[Bug]: Generate button does nothing on img2img tab if ControlNet is enbled.

[John-Keyberg]

Is there an existing issue for this?

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

What happened?

This issue is similar to this one, but it only happens on the img2img tab and only if ControlNet has been enabled and used at least once.

On the img2img tab, with ControlNet enabled, pressing the Generate button will cause a "Waiting..." text to appear inside the loading bar at the top of the image on the right panel, as usual, but then both the text and the bar disappears and nothing happens. No generation. On a few random occasions, the very first generation after launching automatic1111 works, but any subsequent one doesn't.

Clicking the button again also does nothing, and any subsequent click after the first won't cause the "Waiting..." text to appear again - the button just becomes unresponsive. There is nothing on the console, no error message. Txt2img still works normally.

Img2img alone won't work even if CN is disabled. It only starts working again via reloading the UI. I'm using the latest CN as of writing, version 1.1.119.

Steps to reproduce the problem

1. Go to img2img tab and write some prompt, input whatever images on img2img and CN. The setting don't matter.
2. Click Generate. Waiting button disappears and nothing happens.

What should have happened?

The images should have been generated, but nothing happens and the console is empty.

Commit where the problem happens

22bcc7be

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

git pull

List of extensions

None.

Console logs

Already up to date.
venv "E:\AI Generation\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.8 (tags/v3.10.8:aaaf517, Oct 11 2022, 16:50:30) [MSC v.1933 64 bit (AMD64)]
Commit hash: 22bcc7be428c94e9408f589966c2040187245d81
Installing requirements for Web UI

Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
ControlNet v1.1.119
ControlNet v1.1.119
Loading weights [9aba26abdf] from E:\AI Generation\stable-diffusion-webui\models\Stable-diffusion\deliberate_v2.safetensors
Creating model from config: E:\AI Generation\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (Doggettx).
Textual inversion embeddings loaded(0):
Textual inversion embeddings skipped(1): 21charturnerv2
Model loaded in 3.1s (load weights from disk: 0.2s, create model: 0.4s, 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: 7.6s (import torch: 1.1s, import gradio: 0.8s, import ldm: 0.4s, other imports: 0.7s, setup codeformer: 0.1s, load scripts: 0.7s, load SD checkpoint: 3.2s, create ui: 0.3s, gradio launch: 0.1s).

Additional information

No response

[nhari999]

@John-Keyberg Based on the issue you described, it is possible that clearing your browser cache and cookies or trying a different browser may help resolve the problem you are experiencing with ControlNet on the img2img tab. These are practical solutions that could help rule out any local issues with your setup. I also tried to replicate the issue on my end, but everything ran correctly in my local machine, so it would be helpful if you could provide me with more details about your setup or any error messages you may be seeing.

[John-Keyberg]

Clearing cache and cookies solved it for Chrome. It is also working normally in Edge. Thanks.

[merodiro]

Are you using a remote setup? I think this issue happens mostly on remote setups and not when running it locally

[John-Keyberg]

No, I was using it on my own computer.