[Bug]: Inpaint masked area problem with certain resolutin

[iChristGit]

trafficstars

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

Im on latest version, trying to inpaint 2008x3008 picture, when masking something the results are way off the mask area, and Ive tried Chrome and firefox, different vae, models, and cl arguments. Also, when trying to do highres fix with 2008x3008 I get error "ValueError: images do not match"

The weird thing is image size 3008x2008 do work great, both normal and highres. A lot of photos I have are captured with this resolution.

Steps to reproduce the problem

1. Go to Img2img
2. Press inpaint
3. Choose a 2008x3008 picture
4. Mask something
5. See the inpaint part not in-line with your mask
6. Highres fix gives "ValueError: images do not match"

What should have happened?

Mask should be the same as what the user created

Commit where the problem happens

737eb28faca8be2bb996ee0930ec77d1f7ebd939

What platforms do you use to access UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox, Google Chrome

Command Line Arguments

--deepdanbooru --xformers

Additional information, context and logs

To create a public link, set share=True in launch(). Error completing request Arguments: (1, '', '', 'None', 'None', None, {'image': <PIL.Image.Image image mode=RGBA size=3008x2008 at 0x2DDF36997E0>, 'mask': <PIL.PngImagePlugin.PngImageFile image mode=RGBA size=2008x3008 at 0x2DDDD6BBB80>}, None, None, 0, 20, 0, 4, 0, False, False, 1, 1, 7, 0.75, -1.0, -1.0, 0, 0, 0, False, 768, 512, 0, True, 32, 0, '', '', 0, 'Not set', 'Not set', 'Not set', 'Not set', 'No focus', 1030, False, False, '

\n
• CFG Scale should be 2 or lower.
\n

\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 1, 512, 0.75, 0, 0.1, 0, 0.06, 1, False, False, '

Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8

', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, None, '', '', '

Will upscale the image to twice the dimensions; use width and height sliders to set tile size

', 64, 0, False, 4.0, '', 10.0, True, False, True, 30.0, False, False, '', 1, 10, True, 1, False, 1, 0, 0, False, 1, '', 0, '', True, False, False) {} Traceback (most recent call last): File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\modules\ui.py", line 221, in f res = list(func(*args, **kwargs)) File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\webui.py", line 64, in f res = func(*args, **kwargs) File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\modules\img2img.py", line 137, in img2img processed = process_images(p) File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\modules\processing.py", line 359, in process_images res = process_images_inner(p) File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\modules\processing.py", line 421, in process_images_inner p.init(p.all_prompts, p.all_seeds, p.all_subseeds) File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\modules\processing.py", line 716, in init image_masked.paste(image.convert("RGBA").convert("RGBa"), mask=ImageOps.invert(self.mask_for_overlay.convert('L'))) File "D:\Visions Of Chaos\Machine Learning\Text To Image\stable-diffusion-webui\venv\lib\site-packages\PIL\Image.py", line 1628, in paste self.im.paste(im, box, mask.im) ValueError: images do not match

[iChristGit]

any info on that? still same issue.

[Lalimec]

Did you solve this, getting the same error but a different resolution.

[iChristGit]

Did you solve this, getting the same error but a different resolution.

It got fixed by one of the commits. Are you on latest commit?

[Lalimec]

I ve just did a pull now, will see.

[catboxanon]

Closing as stale as the original issue is from October of last year. Open a new issue with updated info if the problem persists.