toshi2k2
toshi2k2
Running the inpainting inference code and using smaller sized images (256 x 256) does not produce expected results. is this expected behavior?  
How can we use other pretrained models (e.g. lsun_beds256) for inpainting inference? Using the pretrained model trvially seems to be running in the following error - ``` c = model.cond_stage_model.encode(batch["masked_image"])...
Hi, Can you explain what the vote_index variable is? I couldn't find any comments in the code explaining it.
The following error pops up if trying to use `ReplayCompose` with a mask. Error - ``` KeyError: Caught KeyError in DataLoader worker process 0. Original Traceback (most recent call last):...
Are there any instructions to adapt the code to new datasets?
The model runs into following error if training from scratch and not running `train.py`: ``` Total imgs for test of occ_level ZERO and occ_type 4341 Testing 0%| | 0/4341 [00:00
Hi, Are there any instructions for training and/or infering a custom data on your model?