Can't use img2img even on a new install.

[Deejay85]

Is there an existing issue for this?

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

What happened?

Can't use img2img.

Steps to reproduce the problem

1. Go to img2img, choose inpaint or inpaint sketch, highlight area to modify
2. Press generate.
3. 1006 error

What should have happened?

A modified image. Nothing happens. I can still generate images just fine though, so this is the only one that's broken.

Sysinfo

SysInfo.txt

What browsers do you use to access the UI ?

No response

Console logs

venv "M:\SD\venv\Scripts\Python.exe"
fatal: not a git repository (or any of the parent directories): .git
fatal: not a git repository (or any of the parent directories): .git
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: 1.6.0
Commit hash: <none>
Installing xformers
Launching Web UI with arguments: --no-half-vae --api --theme dark --xformers --no-half
Loading weights [6ce0161689] from M:\SD\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
Running on local URL:  http://127.0.0.1:7862

To create a public link, set `share=True` in `launch()`.
Creating model from config: M:\SD\configs\v1-inference.yaml
Startup time: 125.7s (prepare environment: 119.2s, import torch: 2.4s, import gradio: 0.8s, setup paths: 0.7s, initialize shared: 0.3s, other imports: 0.5s, load scripts: 0.8s, create ui: 0.4s, gradio launch: 0.5s).
Applying attention optimization: xformers... done.
Model loaded in 6.0s (load weights from disk: 0.6s, create model: 0.3s, apply weights to model: 2.6s, load textual inversion embeddings: 1.3s, calculate empty prompt: 1.0s).
1006
1006
1006
1006
1006
1006
1006

Additional information

Used a new install just to make sure it wasn't anything I was doing. Also change .txt to .nfo on the sysinfo file...couldn't upload it otherwise. ¯_(ツ)_/¯

[tanuki-create]

Same here, when I use i2i, and m2m, same problem happens.(I use Paperspace for WebUI, based on Jupyter notebook) Any idea?

[Deejay85]

I was on the fence about posting the solution, since no one seemed to be reading the post anyway (I even posted this in disussions...no results), but since someone needs help, I got no problems in sharing. :D The solution, surprisingly, isn't any Python file that needs updated or downgraded (like I previously thought), but instead a command line that needs to be inputed. Why the sudden change? I haven't a single clue...all I know is it works, and that I stumbled on the solution by pure accident while researching the solution myself.

Just put in this line and it should work just fine. checks the previous poster's post time It's a good thing I just happened to check my email as I just barely got up. :D

--no-gradio-queue

[carefullyrandom]

I've tried the "--no-gradio-queue" solution but I'm still getting Connection errored out whenever I try to do any sort of img to img tasks. Can't seem to find any other solutions either.