A curated collection of papers on portrait style transfer
29
40 commits
updated Aug 20, 2026
README
Awesome-Portraits-Style-Transfer 
An archive of studies related to portrait style transfer
Table of Contents
Papers
Based on GANs
| Date | Title | Publish | Paper | Code | Homepage | Recom |
|---|---|---|---|---|---|---|
| 2024.11 | BeautyBank: Encoding Facial Makeup in Latent Space | WACV 2025 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.09 | PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation | ArXiv 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.08 | Multi-Style Facial Sketch Synthesis through Masked Generative Modeling | ArXiv 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.04 | ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesis | ICPR 2024 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.03 | AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning | CVPRW 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.03 | DoesFS: Deformable One-shot Face Stylization via DINO Semantic Guidance | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2023.11 | 3D Face Style Transfer with a Hybrid Solution of NeRF and Mesh Rasterization | WACV 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2023.05 | MMFS: Multi-Modal Face Stylization with a Generative Prior | PG 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.03 | Fix the Noise: Disentangling Source Feature for Controllable Domain Translation | CVPR 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.03 | StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces | ICCV 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.11 | DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains | SIGGRAPH Asia 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.10 | TargetCLIP: Official PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer | ECCV 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.09 | VToonify: Controllable High-Resolution Portrait Video Style Transfer | SIGGRAPH Asia 2022 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2022.09 | GODA: Generalized One-shot Domain Adaptation of Generative Adversarial Networks | NeurIPS 2022 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2022.07 | DCT-Net: Domain-Calibrated Translation for Portrait Stylization | SIGGRAPH 2022 (TOG) | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.06 | Real-Time Portrait Stylization on the Edge | ArXiv 2022 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2022.04 | Unsupervised Image-to-Image Translation with Generative Prior | CVPR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.03 | CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning | ArXiv 2022 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2022.03 | A Style-aware Discriminator for Controllable Image Translation | CVPR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.03 | Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer | CVPR 2022 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2022.03 | OneShotCLIP: One-Shot Adaptation of GAN in Just One CLIP | TPAMI 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.12 | SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing | CVPR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.12 | BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation | NeurIPS 2021 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2021.11 | MTG: Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks | ICLR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2021.09 | CariMe: Unpaired Caricature Generation with Multiple Exaggerations | TMM 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.09 | StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation | SIGGRAPH 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.09 | ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement | ICCV 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.09 | SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation | ICCV 2021 | [paper] | [code] | [homepage] | ⭐️ |
| 2021.07 | AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning | SIGGRAPH 2021 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2021.07 | Making Robots Draw A Vivid Portrait In Two Minutes | IROS 2020 | [paper] | [code] | [homepage] | ⭐️ |
| 2021.07 | Line Drawings for Face Portraits from Photos using Global and Local Structure based GANs | IEEE 2020 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.06 | Fine-Tuning StyleGAN2 For Cartoon Face Generation | Arxiv 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.05 | MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing | AAAI 2021 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2021.04 | CPM: Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfer | CVPR 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.02 | AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation | TMM 2021 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2019.07 | U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation | ICLR 2020 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2019.07 | Landmark Assisted CycleGAN for Cartoon Face Generation | ArXiv 2019 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2019.06 | APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs | CVPR 2019 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2018.11 | WarpGAN: Automatic Caricature Generation | CVPR 2019 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2017.03 | Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization | ICCV 2017 | [paper] | [code] | [homepage] | ⭐️⭐️ |
Based on Diffusion Models
| Date | Title | Publish | Paper | Code | Homepage | Recom |
|---|---|---|---|---|---|---|
| 2025.11 | Inversion-Free Style Transfer with Dual Rectified Flows | Arxiv 2025 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2025.09 | StyleFace: Forging a Masterpiece from Any Face - A Universal Framework for Face Stylization | ICLR 2026 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2025.07 | DGPST: Dual Graph Prompt Style Transfer | ICCV 2025 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2025.05 | TF-SA: Training Free Stylized Abstraction | ArXiv 2025 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2025.05 | OmniStyle: Filtering High Quality Style Transfer Data at Scale | CVPR 2025 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2025.04 | GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Faces | ArXiv 2025 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2025.01 | InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation | ICLR 2025 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2025.01 | StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer | CVPR 2025 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2024.12 | StyleMaster: Stylize Your Video with Artistic Generation and Translation | CVPR 2025 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2024.09 | StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models | ECCV 2024 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2024.08 | CSGO: Content-Style Composition in Text-to-Image Generation | NeurIPS 2025 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2024.08 | MagicFace: Training-free Universal-Style Human Image Customized Synthesis | ArXiv 2024 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.08 | ZePo: Zero-Shot Portrait Stylization with Faster Sampling | ACM Multimedia 2024 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2024.07 | InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.05 | Pair Customization: Customizing Text-to-Image Models with a Single Image Pair | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.04 | Style-Booth: Image Style Editing with Multimodal Instruction | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.04 | InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2024.04 | B-LoRA: Implicit Style-Content Separation using B-LoRA | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.03 | DiffStyler: An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration | AAAI 2026 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.03 | A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification | ICASSP 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.02 | VisualStylePrompt: Visual Style Prompting with Swapping Self-Attention | ArXiv 2024 | [paper] | N/A | [homepage] | ⭐️ |
| 2024.01 | FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.01 | CreativeSynth: Creative Blending and Synthesis of Visual Arts based on Multimodal Diffusion | ArXiv 2024 | [paper] | [code] | N/A | ⭐️ |
| 2024.01 | InstantID: Zero-shot Identity-Preserving Generation in Seconds | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | StyleID: Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | FaceStudio: Put Your Face Everywhere in Seconds | ArXiv 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting | ArXiv 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.12 | StyleAligned: Style Aligned Image Generation via Shared Attention | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2023.08 | IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models | ArXiv 2023 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2023.07 | VCT: General Image-to-Image Translation with One-Shot Image Guidance | ICCV 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.06 | Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation | SIGGRAPH Asia 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.11 | ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models | SIGGRAPH Asia 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.05 | Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer | ArXiv 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.03 | ZeCon: Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer | ICCV 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2022.11 | InST: Inversion-Based Style Transfer with Diffusion Models | CVPR 2023 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
Others
| Date | Title | Publish | Paper | Code | Homepage | Recom |
|---|---|---|---|---|---|---|
| 2023.09 | Portrait Stylization: Artistic Style Transfer with Auxiliary Networks for Human Face Stylization | ArXiv 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.12 | CLIPstyler: Image Style Transfer with a Single Text Condition | CVPR 2022 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.08 | AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer | ICCV 2021 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.03 | ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows | CVPR 2021 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2018.06 | Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration | CVPR 2018 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2018.01 | Face Sketch Synthesis with Style Transfer using Pyramid Column Feature | WACV 2018 | [paper] | [code] | N/A | ⭐️⭐️ |
Repositories
Datasets
Face Datasets
| Year | Name | Description | License | HomePage | Download |
|---|---|---|---|---|---|
| 2019 | FFHQ (Flickr-Faces-HQ) | A high-quality dataset of 70,000 human face images at 1024×1024 resolution with considerable variation in age, ethnicity and background. | CC BY-NC-SA 4.0 | [homepage] | [download] |
| 2018 | CelebA-HQ | A high-quality version of CelebA dataset consisting of 30,000 face images at 1024×1024 resolution. | CC BY-NC 4.0 | [homepage] | [download] |
Stylized Face Datasets
| Year | Name | Description | License | HomePage | Download |
|---|---|---|---|---|---|
| 2025 | FFHQ-Makeup | A high-quality synthetic makeup dataset with 90K paired bare-makeup images (18K identities × 5 makeup styles) at 512×512 resolution. | CC BY-NC-SA 4.0 | [homepage] | [download] |
| 2024 | SKSF-A | An high-resolution dataset of professional artist drawn face sketches. | CC BY-NC-SA 4.0 | [homepage] | [download] |
| 2022 | ArcaneFaces | A handcrafted high-quality dataset of over 3400 faces from Arcane. | CC BY 4.0 | [homepage] | [download] |
| 2021 | AAHQ | A high-quality image dataset of artistic-face images. | N/A | [homepage] | [download] |
| 2020 | Metaface | A dataset containing high-quality artistic/stylized face images for machine learning applications. | CC0 | [homepage] | [download] |
| 2020 | Riga Faces | A dataset of 165 high-quality images of mascarons seen on art nouveau buildings in Riga, Latvia. | CC0 | [homepage] | [download] |
| 2020 | Danbooru2020 | A large-scale anime image database with 4.2m+ images and 130m+ tags. | CC0 1.0 | [homepage] | [download] |
| 2020 | Aligned Ukiyo-e Faces | Over five thousand aligned ukiyo-e faces at 1024x1024 pixel resolution. | CC BY-SA 4.0 | [homepage] | [download] |
| 2020 | Cartoon Faces | A dataset of cartoon (Disney) faces for machine learning applications. | CC BY-SA 4.0 | [homepage] | [download] |
| 2020 | Comic faces (paired, synthetic) | A dataset of paired synthetic comic faces for machine learning applications. | CC BY 4.0 | [homepage] | [download] |
| 2020 | Comic faces (paired, synthetic, v2) | A dataset of paired synthetic comic faces for machine learning applications, version 2. | CC BY 4.0 | [homepage] | [download] |
| 2019 | Danbooru2019 | A large-scale anime image database with 3.69m+ images and 108m+ tags. | CC0 1.0 | [homepage] | [download] |
| 2019 | APDrawingGAN Dataset | A dataset used for generating artistic portrait drawings from face photos with hierarchical GANs. | Apache-2.0 | [homepage] | [download] |
| 2018 | Danbooru2018 | A large-scale anime image database with 3.3m+ images and 92.7m+ tags. | CC0 1.0 | [homepage] | [download] |
| 2017 | Danbooru2017 | A large-scale anime image database with 2.9m+ images and 77.5m+ tags. | CC0 1.0 | [homepage] | [download] |
Metrics
| Name | Description | Paper | Code | Homepage |
|---|---|---|---|---|
| FID (Fréchet Inception Distance) | Measures the distance between feature distributions of real and generated images using Inception network activations. | [paper] | [code] | N/A |
| KID (Kernel Inception Distance) | An unbiased alternative to FID that uses kernel methods to compare distributions. | [paper] | [code] | N/A |
| LPIPS (Learned Perceptual Image Patch Similarity) | A deep learning-based perceptual similarity metric that correlates well with human perception. | [paper] | [code] | [homepage] |
| ArtFID | A metric specifically designed for evaluating neural style transfer quality. | [paper] | [code] | N/A |
| ArcFace (ID Similarity) | Face recognition model used to measure identity preservation in face stylization. | [paper] | [code] | [homepage] |
| CLIPScore | A reference-free evaluation metric using CLIP to measure image-text compatibility. | [paper] | [code] | N/A |
| Aesthetic Score | A CLIP-based aesthetic predictor that estimates how visually appealing an image is. | N/A | [code] | N/A |
| StyleID ( ID Similarity under Stylization) | Face recognition model specifically designed to measure identity preservation in face stylization. | [paper] | [code] | [homepage] |
awesome
awesome-list
face-editing
face-stylization
stable-diffusion
style
stylegan
style-transfer
styletransfer
stylization
Contributors
Similar repos
A curated collection of papers on portrait style transfer
29
40 commits
updated Aug 20, 2026
README
Awesome-Portraits-Style-Transfer
An archive of studies related to portrait style transfer
Table of Contents
Papers
Based on GANs
| Date | Title | Publish | Paper | Code | Homepage | Recom |
|---|---|---|---|---|---|---|
| 2024.11 | BeautyBank: Encoding Facial Makeup in Latent Space | WACV 2025 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.09 | PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation | ArXiv 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.08 | Multi-Style Facial Sketch Synthesis through Masked Generative Modeling | ArXiv 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.04 | ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesis | ICPR 2024 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.03 | AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning | CVPRW 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.03 | DoesFS: Deformable One-shot Face Stylization via DINO Semantic Guidance | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2023.11 | 3D Face Style Transfer with a Hybrid Solution of NeRF and Mesh Rasterization | WACV 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2023.05 | MMFS: Multi-Modal Face Stylization with a Generative Prior | PG 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.03 | Fix the Noise: Disentangling Source Feature for Controllable Domain Translation | CVPR 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.03 | StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces | ICCV 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.11 | DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains | SIGGRAPH Asia 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.10 | TargetCLIP: Official PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer | ECCV 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.09 | VToonify: Controllable High-Resolution Portrait Video Style Transfer | SIGGRAPH Asia 2022 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2022.09 | GODA: Generalized One-shot Domain Adaptation of Generative Adversarial Networks | NeurIPS 2022 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2022.07 | DCT-Net: Domain-Calibrated Translation for Portrait Stylization | SIGGRAPH 2022 (TOG) | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.06 | Real-Time Portrait Stylization on the Edge | ArXiv 2022 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2022.04 | Unsupervised Image-to-Image Translation with Generative Prior | CVPR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.03 | CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning | ArXiv 2022 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2022.03 | A Style-aware Discriminator for Controllable Image Translation | CVPR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2022.03 | Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer | CVPR 2022 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2022.03 | OneShotCLIP: One-Shot Adaptation of GAN in Just One CLIP | TPAMI 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.12 | SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing | CVPR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.12 | BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation | NeurIPS 2021 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2021.11 | MTG: Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks | ICLR 2022 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2021.09 | CariMe: Unpaired Caricature Generation with Multiple Exaggerations | TMM 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.09 | StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation | SIGGRAPH 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.09 | ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement | ICCV 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.09 | SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation | ICCV 2021 | [paper] | [code] | [homepage] | ⭐️ |
| 2021.07 | AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning | SIGGRAPH 2021 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2021.07 | Making Robots Draw A Vivid Portrait In Two Minutes | IROS 2020 | [paper] | [code] | [homepage] | ⭐️ |
| 2021.07 | Line Drawings for Face Portraits from Photos using Global and Local Structure based GANs | IEEE 2020 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.06 | Fine-Tuning StyleGAN2 For Cartoon Face Generation | Arxiv 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.05 | MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing | AAAI 2021 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2021.04 | CPM: Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfer | CVPR 2021 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2021.02 | AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation | TMM 2021 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2019.07 | U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation | ICLR 2020 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2019.07 | Landmark Assisted CycleGAN for Cartoon Face Generation | ArXiv 2019 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2019.06 | APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs | CVPR 2019 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2018.11 | WarpGAN: Automatic Caricature Generation | CVPR 2019 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2017.03 | Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization | ICCV 2017 | [paper] | [code] | [homepage] | ⭐️⭐️ |
Based on Diffusion Models
| Date | Title | Publish | Paper | Code | Homepage | Recom |
|---|---|---|---|---|---|---|
| 2025.11 | Inversion-Free Style Transfer with Dual Rectified Flows | Arxiv 2025 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2025.09 | StyleFace: Forging a Masterpiece from Any Face - A Universal Framework for Face Stylization | ICLR 2026 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2025.07 | DGPST: Dual Graph Prompt Style Transfer | ICCV 2025 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2025.05 | TF-SA: Training Free Stylized Abstraction | ArXiv 2025 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2025.05 | OmniStyle: Filtering High Quality Style Transfer Data at Scale | CVPR 2025 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2025.04 | GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Faces | ArXiv 2025 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2025.01 | InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation | ICLR 2025 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2025.01 | StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer | CVPR 2025 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2024.12 | StyleMaster: Stylize Your Video with Artistic Generation and Translation | CVPR 2025 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2024.09 | StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models | ECCV 2024 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2024.08 | CSGO: Content-Style Composition in Text-to-Image Generation | NeurIPS 2025 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2024.08 | MagicFace: Training-free Universal-Style Human Image Customized Synthesis | ArXiv 2024 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.08 | ZePo: Zero-Shot Portrait Stylization with Faster Sampling | ACM Multimedia 2024 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
| 2024.07 | InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.05 | Pair Customization: Customizing Text-to-Image Models with a Single Image Pair | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.04 | Style-Booth: Image Style Editing with Multimodal Instruction | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.04 | InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2024.04 | B-LoRA: Implicit Style-Content Separation using B-LoRA | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.03 | DiffStyler: An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration | AAAI 2026 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2024.03 | A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification | ICASSP 2024 | [paper] | N/A | N/A | ⭐️⭐️ |
| 2024.02 | VisualStylePrompt: Visual Style Prompting with Swapping Self-Attention | ArXiv 2024 | [paper] | N/A | [homepage] | ⭐️ |
| 2024.01 | FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2024.01 | CreativeSynth: Creative Blending and Synthesis of Visual Arts based on Multimodal Diffusion | ArXiv 2024 | [paper] | [code] | N/A | ⭐️ |
| 2024.01 | InstantID: Zero-shot Identity-Preserving Generation in Seconds | ArXiv 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | StyleID: Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | FaceStudio: Put Your Face Everywhere in Seconds | ArXiv 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.12 | Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting | ArXiv 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.12 | StyleAligned: Style Aligned Image Generation via Shared Attention | CVPR 2024 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2023.08 | IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models | ArXiv 2023 | [paper] | [code] | [homepage] | ⭐️⭐️⭐️ |
| 2023.07 | VCT: General Image-to-Image Translation with One-Shot Image Guidance | ICCV 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.06 | Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation | SIGGRAPH Asia 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.11 | ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models | SIGGRAPH Asia 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2023.05 | Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer | ArXiv 2023 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2023.03 | ZeCon: Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer | ICCV 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2022.11 | InST: Inversion-Based Style Transfer with Diffusion Models | CVPR 2023 | [paper] | [code] | N/A | ⭐️⭐️⭐️ |
Others
| Date | Title | Publish | Paper | Code | Homepage | Recom |
|---|---|---|---|---|---|---|
| 2023.09 | Portrait Stylization: Artistic Style Transfer with Auxiliary Networks for Human Face Stylization | ArXiv 2023 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.12 | CLIPstyler: Image Style Transfer with a Single Text Condition | CVPR 2022 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.08 | AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer | ICCV 2021 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2021.03 | ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows | CVPR 2021 | [paper] | [code] | N/A | ⭐️⭐️ |
| 2018.06 | Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration | CVPR 2018 | [paper] | [code] | [homepage] | ⭐️⭐️ |
| 2018.01 | Face Sketch Synthesis with Style Transfer using Pyramid Column Feature | WACV 2018 | [paper] | [code] | N/A | ⭐️⭐️ |
Repositories
Datasets
Face Datasets
| Year | Name | Description | License | HomePage | Download |
|---|---|---|---|---|---|
| 2019 | FFHQ (Flickr-Faces-HQ) | A high-quality dataset of 70,000 human face images at 1024×1024 resolution with considerable variation in age, ethnicity and background. | CC BY-NC-SA 4.0 | [homepage] | [download] |
| 2018 | CelebA-HQ | A high-quality version of CelebA dataset consisting of 30,000 face images at 1024×1024 resolution. | CC BY-NC 4.0 | [homepage] | [download] |
Stylized Face Datasets
| Year | Name | Description | License | HomePage | Download |
|---|---|---|---|---|---|
| 2025 | FFHQ-Makeup | A high-quality synthetic makeup dataset with 90K paired bare-makeup images (18K identities × 5 makeup styles) at 512×512 resolution. | CC BY-NC-SA 4.0 | [homepage] | [download] |
| 2024 | SKSF-A | An high-resolution dataset of professional artist drawn face sketches. | CC BY-NC-SA 4.0 | [homepage] | [download] |
| 2022 | ArcaneFaces | A handcrafted high-quality dataset of over 3400 faces from Arcane. | CC BY 4.0 | [homepage] | [download] |
| 2021 | AAHQ | A high-quality image dataset of artistic-face images. | N/A | [homepage] | [download] |
| 2020 | Metaface | A dataset containing high-quality artistic/stylized face images for machine learning applications. | CC0 | [homepage] | [download] |
| 2020 | Riga Faces | A dataset of 165 high-quality images of mascarons seen on art nouveau buildings in Riga, Latvia. | CC0 | [homepage] | [download] |
| 2020 | Danbooru2020 | A large-scale anime image database with 4.2m+ images and 130m+ tags. | CC0 1.0 | [homepage] | [download] |
| 2020 | Aligned Ukiyo-e Faces | Over five thousand aligned ukiyo-e faces at 1024x1024 pixel resolution. | CC BY-SA 4.0 | [homepage] | [download] |
| 2020 | Cartoon Faces | A dataset of cartoon (Disney) faces for machine learning applications. | CC BY-SA 4.0 | [homepage] | [download] |
| 2020 | Comic faces (paired, synthetic) | A dataset of paired synthetic comic faces for machine learning applications. | CC BY 4.0 | [homepage] | [download] |
| 2020 | Comic faces (paired, synthetic, v2) | A dataset of paired synthetic comic faces for machine learning applications, version 2. | CC BY 4.0 | [homepage] | [download] |
| 2019 | Danbooru2019 | A large-scale anime image database with 3.69m+ images and 108m+ tags. | CC0 1.0 | [homepage] | [download] |
| 2019 | APDrawingGAN Dataset | A dataset used for generating artistic portrait drawings from face photos with hierarchical GANs. | Apache-2.0 | [homepage] | [download] |
| 2018 | Danbooru2018 | A large-scale anime image database with 3.3m+ images and 92.7m+ tags. | CC0 1.0 | [homepage] | [download] |
| 2017 | Danbooru2017 | A large-scale anime image database with 2.9m+ images and 77.5m+ tags. | CC0 1.0 | [homepage] | [download] |
Metrics
| Name | Description | Paper | Code | Homepage |
|---|---|---|---|---|
| FID (Fréchet Inception Distance) | Measures the distance between feature distributions of real and generated images using Inception network activations. | [paper] | [code] | N/A |
| KID (Kernel Inception Distance) | An unbiased alternative to FID that uses kernel methods to compare distributions. | [paper] | [code] | N/A |
| LPIPS (Learned Perceptual Image Patch Similarity) | A deep learning-based perceptual similarity metric that correlates well with human perception. | [paper] | [code] | [homepage] |
| ArtFID | A metric specifically designed for evaluating neural style transfer quality. | [paper] | [code] | N/A |
| ArcFace (ID Similarity) | Face recognition model used to measure identity preservation in face stylization. | [paper] | [code] | [homepage] |
| CLIPScore | A reference-free evaluation metric using CLIP to measure image-text compatibility. | [paper] | [code] | N/A |
| Aesthetic Score | A CLIP-based aesthetic predictor that estimates how visually appealing an image is. | N/A | [code] | N/A |
| StyleID ( ID Similarity under Stylization) | Face recognition model specifically designed to measure identity preservation in face stylization. | [paper] | [code] | [homepage] |
awesome
awesome-list
face-editing
face-stylization
stable-diffusion
style
stylegan
style-transfer
styletransfer
stylization