Back
Similar todos
w/larger datasets, test lowering number images to sample from, but results too blurry to be usable :/ so go back to lowering fps of input data 
#mused
clean data & filter blurry images then start processing/aligning image datasets again #mused
fail w/medium dataset from 360 video (~6,000 images) like small, but full requires too much memory, next strategy is render each input separately #mused
splash image sharper 
#names
better image processing failure fallbacks in 
#readbot
make image previewer backdrop blurred 
#interiorai
spends hours optimizing the brightness, contrast and blur of the auto segmented object mask so it works well for virtual staging and adding auto upscale #interiorai
blurred a bunch of unsplash images 
#unbokeh
fixed image variants to trim boring pixels and then upscale to a given size 
#emojis
