New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug]: Upscale then Inpaint yields errors #7034
Comments
3rd party upscaling then importing into inpainting DO work without issue. Something has changed with the way the upscalers are working in A1111 and inpainting processing them. |
This looks like it is now corrected with the new upgrade dependencies of pytorch and xformers that was rolled out today. |
I'm also having this issue occurring with upgraded dependencies and parameters similar as above. I'd recommend reopening this issue until it's resolved for good. |
I have the same issue but only with the generated upscaled PNG. When using the JPG upscaled generated file, inpainting works OK |
Has anyone discovered a fix for this issue? |
Its an issue from PIL that should have been fixed: python-pillow/Pillow#6123 |
I use pillow 9.4.0 to have a try ,but this question isn't solved,so I suggest to open this issue again. |
i have the exact same issue however could find a workaround by sending the image from inpainting to an extension called photopea (i think it doesnt really matter where you sent it, just make sure somewhere else) then sending it back to inpaint does indeed fix this issue. Didnt try with anything other than photopea atm but hope i could help anyway i recommend loading the file into photopea extension then proceed to send it to img2img somehow inpaint is not available. Then finally sent it to inpaint. I can confirm it works everytime while its not when i upload into inpaint directly. |
Is there an existing issue for this?
What happened?
Since most recent pull, using ANY upscaler and then attempting to inpaint the image afterwards yields the following error. Pre-pull upscaled images still inpaint fine. Tried on two machines that were working and both experience the same issue:
Arguments: ('task(yxldyiqvocchr0u)', 2, 'trying to inpaint', '', [], None, None, {'image': <PIL.Image.Image image mode=RGBA size=2048x2048 at 0x2C2D87213F0>, 'mask': <PIL.PngImagePlugin.PngImageFile image mode=RGBA size=2048x2048 at 0x2C2D8720970>}, None, None, None, None, 20, 0, 4, 0, 1, False, False, 1, 1, 7, 0.75, -1.0, -1.0, 0, 0, 0, False, 512, 512, 0, 1, 32, 0, '', '', 0, '
\n \n
\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 1, 'CFG Scale
should be 2 or lower.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, False, False, '', 'Will upscale the image by the selected scale factor; use width and height sliders to set tile size
', 64, 0, 2, 1, '', 0, '', True, True, False, 'Deforum v0.5-webui-beta
', 'This script is deprecated. Please use the full Deforum extension instead.
', '\nUpdate instructions:
github.com/deforum-art/deforum-for-automatic1111-webui/blob/automatic1111-webui/README.md
', 'discord.gg/deforum
') {}Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\img2img.py", line 94, in img2img
image = ImageOps.exif_transpose(image)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\PIL\ImageOps.py", line 588, in exif_transpose
exif = image.getexif()
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\PIL\Image.py", line 1454, in getexif
self._exif.load(exif_info)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\PIL\Image.py", line 3670, in load
self._info = TiffImagePlugin.ImageFileDirectory_v2(self.head)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\PIL\TiffImagePlugin.py", line 504, in init
raise SyntaxError(msg)
SyntaxError: not a TIFF file (header b"b'Exif\x" not valid)
Steps to reproduce the problem
What should have happened?
Inpainting should kick off without error / produce inpainted picture into img2img-images folder
Commit where the problem happens
f2eae61
What platforms do you use to access UI ?
Windows
What browsers do you use to access the UI ?
Mozilla Firefox, Google Chrome, Brave
Command Line Arguments
Additional information, context and logs
No response
The text was updated successfully, but these errors were encountered: