AUTOMATIC1111 / stable-diffusion-webui

Stable Diffusion web UI
GNU Affero General Public License v3.0
141.69k stars 26.77k forks source link

[Bug]: sketch does not load #9500

Open frakc opened 1 year ago

frakc commented 1 year ago

Is there an existing issue for this?

What happened?

When i send image to sketch, it breaks sketch functionality.

Steps to reproduce the problem

  1. make any image
  2. send to imgtoimg
  3. press sketch

What should have happened?

image should load and should be able to draw over it

Commit where the problem happens

22bcc7be428c94e9408f589966c2040187245d81

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

repeats on 
--autolaunch --xformers

or 

--autolaunch

List of extensions

no

Console logs

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Loading A111 WebUI Launcher
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 i   Settings file found, loading
 →   Updating Settings File  ✓
 i   Launcher Version 1.7.0
 i   Found a custom WebUI Config
 i   No Launcher launch options
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 →   Checking requirements :
 i   Python 3.10.6150.1013 found in registry:  C:\Users\frakc\AppData\Local\Programs\Python\Python310\
 i   Clearing PATH of any mention of Python
 →   Adding python 3.10 to path  ✓
 i   Git found and already in PATH:  C:\Program Files\Git\cmd\git.exe
 i   Automatic1111 SD WebUI found:  D:\Programming\nn_automatic\stable-diffusion-webui
 i   One or more checkpoint models were found
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Loading Complete, opening launcher
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 i   Arguments are now: --xformers
 i   Arguments are now: --xformers
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  WEBUI LAUNCHING VIA EMS LAUNCHER, EXIT THIS WINDOW TO STOP THE WEBUI
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 !   Any error happening after 'commit hash : XXXX' is not related to the launcher. Please report them on Automatic1111's github instead :
 ☁   https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/new/choose
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Cancel
venv "D:\Programming\nn_automatic\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)]
Commit hash: 22bcc7be428c94e9408f589966c2040187245d81
Installing requirements for Web UI
Launching Web UI with arguments: --autolaunch --xformers
Loading weights [d8691b4d16] from D:\Programming\nn_automatic\stable-diffusion-webui\models\Stable-diffusion\deliberate_v11.safetensors
Creating model from config: D:\Programming\nn_automatic\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying xformers cross attention optimization.
Textual inversion embeddings loaded(6): bad-hands-5, bad_prompt_version2, corneo_ball_gag, corneo_nipple_rings, Draenei, sex-machine
Model loaded in 3.4s (load weights from disk: 0.4s, create model: 0.3s, apply weights to model: 0.5s, apply half(): 0.7s, move model to device: 0.6s, load textual inversion embeddings: 0.8s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 8.0s (import torch: 1.3s, import gradio: 0.8s, import ldm: 0.5s, other imports: 0.7s, setup codeformer: 0.2s, load scripts: 0.8s, load SD checkpoint: 3.4s, create ui: 0.2s, gradio launch: 0.2s).
100%|██████████████████████████████████████████████████████████████████████████████████| 24/24 [00:03<00:00,  6.83it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 24/24 [00:02<00:00,  9.41it/s]
Traceback (most recent call last):█████████████████████████████████████████████████████| 24/24 [00:02<00:00, 10.12it/s]
  File "D:\Programming\nn_automatic\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict
    output = await app.get_blocks().process_api(
  File "D:\Programming\nn_automatic\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1073, in process_api
    inputs = self.preprocess_data(fn_index, inputs, state)
  File "D:\Programming\nn_automatic\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 962, in preprocess_data
    processed_input.append(block.preprocess(inputs[i]))
  File "D:\Programming\nn_automatic\stable-diffusion-webui\venv\lib\site-packages\gradio\components.py", line 1594, in preprocess
    im = processing_utils.decode_base64_to_image(x)
  File "D:\Programming\nn_automatic\stable-diffusion-webui\venv\lib\site-packages\gradio\processing_utils.py", line 55, in decode_base64_to_image
    content = encoding.split(";")[1]
IndexError: list index out of range

Additional information

video with demonstation https://youtu.be/YgJypB1zEx8

HHeyJ commented 1 year ago

这是来自QQ邮箱的假期自动回复邮件。   您好,我最近正在学校读书中,无法亲自回复您的邮件。我将在放假后,尽快给您回复。

frakc commented 1 year ago

Hello. this issue seems to appear from some gradio bug https://github.com/gradio-app/gradio/issues/3623

JonyTianming commented 1 year ago

My problem is the same as yours, but my problem is to generate a picture from tex2img, then send to img2img, and then click the sketch below, and then automatically infinitely enlarge until the picture explodes, and a small sad face appears in the upper left corner. There will be an error prompt before, indicating that the picture has exceeded 280 million pixels, so it is cracked. After I updated it again, there was no error, but the problem is still there. Then many plug-ins that need to use the sketch functionality are affected and cannot be used.


Error message before reinstallation:: QQ截图20230503122928

After I reinstalled it all, the error message no longer appears, but the problem is still there, As can be seen from the video (brush size adjustment lever), the resolution of the picture is automatically magnified until it finally explodes. I didn't adjust the size of the brush, but it changes automatically, indicating that the resolution of the picture has been automatically enlarged in the background.

https://user-images.githubusercontent.com/128905039/235833824-079788d6-83a7-482b-9e34-e1c5734cdfe4.mp4

https://user-images.githubusercontent.com/128905039/235833826-2e033f52-405e-440b-82ec-f0330b92da22.mp4

marchcat69 commented 1 year ago

I have same problem

cuffuuguu commented 1 year ago

Are the display scales of Windows and browser both set to 100%?

I had the same problem, but when I set the display scale ratio of both my browser and Windows to 100%, the problem was resolved.

However, 100% display scale may not be suitable for users with high-resolution screens, or you may have other reasons for not wanting to set the Windows display scale to 100%. This could potentially solve your problem:

I tried keeping the scale of windows at my preferred 200%, while setting the browser's scale to 50% (multiplying still results in 100). This should also resolve the issue (if not, then revert back to 100%/100%).

Instead of adjusting the Windows display scale every time you use Sketch/Inpaint Sketch, I believe it is much easier to only adjust the browser's display scale.

frakc commented 1 year ago

Are the display scales of Windows and browser both set to 100%?

I had the same problem, but when I set the display scale ratio of both my browser and Windows to 100%, the problem was resolved.

However, 100% display scale may not be suitable for users with high-resolution screens, or you may have other reasons for not wanting to set the Windows display scale to 100%. This could potentially solve your problem:

I tried keeping the scale of windows at my preferred 200%, while setting the browser's scale to 50% (multiplying still results in 100). This should also resolve the issue (if not, then revert back to 100%/100%).

Instead of adjusting the Windows display scale every time you use Sketch/Inpaint Sketch, I believe it is much easier to only adjust the browser's display scale.

i have ultra wide monitor so 100% scale is pretty uncomfortable thing. But i try. thank