Your Pre-trained Diffusion Model Secretly Knows Restoration

• URL: http://arxiv.org/abs/2604.04924v1
• Date: Mon, 06 Apr 2026 17:59:04 GMT
• Title: Your Pre-trained Diffusion Model Secretly Knows Restoration
• Abstract summary: We show that pre-trained diffusion models inherently possess restoration behavior, which can be unlocked by directly learning prompt embeddings.<n>We introduce our lightweight learned prompts on the pre-trained WAN video model and FLUX image models, converting them into high-performing restoration models.
• Score: 55.7186754179308
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on fine-tuning or Control-Net style modules to leverage the pre-trained diffusion model's priors for AiOR. In this work, we show that these pre-trained diffusion models inherently possess restoration behavior, which can be unlocked by directly learning prompt embeddings at the output of the text encoder. Interestingly, this behavior is largely inaccessible through text prompts and text-token embedding optimization. Furthermore, we observe that naive prompt learning is unstable because the forward noising process using degraded images is misaligned with the reverse sampling trajectory. To resolve this, we train prompts within a diffusion bridge formulation that aligns training and inference dynamics, enforcing a coherent denoising path from noisy degraded states to clean images. Building on these insights, we introduce our lightweight learned prompts on the pre-trained WAN video model and FLUX image models, converting them into high-performing restoration models. Extensive experiments demonstrate that our approach achieves competitive performance and generalization across diverse degradations, while avoiding fine-tuning and restoration-specific control modules.

Related papers

• Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models [0.0]
  h-space patching, the dominant paradigm for training-free diffusion editing, systematically fails for global, low-level transformations.<n>We introduce a novel, generalized framework for image-editing in unconditional diffusion models without explicit training.
  arXiv  Detail & Related papers  (2026-05-29T11:11:04Z)
• ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models [12.021923446217722]
  Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models.<n>Existing adversarial approaches for exploiting this leakage are constrained by fundamental limitations.<n>We introduce ReLAPSe, a policy-based adversarial framework that reformulates concept restoration as a reinforcement learning problem.
  arXiv  Detail & Related papers  (2026-01-30T21:56:50Z)
• Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations [53.91818843831925]
  We propose NExT-Vid, a novel autoregressive visual generative pretraining framework.<n>We introduce a context-isolated autoregressive predictor to decouple semantic representation from target decoding.<n>Through context-isolated flow-matching pretraining, our approach achieves strong representations.
  arXiv  Detail & Related papers  (2025-12-24T07:07:08Z)
• Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement [63.54516423266521]
  Pre-Trained Diffusion-Based (PTDB) methods often sacrifice content fidelity to attain higher perceptual realism.<n>We propose a novel optimization strategy for conditioning in pre-trained diffusion models, enhancing fidelity while preserving realism and aesthetics.<n>Our approach is plug-and-play, seamlessly integrating into existing diffusion networks to provide more effective control.
  arXiv  Detail & Related papers  (2025-10-20T02:40:06Z)
• Harnessing Diffusion-Yielded Score Priors for Image Restoration [29.788482710572307]
  Deep image restoration models aim to learn a mapping from degraded image space to natural image space.<n>Three major classes of methods have emerged, including MSE-based, GAN-based, and diffusion-based methods.<n>We propose a novel method, HYPIR, to address these challenges.
  arXiv  Detail & Related papers  (2025-07-28T07:55:34Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)
• ADIR: Adaptive Diffusion for Image Reconstruction [42.90778718695398]
  Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics.<n>We introduce a conditional sampling framework that leverages the powerful priors learned by diffusion models while enforcing consistency with the available measurements.<n>We employ LoRA-based adaptation using images that are semantically and visually similar to the degraded input, efficiently retrieved from a large and diverse dataset.
  arXiv  Detail & Related papers  (2022-12-06T18:39:58Z)

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.