mlsanityData to 7 Oct 2026

JoJoGAN: One Shot Face Stylization

arXiv 2112.11641 ↗First posted 22 Dec 2021cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

A style mapper applies some fixed style to its input images (so, for example, taking faces to cartoons). This paper describes a simple procedure -- JoJoGAN -- to learn a style mapper from a single example of the style. JoJoGAN uses a GAN inversion procedure and StyleGAN's style-mixing property to produce a substantial paired dataset from a single example style. The paired dataset is then used to fine-tune a StyleGAN. An image can then be style mapped by GAN-inversion followed by the fine-tuned StyleGAN. JoJoGAN needs just one reference and as little as 30 seconds of training time. JoJoGAN can use extreme style references (say, animal faces) successfully. Furthermore, one can control what aspects of the style are used and how much of the style is applied. Qualitative and quantitative evaluation show that JoJoGAN produces high quality high resolution images that vastly outperform the current state-of-the-art.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

35 of 41 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  10. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  11. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  12. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
23 more
  1. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  2. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  3. 2017Universal Style Transfer via Feature Transformscited by 352
  4. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  5. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  6. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  7. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  8. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
  9. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  10. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  11. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 161
  12. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  13. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  14. 2020Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domainscited by 96
  15. 2020Improved StyleGAN Embedding: Where are the Good Latents?cited by 88
  16. 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
  17. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  18. 2021BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generationcited by 47
  19. 2020Deformable Style Transfercited by 31
  20. 2021Retrieve in Style: Unsupervised Facial Feature Transfer and Retrievalcited by 15
  21. 2021StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGANcited by 14
  22. 2021GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)cited by 13
  23. 2019Improving Style Transfer with Calibrated Metricscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 21; 2024: 9; 2025: 2; 2026: 2.

49 papers.

Sort:

By area:

  1. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  2. 2022Diffusion-based Image Translation using Disentangled Style and Content Representationcited by 148
  3. 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 62
  4. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  5. 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatarscited by 38
  6. 2023Training-free Content Injection using h-space in Diffusion Modelscited by 36
  7. 2022DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Modelcited by 32
  8. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  9. 2024UnZipLoRA: Separating Content and Style from a Single Imagecited by 24
  10. 2023MapPrior: Bird's-Eye View Map Layout Estimation with Generative Modelscited by 21
  11. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  12. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
37 more
  1. 2023Domain Re-Modulation for Few-Shot Generative Domain Adaptationcited by 18
  2. 2024One-Shot Structure-Aware Stylized Image Synthesiscited by 14
  3. 2024Deformable One-shot Face Stylization via DINO Semantic Guidancecited by 14
  4. 2022Bridging CLIP and StyleGAN through Latent Alignment for Image Editingcited by 12
  5. 2023WeditGAN: Few-Shot Image Generation via Latent Space Relocationcited by 12
  6. 2024Diffusion-driven GAN Inversion for Multi-Modal Face Image Generationcited by 12
  7. 2022CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learningcited by 10
  8. 2022StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptationcited by 10
  9. 2023Portrait Diffusion: Training-free Face Stylization with Chain-of-Paintingcited by 10
  10. 2024Contrastive Test-Time Composition of Multiple LoRA Models for Image Generationcited by 9
  11. 2022Video2StyleGAN: Disentangling Local and Global Variations in a Videocited by 8
  12. 2022WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylizationcited by 6
  13. 2023StyO: Stylize Your Face in Only One-shotcited by 6
  14. 2023AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learningcited by 5
  15. 2023Target-Aware Generative Augmentations for Single-Shot Adaptationcited by 5
  16. 2022StyLitGAN: Prompting StyleGAN to Produce New Illumination Conditionscited by 4
  17. 2022Leveraging GAN Priors for Few-Shot Part Segmentationcited by 4
  18. 2024Stylized Face Sketch Extraction via Generative Prior with Limited Datacited by 4
  19. 2022MultiStyleGAN: Multiple One-shot Image Stylizations using a Single GANcited by 3
  20. 2023StyleRetoucher: Generalized Portrait Image Retouching with GAN Priorscited by 3
  21. 2024ToonAging: Face Re-Aging upon Artistic Portrait Style Transfercited by 2
  22. 2022Single-Shot Domain Adaptation via Target-Aware Generative Augmentationcited by 1
  23. 2022Realtime Data-Efficient Portrait Stylization Based On Geometric Alignmentcited by 1
  24. 2023Cross-modal Face- and Voice-style Transfercited by 1
  25. 2023Few-shots Portrait Generation with Style Enhancement and Identity Preservationcited by 1
  26. 2023Multi-Modal Face Stylization with a Generative Priorcited by 1
  27. 2023Context-Preserving Two-Stage Video Domain Translation for Portrait Stylizationcited by 1
  28. 2025FFaceNeRF: Few-shot Face Editing in Neural Radiance Fieldscited by 1
  29. 2022Generative Adversarial Network Applications in Creating a Meta-Universecited by 0
  30. 2023Few-shot Face Image Translation via GAN Prior Distillationcited by 0
  31. 20233D Face Arbitrary Style Transfercited by 0
  32. 2023One-Shot Stylization for Full-Body Human Imagescited by 0
  33. 2024ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesiscited by 0
  34. 2024PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptationcited by 0
  35. 2025Efficient Few-shot Identity Preserving Attribute Editing for 3D-aware Deep Generative Modelscited by 0
  36. 2026Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Modelcited by 0
  37. 2026AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfercited by 0