# A training-free framework for high-fidelity appearance transfer via diffusion transformers

arXiv: https://arxiv.org/abs/2603.26767 · HTML: https://mlsanity.com/paper/2603.26767/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 20 of its 21 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Rectified Flow: A Marginal Preserving Approach to Optimal Transport](https://mlsanity.com/paper/2209.14577/) (2022)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Stable Flow: Vital Layers for Training-Free Image Editing](https://mlsanity.com/paper/2411.14430/) (2024)
- [DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing](https://mlsanity.com/paper/2402.02583/) (2024)
- [FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing](https://mlsanity.com/paper/2412.07517/) (2024)
- [DreamEdit: Subject-driven Image Editing](https://mlsanity.com/paper/2306.12624/) (2023)
- [ZeST: Zero-Shot Material Transfer from a Single Image](https://mlsanity.com/paper/2404.06425/) (2024)
- [MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models](https://mlsanity.com/paper/2502.06606/) (2025)
- [Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models](https://mlsanity.com/paper/2406.07008/) (2024)
- [FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers](https://mlsanity.com/paper/2507.15249/) (2025)

## Abstract (arXiv)

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic scene structure. We address this by proposing the first training-free framework specifically designed to tame DiTs for high-fidelity appearance transfer. Our core is a synergistic system that disentangles structure and appearance. We leverage high-fidelity inversion to establish a rich content prior for the source image, capturing its lighting and micro-textures. A novel attention-sharing mechanism then dynamically fuses purified appearance features from a reference, guided by geometric priors. Our unified approach operates at 1024px and outperforms specialized methods on tasks ranging from semantic attribute transfer to fine-grained material application. Extensive experiments confirm our state-of-the-art performance in both structural preservation and appearance fidelity.