DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Authors: Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, Jian Zhang

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate that our method has promising performance on various image editing tasks, including within a single image (e.g., object moving, resizing, and content dragging) or across images (e.g., appearance replacing and object pasting).
Researcher Affiliation Collaboration 1School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University 2ARC Lab, Tencent PCG 3Peking University Shenzhen Graduate School-Rabbitpre AIGC Joint Research Laboratory
Pseudocode No The paper describes the method and its components but does not provide any structured pseudocode or algorithm blocks.
Open Source Code Yes Code is available at https://github.com/MC-E/Dragon Diffusion.
Open Datasets Yes The test set is randomly formed by 800 aligned faces from Celeb A-HQ Karras et al. (2018) training set.
Dataset Splits No The paper mentions using a 'test set' formed from the 'Celeb A-HQ training set' but does not provide specific dataset split information (percentages, sample counts, or explicit validation split details) needed to reproduce the data partitioning for their experiments.
Hardware Specification Yes The experiment is conducted on an NVIDIA A100 GPU with Float32 precision.
Software Dependencies No The paper mentions using 'Stable Diffusion-V1.5' and 'DDIM sampling' but does not provide specific version numbers for software dependencies such as programming languages, libraries, or frameworks.
Experiment Setup Yes The inference adopts DDIM sampling with 50 steps, and we set the classifier-free guidance scale as 5.