TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers

• URL: http://arxiv.org/abs/2603.08928v1
• Date: Mon, 09 Mar 2026 20:57:19 GMT
• Title: TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers
• Abstract summary: Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution.<n>We propose TIDE, a training-free text-to-image (T2I) extrapolation method that enables generation with arbitrary resolution and aspect ratio without additional sampling overhead.
• Score: 1.2927626330863309
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by sharpening attention distributions, but fail to preserve fine-grained semantic details and introduce obvious artifacts. In this work, we analyze the characteristics of DiTs and propose TIDE, a training-free text-to-image (T2I) extrapolation method that enables generation with arbitrary resolution and aspect ratio without additional sampling overhead. We identify the core factor for prompt information loss, and introduce a text anchoring mechanism to correct the imbalance between text and image tokens. To further eliminate artifacts, we design a dynamic temperature control mechanism that leverages the pattern of spectral progression in the diffusion process. Extensive evaluations demonstrate that TIDE delivers high-quality resolution extrapolation capability and integrates seamlessly with existing state-of-the-art methods.

Related papers

• Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations [50.60539317126614]
  Infrared-visible image fusion under realistic degradation scenarios is a challenging task.<n>Recent studies indicate that text can provide prior information about degradation characteristics.<n>We propose TGFusion, a text-guided latent-space flow matching framework.
  arXiv  Detail & Related papers  (2026-08-01T08:43:26Z)
• DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models [15.472520897269147]
  We propose Data Injection and Contrastive Trajectory Refinement (DICT) for conditional image generation tasks.<n>DICT integrates noise-perturbed conditional signals into early denoising stages and applies Contrastive Trajectory Refinement across adjacent denoising states.<n>Experiments show consistent gains in fidelity and perceptual quality over representative task-specific and loss-guided baselines.
  arXiv  Detail & Related papers  (2026-07-04T14:44:06Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• Accurate Latent Inversion for Generative Image Steganography via Rectified Flow [5.404219831398271]
  Steganography based on diffusion models has attracted increasing attention due to its ability to generate high-quality images and exhibit strong robustness.<n>We propose textbfRF-Stego, a novel generative image steganography method that enables accurate latent inversion and significantly improves extraction accuracy.<n> Experimental results show RF-Stego outperforms state-of-the-art methods in terms of extraction accuracy, image quality, robustness, security and generation efficiency.
  arXiv  Detail & Related papers  (2025-08-01T08:46:32Z)
• InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models [10.213390634031049]
  Current IIL methods face two main challenges: a tendency towards overconfidence and difficulty in detecting subtle tampering boundaries.<n>We propose a new paradigm that treats IIL as a conditional mask generation task utilizing diffusion models.<n>Our method, InpDiffusion, utilizes the denoising process enhanced by the integration of image semantic conditions to progressively refine predictions.
  arXiv  Detail & Related papers  (2025-01-06T07:32:12Z)
• Training-Free Layout-to-Image Generation with Marginal Attention Constraints [73.55660250459132]
  We propose a training-free layout-to-image (L2I) approach, which eliminates the need for additional modules or fine-tuning.<n>Specifically, we use text-visual cross-attention feature maps to quantify inconsistencies between the layout of the generated images and the provided instructions.<n>We leverage pixel-to-pixel correlations in the self-attention feature maps to align cross-attention maps and combine three loss functions constrained by boundary attention to update latent features.
  arXiv  Detail & Related papers  (2024-11-15T05:44:45Z)
• FiT: Flexible Vision Transformer for Diffusion Model [81.85667773832279]
  We present a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. Comprehensive experiments demonstrate the exceptional performance of FiT across a broad range of resolutions.
  arXiv  Detail & Related papers  (2024-02-19T18:59:07Z)
• Image Inpainting via Tractable Steering of Diffusion Models [48.16994134964729]
  This paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior.<n>Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs)
  arXiv  Detail & Related papers  (2023-11-28T21:14:02Z)
• Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis [45.19847146506007]
  Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. This paper focuses on adapting text-to-image diffusion models to handle variety while maintaining visual fidelity.
  arXiv  Detail & Related papers  (2023-06-14T17:23:07Z)
• Controlling Text-to-Image Diffusion by Orthogonal Finetuning [74.21549380288631]
  We introduce a principled finetuning method -- Orthogonal Finetuning (OFT) for adapting text-to-image diffusion models to downstream tasks. Unlike existing methods, OFT can provably preserve hyperspherical energy which characterizes the pairwise neuron relationship on the unit hypersphere. We empirically show that our OFT framework outperforms existing methods in generation quality and convergence speed.
  arXiv  Detail & Related papers  (2023-06-12T17:59:23Z)

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.