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
I have noticed that when use img2img inpainting, a brand new image is generated at first, which is shown in the output region when it goes to around 75% steps. Then the masked region which I choose will be pasted into this image, to compose the final output. However, I want the brand new image without paste the input image region back. How can I get it?
I have revised the code in 'processing.py', where I delete
`if self.mask is not None:
blended_samples = samples * self.nmask + self.init_latent * self.mask
if self.scripts is not None:
mba = scripts.MaskBlendArgs(samples, self.nmask, self.init_latent, self.mask, blended_samples)
self.scripts.on_mask_blend(self, mba)
blended_samples = mba.blended_latent
samples = blended_samples`,
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.
-
I have noticed that when use img2img inpainting, a brand new image is generated at first, which is shown in the output region when it goes to around 75% steps. Then the masked region which I choose will be pasted into this image, to compose the final output. However, I want the brand new image without paste the input image region back. How can I get it?
I have revised the code in 'processing.py', where I delete
`if self.mask is not None:
blended_samples = samples * self.nmask + self.init_latent * self.mask
however, nothing changed.
Please help, thx
Beta Was this translation helpful? Give feedback.
All reactions