Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Let the text-to-mask .mask.png file be used as a mask

Browse Source 
Ironically, the black and white mask file generated by the
`invoke> !mask` command could not be passed as the mask to
`img2img`. This is now fixed and the documentation updated.
This commit is contained in:
Lincoln Stein 2022-10-22 13:53:23 -04:00
parent d8c1b78d83
commit 2e14ba8716
2 changed files with 23 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
docs/features/INPAINTING.md
View File

@ -81,15 +81,18 @@ text2mask feature. The syntax is `!mask /path/to/image.png -tm <text>
It will generate three files: It will generate three files:
- The image with the selected area highlighted. - The image with the selected area highlighted.
- it will be named XXXXX.<imagename>.<prompt>.selected.png
- The image with the un-selected area highlighted. - The image with the un-selected area highlighted.
- it will be named XXXXX.<imagename>.<prompt>.deselected.png
- The image with the selected area converted into a black and white - The image with the selected area converted into a black and white
image according to the threshold level. image according to the threshold level
- it will be named XXXXX.<imagename>.<prompt>.masked.png
Note that none of these images are intended to be used as the mask The `.masked.png` file can then be directly passed to the `invoke>`
passed to invoke via `-M` and may give unexpected results if you try prompt in the CLI via the `-M` argument. Do not attempt this with
to use them this way. Instead, use `!mask` for testing that you are the `selected.png` or `deselected.png` files, as they contain some
selecting the right mask area, and then do inpainting using the transparency throughout the image and will not produce the desired
best selection term and threshold. results.
Here is an example of how `!mask` works: Here is an example of how `!mask` works:
@ -120,7 +123,7 @@ It looks like we selected the hair pretty well at the 0.5 threshold
let's have some fun: let's have some fun:
``` ```
invoke> medusa with cobras -I ./test-pictures/curly.png -tm hair 0.5 -C20 invoke> medusa with cobras -I ./test-pictures/curly.png -M 000019.curly.hair.masked.png -C20
>> loaded input image of size 512x512 from ./test-pictures/curly.png >> loaded input image of size 512x512 from ./test-pictures/curly.png
... ...
Outputs: Outputs:
@ -129,6 +132,13 @@ Outputs:
<img src="../assets/inpainting/000024.801380492.png"> <img src="../assets/inpainting/000024.801380492.png">
You can also skip the `!mask` creation step and just select the masked
region directly:
```
invoke> medusa with cobras -I ./test-pictures/curly.png -tm hair -C20
```
### Inpainting is not changing the masked region enough! ### Inpainting is not changing the masked region enough!
One of the things to understand about how inpainting works is that it One of the things to understand about how inpainting works is that it

9
ldm/generate.py
View File

@ -911,9 +911,12 @@ class Generate:
# with alpha transparency. It converts it into a black/white # with alpha transparency. It converts it into a black/white
# image with the transparent part black. # image with the transparent part black.
def _image_to_mask(self, mask_image, invert=False) -> Image: def _image_to_mask(self, mask_image, invert=False) -> Image:
# Obtain the mask from the transparency channel if mask_image.mode in ('L','RGB'):
mask = Image.new(mode="L", size=mask_image.size, color=255) mask = mask_image
mask.putdata(mask_image.getdata(band=3)) else:
# Obtain the mask from the transparency channel
mask = Image.new(mode="L", size=mask_image.size, color=255)
mask.putdata(mask_image.getdata(band=3))
if invert: if invert:
mask = ImageOps.invert(mask) mask = ImageOps.invert(mask)
return mask return mask