Zheling Meng

I meet the same problem. I check the source code and it seems that the relative params are not loaded by load_network_pkl. You can add the following code to function...

And other links also present the same problem.

I also met this problem when I try to use llama3-llava-next-8b

Maybe you can check whether you load the right model. I solve it by it.

I set QF as 100 and get the results: ``` ACC: 0.63300 AP: 0.98968 R_ACC: 1.00000 F_ACC: 0.26600 ```

Actually as the paper stated, the model should be robust to jpeg compression.

Hi, have you already reproduced compute_dire.py on your dataset? I didn't see so significant reconstruction error...

> Are you sure these images are correct? My results are more close to the author's results though.    Do you also use `256x256_diffusion_uncond.pt` ?

> > > Are you sure these images are correct? My results are more close to the author's results though.    > > > > > > Do...

I found that if `real_step != 0` and `use_ddim=True` then can get my dire images. Under original config, I can also get similar images with you but it is too...