Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models

TL;DR

This paper conducts a reproducibility study of DragDiffusion, a diffusion-based interactive image editing method, confirming its core claims while analyzing sensitivity to hyperparameters and evaluating a multi-timestep variant.

Contribution

It provides a detailed reproducibility analysis of DragDiffusion, clarifying the conditions for reliable results and assessing the impact of hyperparameters and modifications.

Findings

Reproduced main ablation studies with close agreement.

Performance is sensitive to certain hyperparameters like timestep and feature level.

Multi-timestep optimization does not improve accuracy but increases computational cost.

Abstract

DragDiffusion is a diffusion-based method for interactive point-based image editing that enables users to manipulate images by directly dragging selected points. The method claims that accurate spatial control can be achieved by optimizing a single diffusion latent at an intermediate timestep, together with identity-preserving fine-tuning and spatial regularization. This work presents a reproducibility study of DragDiffusion using the authors' released implementation and the DragBench benchmark. We reproduce the main ablation studies on diffusion timestep selection, LoRA-based fine-tuning, mask regularization strength, and UNet feature supervision, and observe close agreement with the qualitative and quantitative trends reported in the original work. At the same time, our experiments show that performance is sensitive to a small number of hyperparameter assumptions, particularly the optimized timestep and the feature level used for motion supervision, while other components admit broader operating ranges. We further evaluate a multi-timestep latent optimization variant and find that it does not improve spatial accuracy while substantially increasing computational cost. Overall, our findings support the central claims of DragDiffusion while clarifying the conditions under which they are reliably reproducible. Code is available at https://github.com/AliSubhan5341/DragDiffusion-TMLR-Reproducibility-Challenge.