Stable Score Distillation

TL;DR

Stable Score Distillation (SSD) offers a simplified, stable, and efficient framework for text-guided image and 3D editing, improving alignment, control, and editing strength over previous complex methods.

Contribution

SSD introduces a novel, streamlined approach using a single classifier with CFG and null-text branches to enhance stability and control in text-guided editing tasks.

Findings

Achieves state-of-the-art results in 2D and 3D editing.

Faster convergence and reduced complexity compared to prior methods.

Maintains coherence and structure during editing.

Abstract

Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing strength. These limitations stem from reliance on complex auxiliary structures, which introduce conflicting optimization signals and restrict precise, localized edits. We introduce Stable Score Distillation (SSD), a streamlined framework that enhances stability and alignment in the editing process by anchoring a single classifier to the source prompt. Specifically, SSD utilizes Classifier-Free Guidance (CFG) equation to achieves cross-prompt alignment, and introduces a constant term null-text branch to stabilize the optimization process. This approach preserves the original content's structure and ensures that editing trajectories are closely aligned with the source prompt, enabling smooth, prompt-specific modifications while maintaining coherence in surrounding regions. Additionally, SSD incorporates a prompt enhancement branch to boost editing strength, particularly for style transformations. Our method achieves state-of-the-art results in 2D and 3D editing tasks, including NeRF and text-driven style edits, with faster convergence and reduced complexity, providing a robust and efficient solution for text-guided editing.