Windows likes nothing more than screwing up line endings :/
I have re-uploaded this file from a Linux box, and tested. It should work now if you grab it again.
Windows likes nothing more than screwing up line endings :/
I have re-uploaded this file from a Linux box, and tested. It should work now if you grab it again.
Don't populate the Timelapse Input fields?
If you're looking to create a timelapse, or are still having issues, please post the crash report (if one was generated), or hit the "Generate" button and post the output from that here.
Your AMD card has not been detected (for whatever reason).
First I'd make sure your AMD drivers are up to date.
If you open the GUI and go to the help menu > Output System Info, please post the output here.
Have you tried fixing your filenames as per the error message?
Error in thread (_run_1): Error while reading image. This is most likely caused by special characters in the filename: 'Z:\Desktop\AIhuanlian\xhssf\xhssf_000514_1 - 副本.png'
This is likely an issue with Anaconda.
Try hitting "Update Index..." at the top of the Environments page in Anaconda Navigator, wait for it to refresh, then see if you can select a different Python version when creating a new environment then.
There is some issue on your system, and you'll probably need to manually install to resolve it.
You definitely should be outputting to different folders, and then looking to fix up the alignments for each extract run prior to merging.
Once the files are merged, you won't be able to use the Manual tool to fix up any issues.
Space in folder name should be fine.
I suspect that you have at least 1 image (maybe more) in your B set that is not the correct size. All the images in your training folders should be output from the extract process, and should be identical sizes.
Follow these instructions, and let us know if you are still facing the same issue:
app.php/faqpage#f1r1
This thread should help, where your specific issue is also covered (a little later on).
if you're still struggling, let us know:
An 8GB card should be more than enough to run Faceswap, but it is model dependent. It also doesn't normally just 'hang', it will usually error out if you don't have enough VRAM.
Glad you got it working though,
Basically, [mention]bryanlyon[/mention] has offered to implement this, so feel free to keep nagging him about it.
You can try running the Faceswap installer again, or you can install miniconda yourself, manually, and then run the Faceswap installer again
You'll need to be a bit more specific than that.