Kwon and Ye 2022], several works introduce a user-provided mask to specify the region that should be altered [Avrahami et al. 2022a; Bau et al.…”
BackgroundMethodSelf-citationXia, W., Zhang, Y., Yang, Y., Xue, J.-H., Zhou, B., & Yang, M.-H. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3181070 · Cited by 366
Paint by Example: Exemplar-based Image Editing with Diffusion Models
Yang, B., Gu, S., Zhang, B., Zhang, T., Chen, X., Sun, X., Chen, D., & Wen, F. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01763 · Cited by 356
Inversion-based Style Transfer with Diffusion Models
Zhang, Y., Huang, N., Tang, F., Huang, H., Ma, C., Dong, W., & Xu, C. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00978 · Cited by 353
Avrahami, O., Fried, O., & Lischinski, D. (2023) · ACM Transactions on Graphics · doi:10.1145/3592450 · Cited by 345
Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
Metzer, G., Richardson, E., Patashnik, O., Giryes, R., & Cohen-Or, D. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01218 · Cited by 336
Self-citationMotionCLIP: Exposing Human Motion Generation to CLIP Space
Tevet, G., Gordon, B., Hertz, A., Bermano, A. H., & Cohen-Or, D. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20047-2_21 · Cited by 317
Self-citationInstruct-NeRF2NeRF: Editing 3D Scenes with Instructions
Haque, A., Tancik, M., Efros, A. A., Holynski, A., & Kanazawa, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01808 · Cited by 314
Muse: Text-To-Image Generation via Masked Generative Transformers
Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K., Freeman, W. T., Rubinstein, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.00704 · Cited by 157
Face Generation and Editing With StyleGAN: A Survey
Melnik, A., Miasayedzenkau, M., Makaravets, D., Pirshtuk, D., Akbulut, E., Holzmann, D., Renusch, T., Reichert, G., & Ritter, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3350004 · Cited by 105
ArtVerse: A Paradigm for Parallel Human–Machine Collaborative Painting Creation in Metaverses
Guo, C., Dou, Y., Bai, T., Dai, X., Wang, C., & Wen, Y. (2023) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2022.3230406 · Cited by 53
Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model
Xiao, S., Huang, S., Lin, Y., Ye, Y., & Zeng, W. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3326913 · Cited by 44
LAFITE: Towards Language-Free Training for Text-to-Image Generation
Zhou, Y., Zhang, R., Chen, C., Li, C., Tensmeyer, C., Yu, T., Gu, J., Xu, J., & Sun, T. (2021) · arXiv · doi:10.48550/arxiv.2111.13792 · Cited by 38
Metadata
- Authors
- Gal, R., Patashnik, O., Maron, H., Bermano, A. H., Chechik, G., & Cohen-Or, D.
- Venue
- ACM Transactions on Graphics
- Published
- 2022-07
- Volume
- 41
- Issue
- 4
- Pages
- 1-13
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W4286611278
- Cited by
- 500
- References
- 34
- FWCI
- 35.61
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.