# In-Token Learning for High-Fidelity Image Restoration via Diffusion Transformers

arXiv: https://arxiv.org/abs/2609.33523 · HTML: https://mlsanity.com/paper/2609.33523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [Instance-aware Image Colorization](https://mlsanity.com/paper/2005.10825/) (2020)
- [DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation](https://mlsanity.com/paper/2410.18666/) (2024)
- [DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders](https://mlsanity.com/paper/2212.11613/) (2022)
- [BigColor: Colorization using a Generative Color Prior for Natural Images](https://mlsanity.com/paper/2207.09685/) (2022)
- [FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution](https://mlsanity.com/paper/2411.18824/) (2024)
- [Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration](https://mlsanity.com/paper/2504.15159/) (2025)

## Abstract (arXiv)

We present In-Token Learning, an image restoration framework that adapts a pretrained diffusion transformer using conditional rectified flow matching. Clean targets paired with degraded inputs supervise transport from Gaussian noise to restored images. Spatially aligned degraded-image tokens are fused with evolving latent tokens along the channel dimension, preserving the image-token count at a given resolution. Direct Low-Quality Guidance (DLG) combines frozen degraded-image embeddings with a fixed task prompt through the native conditioning pathway, without a trainable ControlNet-style branch or image captioning. We evaluate super-resolution and denoising on DIV2K, LSDIR, FFHQ, RealLQ250, and RealPhoto60, and automatic colorization on DIV2K and LSDIR. The tasks use separately trained checkpoints under the same framework. Results show competitive fidelity and perceptual quality under the evaluated protocols, with weaker generalization on RealLQ250. We report full-image QHD (2560×1440) inference and a tiled 12K restoration demonstration of Along the River During the Qingming Festival. Attention cost still increases with resolution. This technical report preserves the early broader study underlying Fill2SR, which subsequently developed the real-world super-resolution direction.