Diego C Sampaio

> Thanks for taking a look. Yeah I'm sure I am running it the same way as I copy/pasted the RUN command from the `nvidia/cuda` `run.sh`, minus some QT_FONT_DPI cruft...

Patchmatch is very important for the WEB interface, the github link is incorrect, the correct one is https://github.com/invoke-ai/InvokeAI/blob/main/docs/installation/060_INSTALL_PATCHMATCH.md Try following the patchmatch installation instructions and see if that resolves the...

So, face restoration is extremely resource consuming, it is quite normal that for 500 images, and with only 8gb of available VRAM, all the memory is consumed. I don't know...

If you install invoke without first installing CUDA support for Nvidia driver, which needs to be installed seperately, it is not automatically installed just by installing video card driver, torch...

Ok, there are two relevant problems in the log, first the patchmatch installation, but for now it still doesn't work on Mac. Second, the script is not finding the corresponding...

Okay, this is an SSL certificate error, when invoke tries to download detection_Resnet50_Final.pth. There is a way to solve this by changing an execution file, but I couldn't find the...

> Duplicate of #1810? Yes, this is the issue that I was looking for.

Hi, it's been a while since I last checked this, but there was a compatibility issue with the gtx 16XX series. According to this issue https://github.com/invoke-ai/InvokeAI/issues/775 the problem seems to...

The link reference seems to be incorrect, I get the same error, The correct address is: https://github.com/invoke-ai/InvokeAI/blob/main/docs/installation/050_INSTALLING_MODELS.md With "050" before "INSTALLING_MODELS.md".

I can confirm this, switching to the inpanting model sometimes causes the invoke to hang. Switching between models often seems to do the same thing too. OS: Linux VGA: Nvidia...