DIRE icon indicating copy to clipboard operation
DIRE copied to clipboard

[ICCV 2023] Official implementation of the paper: "DIRE for Diffusion-Generated Image Detection"

Results 22 DIRE issues
Sort by recently updated
recently updated
newest added

Why is the code running with an error, the images have already been put into the specified folder by pressing readme?

I did test as the following steps, but cannot get the same results in paper. Is there anything wrong in my steps? ### My steps 1. from the OneDrive location...

I used lsun_pndm.pth and test on lsun/lsun/sdv1,but got lsun_lsun_sdv1: ACC: 1.00000 AP: 1.00000 R_ACC: 1.00000 F_ACC: 1.00000 ,and I train the model used the dataset and got the same result.but...

some files in the dataset can not be downloaded correctly ![image](https://github.com/ZhendongWang6/DIRE/assets/118585107/6bd89357-1296-4769-a64b-484ded3ebb56) (I have downloaded the dataset twice)

I'd like to know how to run robustness test? From my perspective, I first add distortion to original images, then run `compute_dire.sh` to get their dire image, finally run test.sh...

I ran `test.sh` on LSUN-B dataset and its corresponding generated images by ADM, with checkpoint `lsun_adm.pth`, the output in terminal is: ``` 'lsun_adm:lsun_adm' model testing on... lsun_adm: ACC: 0.89900 AP:...

I used lsun_bed.pth and test on the dire testset lsun_bedroom/lsun_bedroom/adm, 3 accuracy rates are okay but the ap is very low, far less than 1.0. ACC: 1.00000 AP: 0.30710 R_ACC:...

Hi, thanks for aharing the dataset and code. I noticed the 3 package(dite, images, recons) are provided, what are the differences between them? And there is a little suggestion that...

I downloaded the dataset from one-drive. when I unzip dataset, I got:

I am running simple tests with your data, something like ``` python demo.py -f test/celebahq/real/000009.jpg -m checkpoints/celebahq_sdv2.pth Testing on image 'test/celebahq/real/000009.jpg' ************************************************** Prob of being synthetic: 1.0000 ``` Every single...