Control and Realism: Best of Both Worlds in Layout-to-Image without Training

• URL: http://arxiv.org/abs/2506.15563v1
• Date: Wed, 18 Jun 2025 15:39:02 GMT
• Title: Control and Realism: Best of Both Worlds in Layout-to-Image without Training
• Authors: Bonan Li, Yinhan Hu, Songhua Liu, Xinchao Wang,
• Abstract summary: We present WinWinLay, a training-free method for layout-to-Image generation.<n>We propose two key strategies, Non-local Attention Energy and Adaptive Update, that collaboratively enhance control precision and realism.<n>WinWinLay excels in controlling element placement and achieving photorealistic visual fidelity, outperforming the current state-of-the-art methods.
• Score: 59.16447569868382
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Layout-to-Image generation aims to create complex scenes with precise control over the placement and arrangement of subjects. Existing works have demonstrated that pre-trained Text-to-Image diffusion models can achieve this goal without training on any specific data; however, they often face challenges with imprecise localization and unrealistic artifacts. Focusing on these drawbacks, we propose a novel training-free method, WinWinLay. At its core, WinWinLay presents two key strategies, Non-local Attention Energy Function and Adaptive Update, that collaboratively enhance control precision and realism. On one hand, we theoretically demonstrate that the commonly used attention energy function introduces inherent spatial distribution biases, hindering objects from being uniformly aligned with layout instructions. To overcome this issue, non-local attention prior is explored to redistribute attention scores, facilitating objects to better conform to the specified spatial conditions. On the other hand, we identify that the vanilla backpropagation update rule can cause deviations from the pre-trained domain, leading to out-of-distribution artifacts. We accordingly introduce a Langevin dynamics-based adaptive update scheme as a remedy that promotes in-domain updating while respecting layout constraints. Extensive experiments demonstrate that WinWinLay excels in controlling element placement and achieving photorealistic visual fidelity, outperforming the current state-of-the-art methods.

Related papers

• RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generation [16.038598998902767]
  Text-to-image (T2I) diffusion models have shown remarkable success in generating high-quality images from text prompts.<n>We propose a flexible feature injection framework that decouples the injection timestep from the denoising process.<n>Our approach achieves state-of-the-art performance across diverse zero-shot conditioning scenarios.
  arXiv  Detail & Related papers  (2025-07-03T16:56:15Z)
• TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization [59.412236435627094]
  TALE is a training-free framework harnessing the generative capabilities of text-to-image diffusion models. We equip TALE with two mechanisms dubbed Adaptive Latent Manipulation and Energy-guided Latent Optimization. Our experiments demonstrate that TALE surpasses prior baselines and attains state-of-the-art performance in image-guided composition.
  arXiv  Detail & Related papers  (2024-08-07T08:52:21Z)
• Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration [64.84134880709625]
  We show that it is possible to perform domain adaptation via the noise space using diffusion models.<n>In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful diffusion loss.<n>We present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model.
  arXiv  Detail & Related papers  (2024-06-26T17:40:30Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control [73.6361029556484]
  Embodied AI agents require a fine-grained understanding of the physical world mediated through visual and language inputs. We consider pre-trained text-to-image diffusion models, which are explicitly optimized to generate images from text prompts. We show that Stable Control Representations enable learning policies that exhibit state-of-the-art performance on OVMM, a difficult open-vocabulary navigation benchmark.
  arXiv  Detail & Related papers  (2024-05-09T15:39:54Z)
• Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis [15.76266032768078]
  This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries.<n>We first introduce vision guidance as a foundational spatial cue within the perturbed distribution.<n>We propose a universal framework, Layered Rendering Diffusion (LRDiff), which constructs an image-rendering process with multiple layers.
  arXiv  Detail & Related papers  (2023-11-30T10:36:19Z)
• PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training [4.336877104987131]
  Unsupervised domain adaptation is a promising technique for semantic segmentation. We present a novel framework for unsupervised domain adaptation based on the notion of target-domain consistency training. Our approach is simpler, easier to implement, and more memory-efficient during training.
  arXiv  Detail & Related papers  (2021-05-17T19:36:28Z)
• Unsupervised Metric Relocalization Using Transform Consistency Loss [66.19479868638925]
  Training networks to perform metric relocalization traditionally requires accurate image correspondences. We propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration. We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.
  arXiv  Detail & Related papers  (2020-11-01T19:24:27Z)

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.