Generating Compositional Scenes via Text-to-image RGBA Instance Generation

TL;DR

This paper introduces a multi-stage diffusion-based method for generating and editing complex scenes with fine-grained control over object attributes and layout, using RGBA instance generation and multi-layer composition.

Contribution

It proposes a novel multi-stage diffusion paradigm that generates isolated RGBA object instances and composes them into scenes, enabling detailed control and scene manipulation.

Findings

Capable of generating diverse, high-quality object instances.

Allows precise control over object attributes and placement.

Enables complex scene editing and manipulation.

Abstract

Text-to-image diffusion generative models can generate high quality images at the cost of tedious prompt engineering. Controllability can be improved by introducing layout conditioning, however existing methods lack layout editing ability and fine-grained control over object attributes. The concept of multi-layer generation holds great potential to address these limitations, however generating image instances concurrently to scene composition limits control over fine-grained object attributes, relative positioning in 3D space and scene manipulation abilities. In this work, we propose a novel multi-stage generation paradigm that is designed for fine-grained control, flexibility and interactivity. To ensure control over instance attributes, we devise a novel training paradigm to adapt a diffusion model to generate isolated scene components as RGBA images with transparency information. To build complex images, we employ these pre-generated instances and introduce a multi-layer composite generation process that smoothly assembles components in realistic scenes. Our experiments show that our RGBA diffusion model is capable of generating diverse and high quality instances with precise control over object attributes. Through multi-layer composition, we demonstrate that our approach allows to build and manipulate images from highly complex prompts with fine-grained control over object appearance and location, granting a higher degree of control than competing methods.