FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection

TL;DR

FineControlNet enhances text-to-image generation by enabling detailed control over individual instance appearances and poses, combining geometric and textual prompts for more precise image synthesis.

Contribution

It introduces FineControlNet, a novel model that integrates fine-grained appearance control with pose guidance in image generation, surpassing existing pose-conditioned diffusion models.

Findings

Outperforms state-of-the-art models in pose and appearance control

Achieves more accurate adherence to text prompts and poses

Demonstrates superior image quality and control fidelity

Abstract

Recently introduced ControlNet has the ability to steer the text-driven image generation process with geometric input such as human 2D pose, or edge features. While ControlNet provides control over the geometric form of the instances in the generated image, it lacks the capability to dictate the visual appearance of each instance. We present FineControlNet to provide fine control over each instance's appearance while maintaining the precise pose control capability. Specifically, we develop and demonstrate FineControlNet with geometric control via human pose images and appearance control via instance-level text prompts. The spatial alignment of instance-specific text prompts and 2D poses in latent space enables the fine control capabilities of FineControlNet. We evaluate the performance of FineControlNet with rigorous comparison against state-of-the-art pose-conditioned text-to-image diffusion models. FineControlNet achieves superior performance in generating images that follow the user-provided instance-specific text prompts and poses compared with existing methods. Project webpage: https://samsunglabs.github.io/FineControlNet-project-page