mlsanityData to 7 Oct 2026

SLayR: Scene Layout Generation with Rectified Flow

arXiv 2412.05003 ↗First posted 6 Dec 2024cs.CVcited by 1

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We introduce SLayR, Scene Layout Generation with Rectified flow, a novel transformer-based model for text-to-layout generation which can then be paired with existing layout-to-image models to produce images. SLayR addresses a domain in which current text-to-image pipelines struggle: generating scene layouts that are of significant variety and plausibility, when the given prompt is ambiguous and does not provide constraints on the scene. SLayR surpasses existing baselines including LLMs in unconstrained generation, and can generate layouts from an open caption set. To accurately evaluate the layout generation, we introduce a new benchmark suite, including numerical metrics and a carefully designed repeatable human-evaluation procedure that assesses the plausibility and variety of generated images. We show that our method sets a new state of the art for achieving both at the same time, while being at least 3x times smaller in the number of parameters.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 41 of its 49 references that are in the map. First posted on arXiv 6 Dec 2024.

Builds on

41 of 49 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance24 May
  2. 2024LayoutFlow: Flow Matching for Layout Generation27 Mar
  3. 2024InstanceDiffusion: Instance-level Control for Image Generation5 Feb
  4. 2024Image Synthesis with Graph Conditioning: CLIP-Guided Diffusion Models for Scene Graphs25 Jan
  5. 2023Rich Human Feedback for Text-to-Image Generation15 Dec
  6. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs30 Nov
  7. 2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion20 Jul
  8. 2023LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models23 May
  9. 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models21 Mar
  10. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generation14 Mar
  11. 2023Text-to-image Diffusion Models in Generative AI: A Survey14 Mar
  12. 2023DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer7 Mar
3 more
  1. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation16 Feb
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  3. 2023GLIGEN: Open-Set Grounded Text-to-Image Generation17 Jan

Other references · 26

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  7. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  8. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  9. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 465
  10. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  11. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  12. 2023Training-Free Layout Control with Cross-Attention Guidancecited by 312
14 more
  1. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  2. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 130
  3. 2023Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometrycited by 121
  4. 2018Image Generation from Layoutcited by 105
  5. 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splattingcited by 104
  6. 2019Neural Design Network: Graphic Layout Generation with Constraintscited by 83
  7. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  8. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 76
  9. 2023Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generationcited by 66
  10. 2020Object-Centric Image Generation from Layoutscited by 57
  11. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  12. 2024Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databasescited by 43
  13. 2023Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generationcited by 11
  14. 2024DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modelingcited by 7

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generationcited by 37

Similar, not cited

Close in wording, no citation either way

  1. 2025Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers
  2. 2023LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
  3. 2023Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
  4. 2025A Two-Stage System for Layout-Controlled Image Generation using Large Language Models and Diffusion Models
  5. 2025Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing
  6. 2023Reason out Your Layout: Evoking the Layout Master from Large Language Models for Text-to-Image Synthesis
  7. 2023LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation
  8. 2026Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion