For inpainting model, Mask

Zj-BinXia / DiffIR

This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

402 stars 17 forks source link

For inpainting model, Mask #45

Open ErwinKC opened 3 months ago

ErwinKC commented 3 months ago

For inpainting model, there's a 4 channels input, mask will be one of them and the output is 3 channels data. I'm wondering does this mask contribute to the network, or I can delete it and make input for 4 channels as well. Best regards, Thanks.

Zj-BinXia commented 3 months ago

The four channel input contains masked image and mask. I just follow the LaMa and do not validate the contribution of mask.