stable-diffusion-webui
stable-diffusion-webui copied to clipboard
AUTOMATIC1111
[Bug]: inpaint image doesn't fit to screen on mobile
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
What happened?
When using the latest Stable Diffusion web UI on mobile the image sent to inpaint doesn't fit on a mobile screen, resulting in a cut image:
One commit that doesn't have this issue is dfeee786, where the image sent to inpaint fits well on a mobile screen:
Steps to reproduce the problem
- Update to the latest webui (1.3.2)
- Launch webui with --listen command
- Access webui via mobile device's browser (Android phone with Chrome in my case)
- Go to the img2img tab
- Go to Inpaint
- import an image to inpaint
What should have happened?
When sending an image to inpaint on a mobile device, the image should fit to the device's screen like this:
Commit where the problem happens
1.3.2
What Python version are you running on ?
Python 3.10.x
What platforms do you use to access the UI ?
Android
What device are you running WebUI on?
Nvidia GPUs (RTX 20 above)
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
./webui.bat --listen --deepdanbooru --xformers
List of extensions
No
Console logs
PS C:\Users\UserDEV\stable-diffusion-webui> ./webui.bat --listen --deepdanbooru --xformers
venv "C:\Users\UserDEV\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.3.2
Commit hash: baf6946e06249c5af9851c60171692c44ef633e0
Fetching updates for Stable Diffusion...
Checking out commit for Stable Diffusion with hash: cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf...
Fetching updates for K-diffusion...
Checking out commit for K-diffusion with hash: c9fe758757e022f05ca5a53fa8fac28889e4f1cf...
Installing requirements
Launching Web UI with arguments: --listen --deepdanbooru --xformers
==============================================================================
You are running torch 1.13.1+cu117.
The program is tested to work with torch 2.0.0.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.
Use --skip-version-check commandline argument to disable this check.
==============================================================================
=================================================================================
You are running xformers 0.0.16rc425.
The program is tested to work with xformers 0.0.17.
To reinstall the desired version, run with commandline flag --reinstall-xformers.
Use --skip-version-check commandline argument to disable this check.
=================================================================================
Loading weights [30ecde0ac1] from C:\Users\UserDEV\stable-diffusion-webui\models\Stable-diffusion\SD1.5.safetensors
Creating model from config: C:\Users\UserDEV\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Loading VAE weights specified in settings: C:\Users\UserDEV\stable-diffusion-webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Running on local URL: http://0.0.0.0:7860
To create a public link, set `share=True` in `launch()`.
Startup time: 37.9s (import torch: 5.8s, import gradio: 1.2s, import ldm: 0.8s, other imports: 1.7s, setup codeformer: 0.1s, list SD models: 0.1s, load scripts: 3.8s, create ui: 19.0s, gradio launch: 5.2s).
Applying optimization: xformers... done.
Textual inversion embeddings loaded(4): bad-artist, bad_prompt, EasyNegative
Model loaded in 28.7s (load weights from disk: 19.0s, create model: 0.8s, apply weights to model: 3.0s, apply half(): 0.6s, load VAE: 1.2s, move model to device: 1.3s, load textual inversion embeddings: 2.8s).
Additional information
No response
+1
Device: Samsung Galaxy S23 Ultra & iPhone 14 Pro Max OS: Android 13/One UI 5.1 & iOS 16.5 Browsers: Chrome, Samsung Browser, Safari
Edit: I've found that if you long press on one of the buttons, it allows you to vertically/horizontally move the image around.
Which button!?
+1
Device: Samsung Galaxy S23 Ultra & iPhone 14 Pro Max OS: Android 13/One UI 5.1 & iOS 16.5 Browsers: Chrome, Samsung Browser, Safari
Edit: I've found that if you long press on one of the buttons, it allows you to vertically/horizontally move the image around.
how?
Which button!?
It’s a hack, but holding (not just pressing) down on any of these will let you pan the picture. You’re still screwed though if the image is too big.
This is not only mobile or --listen, I have the same issue on my 13'' MacBook in the local webui with 768x512 images (vertical images work well).
Currently, the only workaround I found is to zoom out the whole page in the browser (which incidentally makes the text too small to be read).
I primarily access Automatic1111 through my Samsung Galaxy S21 with Chrome. I also have this issue and it makes inpainting basically unusable. Thanks for working on this!!
https://github.com/NoCrypt/inpaint-nav
This extension fixes it.
This solution worked for me! Thank you
Dont thank me, thank the creator of the extension, nocrypt.
On Sun, 3 Sept 2023, 00:38 mattmorr1990, @.***> wrote:
https://github.com/NoCrypt/inpaint-nav
This extension fixes it.
This solution worked for me! Thank you
— Reply to this email directly, view it on GitHub https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/11045#issuecomment-1703908840, or unsubscribe https://github.com/notifications/unsubscribe-auth/A77NYE7BHS4EJB4N47IMCODXYN4IXANCNFSM6AAAAAAY3LJMAM . You are receiving this because you commented.Message ID: @.***>