Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis

TL;DR

This paper introduces Generative Photography, a framework that enables scene-consistent camera control in text-to-image synthesis, improving realism and consistency across different camera settings.

Contribution

It proposes Dimensionality Lifting and Differential Camera Intrinsics Learning to control camera parameters during image generation, a novel approach for scene consistency.

Findings

Produces more scene-consistent images than state-of-the-art models

Enables smooth transitions across camera settings

Improves photorealism in generated images

Abstract

Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the generator will not be able to interpret and generate scene-consistent images. This limitation not only hinders the adoption of generative tools in professional photography but also highlights the broader challenge of aligning data-driven models with real-world physical settings. In this paper, we introduce Generative Photography, a framework that allows controlling camera intrinsic settings during content generation. The core innovation of this work are the concepts of Dimensionality Lifting and Differential Camera Intrinsics Learning, enabling smooth and consistent transitions across different camera settings. Experimental results show that our method produces significantly more scene-consistent photorealistic images than state-of-the-art models such as Stable Diffusion 3 and FLUX. Our code and additional results are available at https://generative-photography.github.io/project.