Faceswap Forum

You are using the legacy 1.0 version of Faceswap. I assume this is an accident on your part, and you are trying to run convert on an alignments file created with a more recent version of Faceswap. Either way, with your GPU, there is no reason to use version 1.0, and it is entirely unsupported. Unins...

This looks like a version conflict to me.

In the first instance, follow all of these steps and see if that resolves your issue:
app.php/faqpage#f1r1

Just my 2 cents. Firstly this: someone in a different thread explained that it's using BOTH Warp to Landmarks and NO Warp that's correct is nonsense. Ignore it. (No warp means no warp. Doesn't matter if warp to landmarks is selected or not, it won't be used). Some people have said that disabling war...

Hate to add another post on this, as we dealt with this at an earlier time but I can't find the old post. I started a new model based on STOJO, at 512, using efficienetv2 -L (a 23Gb model 😯.) It seems the color scale hasn't been fixed. I brought this up months ago but moved on to the DNY512 model. ...

Sadly, this will likely be an issue with your video. Most likely what you see initially is correct, but, for whatever reason, the manual tool is having difficulty keeping the video frames and the alignment information synced up.

This will most likely be fixable by re-encoding the video file.

No, it's not because of lack of RAM.

It will be some specific M1 issue, which I would be unable to advise on, not owning an M1 Mac.

The best I could recommend, is to do the Mac equivalent of this: app.php/faqpage#f1r1 and hope for the best.

Ok, you're still losing me. My initial post said: > As to the miniconda issue, most likely it is a network issue when downloading. In the first instance do this: > https://forum.faceswap.dev/app.php/faqpage#f1r1 This is a link to our FAQ page which gives step by step instructions for making sure tha...

Not easily, no.

Quickest and easiest way would be just run an extract on a single image, selecting all maskers (and identity), and pick up the URLs that way.

Yes. It's why we use EG/sec. Iteration is entirely dependant on batch size. 1 iteration = 1 batch through the model.

I don't follow....

I assume you are using the installer (viewtopic.php?t=20)? In which case I mean click the "Show Details" button on this:
download/file.php?id=39

Ok, you are experiencing very strange behaviour which I have not seen before, and so I can only assume is unique to your setup/location in some way. I'm not sure what you mean by zip2/zip3. The model files are just zipped up files. There is nothing special about them. Windows should be able to unzip...

GTX 1650 will be fine. You won't be able to use some of the larger models, but it will run ok. As to the miniconda issue, most likely it is a network issue when downloading. In the first instance do this: https://forum.faceswap.dev/app.php/faqpage#f1r1 If it doesn't solve your issue, you should open...

As you found, I did start to make configuration for themes, but tkinter is quite fiddly in some areas (some parts are easy to theme, others just want to stay at stock OS colours), so I abandoned it for other priorities. If you do make more progress on this though, I would be more than happy to add i...

cv2.error: Unknown C++ exception from OpenCV code Well. That's about as vague as they come. Most likely a conflict caused by something else installed since it was last working, These steps should help: https://forum.faceswap.dev/app.php/faqpage#f1r1 I notice you are running in CPU mode. Faceswap is...

Unzip it.

Faceswap does not know if the zip file is a full file or a partial download, so it has to query the server to get the file size.

If the model is unzipped, then it doesn't need to do this test.

Super resolution on video is tricky, because GANs tend to lack temoral coherence. This means that the end result is far from satisfactory

It's hard to say without images, but you could try enabling ICNR initialization which is specifically designed to avoid the checkerboard effect.

https://arxiv.org/abs/1707.02937

The encoder is compressing an image down to a smaller representation. the Decoder enlarges the representation back up to a reconstructed image. I think you are probably thinking more about input size vs output size, in which case, encoder scaling is there to make those kinds of balances if you so wish

Unfortunately, for contractual reasons, I am unable to say.

Encoder doesn't output at image size. It outputs a feature map at reduced spatial dimension, but increased depth.

Faceswap Forum

Search found 2196 matches

Re: conversion problem

Re: failed to start trainning based on cpu: module 'numpy' has no attribute 'bool'

Re: Everything says to switch to "No Warp" eventually, but when I to, it looks clearly like the source face again.

Re: Bug - RGB/BRG

Re: When using the manual tool to adjust alignments, the alignment changes drastically when I select a frame

Re: M1 Max, Freeze on start training

Re: Cant install miniconda

Re: Faceswap hangs and wont download model?

Re: Are Iterations the same?

Re: Cant install miniconda

Re: Faceswap hangs and wont download model?

Re: Cant install miniconda

Re: Basic Dark Mode Theme

Re: Extracting error

Re: Faceswap hangs and wont download model?

Re: Super Resolution on low quality video

Re: Weird Checkerboard effect

Re: [Guide] Introducing - Phaze-A

Re: Synthetic Faceset for Deepfakes

Re: [Guide] Introducing - Phaze-A