Proportion and Perspective Control for Flow-Based Image Generation

Julien Boudier, Hugo Caselles-Dupré
10/13/2025
cs.CVcs.AI

No confident code implementation found for this paper.

Abstract

While modern text-to-image diffusion models generate high-fidelity images, they offer limited control over the spatial and geometric structure of the output. To address this, we introduce and evaluate two ControlNets specialized for artistic control: (1) a proportion ControlNet that uses bounding boxes to dictate the position and scale of objects, and (2) a perspective ControlNet that employs vanishing lines to control the 3D geometry of the scene. We support the training of these modules with data pipelines that leverage vision-language models for annotation and specialized algorithms for conditioning image synthesis. Our experiments demonstrate that both modules provide effective control but exhibit limitations with complex constraints. Both models are released on HuggingFace: https://huggingface.co/obvious-research

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

88% match1 repo2752026

Generating Images with 3D Annotations Using Diffusion Models

88% match1 repo472026

A Two-Stage System for Layout-Controlled Image Generation using Large Language Models and Diffusion Models

88% match2025

DreamWalk: Style Space Exploration using Diffusion Guidance

88% match2024

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

87% match2025

3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation

87% match1 repo3462024

Cite this paper

@article{boudier2025proportion,
  title  = {Proportion and Perspective Control for Flow-Based Image Generation},
  author = {Julien Boudier and Hugo Caselles-Dupré},
  year   = {2025},
  eprint = {2510.21763},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.21763v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.21763.svg)](https://codeofpaper.com/paper/2510.21763)

Discussion