Open mr-september opened 1 year ago
I found this issue on the main branch as well, the problem is with the VAE, add --no-half-vae to your command line arguments @mr-september
These are my current command line arguments, --autolaunch --opt-sub-quad-attention --opt-split-attention-v1 --no-half-vae --precision full --no-half --disable-nan-check
So far everything is working.
I needed to keep --no-half for inpainting to work.
Windows 10, 6900xt.
Is the workaround above the only solution to getting inpainting working and are there any plans to investigate this further? This seems specific to using the inpainting feature with half precision. @lshqqytiger
In testing the following behaviour occurs:
Fill: The targeted area remains pale and no filling is done. Original: Slight burn is seen on the targeted area but no variance in the image is made. Latent noise: The targeted area remains pale and no variance in the image is made. Latent nothing: The targeted area remains pale and no variance in the image is made.
This issue doesn't seem to be model, VAE, or sampler specific either.
Build: 108ada8
Arguments used: --medvram --opt-sub-quad-attention
Ideally, I'd like to use half precision for image generation / inpainting due to speed/VRAM use, but so far the only way I can get inpainting to work at all is to add the --no-half
argument.
Because DirectML does not natively support autocast, I implemented it by myself. So, it can be quite different from its native implementation of torch and hardly provide any improvement on performance or VRAM side. I can't access the source code of DirectML because it is not an open-source software, I can't do much about half precision.
when you run with without --no-half, in painting is very strange, it looks like what it does though is
any pixels along the top of the image stretch down all the way, then the mask is rotated by 90°
Hopefully this can narrow down the issue
@Bod9001 that's a very interesting find!
Some quick updates on my end: Maybe it's part of the teething issues from Auto1111/DirectML, but this issue (inpainting not working) and other issues (img-2-img not working, sometimes the "show extra networks" doesn't work) seem to randomly come and go. No updates or restarts or whatevers apparently fix or cause them. Truly very mysterious.
I found this issue on the main branch as well, the problem is with the VAE, add --no-half-vae to your command line arguments @mr-september
Hey Im a big noob. How do I just add stuff to the command line arguments?
Im on windows 10 and 6700xt GPU. Gives me the same blur
redownload models. put in in seperate folder (fixed models) and give it a hard read only attribute. Use seperate checkpoint for adetailer, so it has to reload between txt2image and adetailer. also allow only 1 model in memory.
I've had no nans errors after doing that
Is there an existing issue for this?
What happened?
Been using this extensively for a week... today suddenly inpainting stopped working halfway through. All output images are either exactly the input image, or with the blurred mask.
Steps to reproduce the problem
What should have happened?
Inpainted image
Commit where the problem happens
fd59537
What platforms do you use to access the UI ?
Windows 11, AMD 5700
What browsers do you use to access the UI ?
Opera
Command Line Arguments
List of extensions
Extension | URL | Version | Update -- | -- | -- | -- StylePile | https://github.com/some9000/StylePile.git | 85b549a1 (Thu Apr 13 18:42:34 2023) | unknown batch-face-swap | https://github.com/kex0/batch-face-swap.git | 60e259d8 (Thu Mar 16 02:02:46 2023) | unknown infinite-zoom-automatic1111-webui | https://github.com/v8hid/infinite-zoom-automatic1111-webui.git | b693c79f (Mon Apr 17 03:25:58 2023) | unknown multidiffusion-upscaler-for-automatic1111 | https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111.git | f3d79a47 (Sat Apr 15 17:29:10 2023) | unknown openOutpaint-webUI-extension | https://github.com/zero01101/openOutpaint-webUI-extension.git | 5e84d6d5 (Mon Apr 10 23:01:41 2023) | unknown sd-dynamic-prompts | https://github.com/adieyal/sd-dynamic-prompts.git | 9e7be4a2 (Sun Apr 16 07:55:24 2023) | unknown sd-extension-aesthetic-scorer | https://github.com/vladmandic/sd-extension-aesthetic-scorer.git | a35fb67a (Thu Apr 13 15:18:56 2023) | unknown sd-webui-3d-open-pose-editor | https://github.com/nonnonstop/sd-webui-3d-open-pose-editor.git | f2d5aac5 (Sat Apr 15 13:21:06 2023) | unknown sd-webui-ar | https://github.com/alemelis/sd-webui-ar.git | 9df49dc2 (Wed Apr 12 09:23:17 2023) | unknown sd-webui-controlnet | https://github.com/Mikubill/sd-webui-controlnet.git | 880bb7e3 (Mon Apr 17 06:41:09 2023) | unknown stable-diffusion-webui-Prompt_Generator | https://github.com/imrayya/stable-diffusion-webui-Prompt_Generator.git | 0d4de20f (Fri Mar 17 11:22:15 2023) | unknown stable-diffusion-webui-state | https://github.com/ilian6806/stable-diffusion-webui-state.git | 4cc8fa3c (Tue Apr 11 10:25:08 2023) | unknown ultimate-upscale-for-automatic1111 | https://github.com/Coyote-A/ultimate-upscale-for-automatic1111.git | 0a3d03a4 (Tue Feb 7 06:07:23 2023) | unknownConsole logs
Additional information
I have tried:
venv
folder to force-update everything as suggested in issue 77. torch-directml "Version: 0.1.13.1.dev230413"