mlsanityData to 7 Oct 2026

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

arXiv 2011.12799 ↗First posted 25 Nov 2020cs.CV cs.GR cs.LGcited by 331

Not on the map. Why?

Cited by 38 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We explore and analyze the latent style space of StyleGAN2, a state-of-the-art architecture for image generation, using models pretrained on several different datasets. We first show that StyleSpace, the space of channel-wise style parameters, is significantly more disentangled than the other intermediate latent spaces explored by previous works. Next, we describe a method for discovering a large collection of style channels, each of which is shown to control a distinct visual attribute in a highly localized and disentangled manner. Third, we propose a simple method for identifying style channels that control a specific attribute, using a pretrained classifier or a small number of example images. Manipulation of visual attributes via these StyleSpace controls is shown to be better disentangled than via those proposed in previous works. To show this, we make use of a newly proposed Attribute Dependency metric. Finally, we demonstrate the applicability of StyleSpace controls to the manipulation of real images. Our findings pave the way to semantically meaningful and well-disentangled image manipulations via simple and intuitive interfaces.

Key facts. Cited by 331 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 49; 2022: 108; 2023: 99; 2024: 46; 2025: 20; 2026: 9.

331 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  2. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  3. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  4. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  5. 2023Zero-shot Image-to-Image Translationcited by 503
  6. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  7. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  8. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  9. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  10. 2021GAN Inversion: A Surveycited by 366
  11. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  12. 2023P+: Extended Textual Conditioning in Text-to-Image Generationcited by 242
38 more
  1. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  2. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  3. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  4. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Modelscited by 148
  5. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  6. 2021LAFITE: Towards Language-Free Training for Text-to-Image Generationcited by 126
  7. 2023Generalizing Dataset Distillation via Deep Generative Priorcited by 125
  8. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  9. 2021Generative Adversarial Transformerscited by 120
  10. 2022Disentangled Representation Learningcited by 111
  11. 2021Paint by Wordcited by 107
  12. 2021Generative Models as a Data Source for Multiview Representation Learningcited by 104
  13. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  14. 2021Only a Matter of Style: Age Transformation Using a Style-Based Regression Modelcited by 92
  15. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  16. 2021CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directionscited by 78
  17. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  18. 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
  19. 2021A Latent Transformer for Disentangled Face Editing in Images and Videoscited by 67
  20. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  21. 2021Editing a classifier by rewriting its prediction rulescited by 64
  22. 2023Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Modelscited by 60
  23. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  24. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  25. 2024Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversioncited by 58
  26. 2022Disentangling visual and written concepts in CLIPcited by 57
  27. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  28. 2021Labels4Free: Unsupervised Segmentation using StyleGANcited by 53
  29. 2021Low-Rank Subspaces in GANscited by 52
  30. 2023Generative Models: What Do They Know? Do They Know Things? Let's Find Out!cited by 50
  31. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  32. 2021StyleAlign: Analysis and Applications of Aligned StyleGAN Modelscited by 48
  33. 2023HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Facescited by 48
  34. 2023Adaptive Frequency Filters As Efficient Global Token Mixerscited by 45
  35. 2024Image Sculpting: Precise Object Editing with 3D Geometry Controlcited by 45
  36. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  37. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  38. 2022Spatially-Adaptive Multilayer Selection for GAN Inversion and Editingcited by 39

50 most cited of 331 All 331 (JSON)