Exposing Text-Image Inconsistency Using Diffusion Models (ICLR 2024)
Jupyter Notebook 4.96%Python 95.04%
d-tiil's Introduction
๐ Hi, Iโm Mingzhen Huang
๐ Iโm interested in Computer Vision and Machine Learning, especially in video based object-centric visual recognition (e.g. object detection/tracking)
๐ฑ Iโm currently learning video pose estimation and tracking, vision language tasks.
๐๏ธ Iโm looking to collaborate on all computer vision related tasks.
๐ซ Please reach me via mhuang33 AT buffalo DOT edu
Excuse me, we found some problems in the reproduction process, and the edited image is not as realistic as the paper shows. Even though the model_fine_tuning_optimization_steps is set to 500
prompt
prompt = 'Wolf shown recovering will be adopted by a veterinary technician'
original image
edited image
The edited image is far from the original, is there any parameter need to be adjusted?
final mask
The final mask can not convey the ground truth of the region.