You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When working with large images I often upscale the image then downscale the result because images larger than 2048 in either direction causes temporary graphical glitches.
An option to have 1.5 , 2.0 , 2.5 , 3.0 , 4.0 super sampling would be helpful.
For example, If the 2.0 super sampling option was picked and the chosen tile size was 512 it would scale the 512x512 input to 1024x1024 , perform the diffusion , then scale it back down to 512x512.
Inpainting already does this for the masked content if the resolution does not match the source image.
Not essential but would be a nice feature to have :)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
When working with large images I often upscale the image then downscale the result because images larger than 2048 in either direction causes temporary graphical glitches.
An option to have 1.5 , 2.0 , 2.5 , 3.0 , 4.0 super sampling would be helpful.
For example, If the 2.0 super sampling option was picked and the chosen tile size was 512 it would scale the 512x512 input to 1024x1024 , perform the diffusion , then scale it back down to 512x512.
Inpainting already does this for the masked content if the resolution does not match the source image.
Not essential but would be a nice feature to have :)
Beta Was this translation helpful? Give feedback.
All reactions