Claudio Rota

Hi, I had the same issue. I used "zip -s 0 outdoor_png.zip --out tmp.zip && unzip tmp.zip -d .", and it worked for me (for the outdoor_png folder). I hope...

Hi, > I want to know the difference between the two function get_velocity and get_approximated_x0 in scheduler/ddpm_scheduler.py with the v_prediction type in step function in line 356. Seems they all...

Hi @hzhXue, It's not clear what you want to do. Do you want to perform X2 super-resolution instead of 4? Or do you want to use a bigger model?

> I want X2 super-resolution The actual upscaling is performed by the VAE model, which has 2 upscaling layers. The only way for x2 upscaling is to change the VAE,...

Hi @Walnutes, > **Vimeo-90K Dataset Process and Training Code/Scripts:** The dataset directory only contains reds_dataset.py, and train.py seems to import this class exclusively. Could you kindly provide the complete data...

From BasicSR, you need the file [vimeo90k_dataset.py](https://github.com/XPixelGroup/BasicSR/blob/master/basicsr/data/vimeo90k_dataset.py). You have to modify the class `Vimeo90KRecurrentDataset` (check my [reds_dataset.py](https://github.com/claudiom4sir/StableVSR/blob/main/dataset/reds_dataset.py)) . You can find metadata.txt for Vimeo [here](https://github.com/XPixelGroup/BasicSR/tree/master/basicsr/data/meta_info). You might remove the image...

> In the REDS dataset, these values are set to 3 and 1, respectively, to generate the neighbor_list parameter, which determines the number of frames (t) per batch. However, in...