StyO: Stylize Your Face in Only One-Shot

by   Bonan Li, et al.

This paper focuses on face stylization with a single artistic target. Existing works for this task often fail to retain the source content while achieving geometry variation. Here, we present a novel StyO model, ie. Stylize the face in only One-shot, to solve the above problem. In particular, StyO exploits a disentanglement and recombination strategy. It first disentangles the content and style of source and target images into identifiers, which are then recombined in a cross manner to derive the stylized face image. In this way, StyO decomposes complex images into independent and specific attributes, and simplifies one-shot face stylization as the combination of different attributes from input images, thus producing results better matching face geometry of target image and content of source one. StyO is implemented with latent diffusion models (LDM) and composed of two key modules: 1) Identifier Disentanglement Learner (IDL) for disentanglement phase. It represents identifiers as contrastive text prompts, ie. positive and negative descriptions. And it introduces a novel triple reconstruction loss to fine-tune the pre-trained LDM for encoding style and content into corresponding identifiers; 2) Fine-grained Content Controller (FCC) for the recombination phase. It recombines disentangled identifiers from IDL to form an augmented text prompt for generating stylized faces. In addition, FCC also constrains the cross-attention maps of latent and text features to preserve source face details in results. The extensive evaluation shows that StyO produces high-quality images on numerous paintings of various styles and outperforms the current state-of-the-art. Code will be released upon acceptance.


page 1

page 4

page 7

page 8

page 9


Face Transformer: Towards High Fidelity and Accurate Face Swapping

Face swapping aims to generate swapped images that fuse the identity of ...

FlowFace++: Explicit Semantic Flow-supervised End-to-End Face Swapping

This work proposes a novel face-swapping framework FlowFace++, utilizing...

AnyFace: Free-style Text-to-Face Synthesis and Manipulation

Existing text-to-image synthesis methods generally are only applicable t...

Face Swapping as A Simple Arithmetic Operation

We propose a novel high-fidelity face swapping method called "Arithmetic...

TextStyleBrush: Transfer of Text Aesthetics from a Single Example

We present a novel approach for disentangling the content of a text imag...

One-shot Face Reenactment

To enable realistic shape (e.g. pose and expression) transfer, existing ...

Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation

In this paper, we are interested in generating fine-grained cartoon face...

Please sign up or login with your details

Forgot password? Click here to reset