TeleStyle: Content-Preserving Style Transfer in Images and Videos

TL;DR

TeleStyle is a novel, lightweight model for content-preserving style transfer in images and videos, utilizing curriculum learning and a new dataset to achieve state-of-the-art results in style similarity, content fidelity, and visual quality.

Contribution

The paper introduces TeleStyle, a new model that combines curriculum continual learning and a specialized dataset to improve style transfer quality and generalization for images and videos.

Findings

Achieves state-of-the-art performance in style similarity and content preservation.

Effectively generalizes to unseen styles through curriculum continual learning.

Enhances temporal consistency in video stylization.

Abstract

Content-preserving style transfer, generating stylized outputs based on content and style references, remains a significant challenge for Diffusion Transformers (DiTs) due to the inherent entanglement of content and style features in their internal representations. In this technical report, we present TeleStyle, a lightweight yet effective model for both image and video stylization. Built upon Qwen-Image-Edit, TeleStyle leverages the base model's robust capabilities in content preservation and style customization. To facilitate effective training, we curated a high-quality dataset of distinct specific styles and further synthesized triplets using thousands of diverse, in-the-wild style categories. We introduce a Curriculum Continual Learning framework to train TeleStyle on this hybrid dataset of clean (curated) and noisy (synthetic) triplets. This approach enables the model to generalize to unseen styles without compromising precise content fidelity. Additionally, we introduce a video-to-video stylization module to enhance temporal consistency and visual quality. TeleStyle achieves state-of-the-art performance across three core evaluation metrics: style similarity, content consistency, and aesthetic quality. Code and pre-trained models are available at https://github.com/Tele-AI/TeleStyle