Faceswap Forum

jode

You can't pass config items direct from the command line, no. You can, however, pass config file paths direct from the command line. So you can just create a different config file for each of your changes, and pass the relevant path in: -C CONFIGFILE, --configfile CONFIGFILE Optionally overide the ...

jode

If I'm running extraction from command line, is there any way to add some parameters existing in extract.ini straight to the command? For example if I'm using mtcnn detector and I want to use different scalefactor than in extract.ini, is there any way to change it like adding '-scalefactor 0.8' to c...

jode

With some videos faceswap doesn't detect faces if they are too far away (even with minimum settings), too blurry or in hard angle. It's very time consuming to fix these faces with manual tool. I've done some testing with face restoration scripts with good results: First I extract faces from original...

jode

The easiest way to achieve what you are looking for (outside of the manual tool) would be: . . Sadly that's what I've done this far and making thing's easier would be in manual tool, not outside of it. But maybe some day... IIRC ths can't be disabled by default. You have to uncheck the 'show previe...

jode

How difficult would it be to add some face filter more to manual tool? I'd really like to have "only 1 face", "2 faces" and "over 2 faces". Filters existing doesn't help the way I like because "has faces" shows every frame with faces despite the amount of them...

jode

The GUI and Cli run exactly the same process, so there should be no discernible difference. Most likely, you are not running the Cli line from inside your faceswap environment. You need to do: Start > Anaconda Prompt conda activate faceswap Then execute the command line. You need to do this so that...

jode

I have wondered why extract speed is so much slower from command line than doing it from gui? From command line speed is something about 5 it/sec when making it with same settings and same videofiles from gui it's about 15-20 it/sec. That makes no sense

jode

I found one new way to find bad images from extracted B face dataset. My own presorting tool I'm making uses mask preview files to see what faces is worth to keep. I use Dupeguru to delete too similar faces. But before that, I use Dupeguru to find all 80% duplicates and when results windows opens I ...

jode

I found out how to do it with imagemagick but it's little bit clumsy. First you have to convert image to 2 color image and then use connected-components to make txt file where all objects are listed. Then read the list to define if there's two or more objects (two because background is one and face ...

jode

I maybe wrote badly (sorry my english) but if you extract images and then use mask tool to make mask preview images of extracted images, there's only one face in the image. But if there's hair over cheek, it cut's face in two parts. The main face is the biggest object and then there's backgroundcolo...

jode

Does anybody know if there's some tool that can sort images by how many objects them have? For example if mask preview picture contains only face in white background, that's 1 object. But if there's hair over cheek and it cuts face in to two parts, then it's two objects. I think this could be done s...

jode

Thanks. It'd be a nice feature to have the extract process have an option to generate (or convert the existing image) to a png with the data header but as the same full image. That way FaceSwap could be used as a general tool for sorting images by face. Extract your original images, sort them with ...

jode

I love over analysing datasets, so good work, and keep it up :) Feel free to share your script here so others can try it out. I can also look at your blur code, as the blur detection we have in Faceswap already masks out the background, so if it works well, I can look to implement it as a sort opti...

jode

I have now improved my system and I extended folders to 49 (7x7). It's necessary because folders 1-14 and 36-49 have usually so few images so there must be more folders in the middle where most of the images is grouped. I have made script that groups all extracted images to those 49 directories. The...

jode

When using rename option in alignmets tool it won't work without alignments file. But it renames filenames right even if it have wrong alignments file given. Does it really need it or is there something going wrong with images with wrong alignments file? Just to be sure before making any damage

jode

FIrst of all I had misunderstood what pitch and yaw means :oops: Those was just the right type of grouping I was looking for before. Now making trainsetmaker-script it more easier: So the process will be something like this to every B face video: After extraction I group images by face for cleaning ...

jode

Thanks for sharing. A couple of points/questions... First I use sort tool to group images by blur making 10 different bins. Then I discard blurriest image directories containing about 20% of images and there's left about 8000 sharpest images. Do you find this effective? I have found sorting by blur...

jode

Let's say the situation is that we have 5 videos which we want to use making good training set for face B. But how to choose versatile set of images from every face angle possible but not too much same type of images? I'm using this method which goes something like this: At the beginning I of course...

jode

Maybe stupid question but is it possible to train only B side? I often use same B side to different A sides. Hoping I could make B side "ready" for next project and then just load weights to make training faster. Is it possible with Phaze-A trainer?

jode

Sometimes when training, frontal faces train faster than profile faces. In preview profiles are more blurry than frontal ones. I've made new faceset from those hard training profile faces to train only them more to catch up frontal faces. Does this harm model anyway?

Faceswap Forum

Search found 24 matches

Re: Config parameters from command line

Config parameters from command line

Feature request / Tip: How to improve face detecting

Re: Manual Tool and faces filters

Manual Tool and faces filters

Re: Extract speed from command line

Extract speed from command line

Re: Image sorting tool

Re: Image sorting tool

Re: Image sorting tool

Image sorting tool

Re: Extract+Sort by face (full images, not just face)

Re: My way of creating good training set

Re: My way of creating good training set UPDATE

Alignments tool 'rename'

Re: My way of creating good training set

Re: My way of creating good training set

My way of creating good training set

Training only B side

Training with different facesets