TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillation

• URL: http://arxiv.org/abs/2606.20709v1
• Date: Tue, 16 Jun 2026 10:45:33 GMT
• Title: TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillation
• Abstract summary: Given a content reference and a style reference, content-preserving style transfer requires the model to generate stylized outputs.<n>TeleStyle V1 is trained with photorealistic content reference and artistic style reference.<n>TeleStyle V2 supports Content-Style references in the forms of Realistic-and-Realistic (RnR), Realistic-and-Stylized (RnS), Stylized-and-Stylized (SnS)
• Score: 54.141830240935455
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given a content reference and a style reference, content-preserving style transfer requires the model to generate stylized outputs with content and style consistency. We introduced TeleStyle V1 to tackle this problem. However, TeleStyle V1 is trained with photorealistic content reference and artistic style reference, which makes it incapable to cope with artistic content reference and realistic style reference in most cases. In this paper, we designed a Self-Distillation data synthesis strategy to construct such triplets from TeleStyle V1. Trained with such self-distilled triplets, our TeleStyle V2 supports Content-Style references in the forms of Realistic-and-Realistic (RnR), Realistic-and-Stylized (RnS), Stylized-and-Realistic (SnR), Stylized-and-Stylized (SnS). In addition, we found Distribution Matching Distillation could preserve the general text-guided image editing capability of the foundation model and fix the content consistency degradation caused by SFT process. Through quantitative evaluations, our TeleStyleV2-QIE-2509-DMD performs at least on par with Qwen-Image-Edit-2509-DMD, demonstrating strong general image editing skills beyond content-preserving style transfer. We observed the content/style reference order confusion problem in TeleStyle V1 and further introduced prompt enhancer to solve it. TeleStyle V2 uses Qwen-Image-Edit's VLM encoder, Qwen2.5-VL-7B, to generate content prompt and style prompt for free. TeleStyle V2 could achieve comparable style transfer performance with state-of-the-art commercial model, gemini-3-pro-image-preview.

Related papers

• M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting [21.399777116251858]
  We introduce a novel real-time styling technique M2StyleGS to generate a sequence of precisely color-mapped views.<n>M2StyleGS achieves better visual quality and surpasses the previous work by up to 32.92% in terms of consistency.
  arXiv  Detail & Related papers  (2026-04-04T15:51:56Z)
• TeleStyle: Content-Preserving Style Transfer in Images and Videos [52.76027947278353]
  We present TeleStyle, a lightweight model for both image and video stylization.<n>We curated a high-quality dataset of distinct specific styles and synthesized triplets using thousands of diverse, in-the-wild style categories.<n>TeleStyle achieves state-of-the-art performance across three core evaluation metrics: style similarity, content consistency, and aesthetic quality.
  arXiv  Detail & Related papers  (2026-01-28T02:16:03Z)
• QwenStyle: Content-Preserving Style Transfer with Qwen-Image-Edit [54.11909509184315]
  We propose the first content-preserving style transfer model trained on Qwen-Image-Edit.<n>QwenStyle V1 achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality.
  arXiv  Detail & Related papers  (2026-01-08T10:22:51Z)
• DreamStyle: A Unified Framework for Video Stylization [18.820518165759403]
  We introduce DreamStyle, a unified framework for video stylization.<n>It supports (1) text-guided, (2) style-image-guided, and (3) first-frame-guided video stylization.<n>Both qualitative and quantitative evaluations demonstrate that DreamStyle is competent in all three video stylization tasks.
  arXiv  Detail & Related papers  (2026-01-06T07:42:12Z)
• StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter [78.75422651890776]
  StyleCrafter is a generic method that enhances pre-trained T2V models with a style control adapter. To promote content-style disentanglement, we remove style descriptions from the text prompt and extract style information solely from the reference image. StyleCrafter efficiently generates high-quality stylized videos that align with the content of the texts and resemble the style of the reference images.
  arXiv  Detail & Related papers  (2023-12-01T03:53:21Z)
• StyleAdapter: A Unified Stylized Image Generation Model [97.24936247688824]
  StyleAdapter is a unified stylized image generation model capable of producing a variety of stylized images. It can be integrated with existing controllable synthesis methods, such as T2I-adapter and ControlNet.
  arXiv  Detail & Related papers  (2023-09-04T19:16:46Z)
• Arbitrary Style Transfer via Multi-Adaptation Network [109.6765099732799]
  A desired style transfer, given a content image and referenced style painting, would render the content image with the color tone and vivid stroke patterns of the style painting. A new disentanglement loss function enables our network to extract main style patterns and exact content structures to adapt to various input images.
  arXiv  Detail & Related papers  (2020-05-27T08:00:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.