bycloud

the original code only has `suffix=down` as an option. The other options do exist, but idk why it wasn't included. This is my solution: go to `degrade.py` and remove `#elif...`...

The same error is still occurring even if I made the images (naive & input_name) to the same directory as main_train.py And yes the input_name is a jpg and naive...

Give this repo I wrote modified for Windows instead: https://github.com/bycloudai/3d-photo-inpainting-Windows

@stevosaurus do you mind elaborating a bit more? I've tried getting the files `feature.h` included from `colmap/src/head/dev-55e04ac3eb.clean/src/exe` to `vcpkg/installed/x64-windows/include/colmap` but it still the same error unfortunately.

I realized I need to change the model id inside quick_start.py But even after I changed the model ID in quick_start.py I got another error: ``` loading all networks... joint...

@jonbarron unfortunately it is already satisfied... 

Ya it seems to work just by adjusting the `f.read(8)` to `f.read(4)`, I should've figured that out myself hahaha That worked as a solution but was caught with another one...

I tried training with a single image, I don't see any obvious visual improvements weirdly. Every parameter here is the same except for using Anythingv3 for the model  Clip...

I tried again training with a single image, in an attempt to replicate the results of ani-nahida that 7eu7d7 have shown on README. I used the exact image to train....

@bladedsupernova do you mind sharing your exact parameters in training the embeddings?